HENGCDHENGCD INDUSTRIAL AI
Consulta de proyectoIniciar sesión
InicioSolucionesServiciosPreciosCentro de descargasFacturaciónActualizacionesNosotrosTablón de mensajesConsulta de proyectoIniciar sesión

MODEL PRICING

Precios y puntos claros

Consulte en una sola página los precios, la integración del conector y las condiciones de disponibilidad. El acceso real depende de la clave API y la ruta del servidor.

01

Contenido

Consulte en una sola página los precios, la integración del conector y las condiciones de disponibilidad. El acceso real depende de la clave API y la ruta del servidor.

Esta página es un resumen traducido. La versión china rige los detalles técnicos y contractuales.

Catálogo público613modelos, incluidos candidatos
Conector HCD Codex91modelos incluidos
Estudio de imágenes25modelos incluidos
Estudio de audio17modelos incluidos
Estudio de voz en tiempo real7modelos incluidos
Estudio de vídeo32modelos incluidos
Estudio de documentos6modelos incluidos
Estudio de conocimiento26modelos incluidos
Estudio 3D3modelos incluidos
Estudio de texto y código2modelos incluidos

Las cifras proceden de las listas publicadas de cada acceso, sin duplicados dentro de un estudio. Un modelo puede aparecer en varios estudios. El acceso y las funciones dependen de los permisos de la clave API, las rutas del servidor y las especificaciones del modelo.

Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.

Las tarifas Token se muestran por millón de Tokens. Otras capacidades usan la unidad indicada. Los tramos siguen la tarifa de cada modelo. La cuenta refleja el consumo real; el coeficiente de API Key solo se aplica a los puntos de la clave. Los servicios habilitados descuentan puntos según el uso real. La recarga en línea y la emisión de facturas siguen sin estar disponibles.

ModeloConsumo de puntos

Se priorizan los modelos independientes. Una instantánea o alias solo se incluye si es el único acceso disponible de la misma plataforma, generación y familia de capacidades. Todos los tipos permite consultar las demás versiones con sus propios códigos, precios y estados. Las pruebas pendientes no significan indisponibilidad. Las voces y servicios no son nuevos modelos base. La clasificación conserva las rutas API y certificaciones.

Mostrados / total: 482 / 613
Claude Haiku 5.5claude-haiku-5-5Modelo independienteAnthropic · Estable2026-10-07Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento—Rendimiento/precio—
Sin evaluar
Uso de entrada · por millón de Tokens200.000 puntosUso por aciertos de caché · por millón de Tokens20.000 puntosUso de escritura caché · 5m · por millón de Tokens250.000 puntosUso de escritura caché · 1h · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens1.000.000 puntosBúsqueda web · por 1.000 unidades de búsqueda20.000.000 puntos
Claude Haiku 5.5-100claude-haiku-5-5-100Modelo independienteAnthropic · Estable2026-10-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.7Rendimiento/precio · Estimated82.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basisSin evaluar · Confidence 0%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Gemini Nano Banana 2.1-100gemini-nano-banana-2.1Modelo independienteGoogle · Estable2026-10-06Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento92.5Rendimiento/precio · Estimated66.5
ProvisionalSin evaluar · Confidence 0%
Uso de entrada · por millón de Tokens3.000.000 puntosUso de entrada · Imagen · por millón de Tokens3.000.000 puntosUso por aciertos de caché · por millón de Tokens300.000 puntosUso de salida · por millón de Tokens15.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens300.000 puntosUso de salida · Imagen · por millón de Tokens60.000.000 puntos
Qwen-Image-2.1-Proqwen-image-2.1-proModelo independienteQwen · Estable2026-10-02Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent
Uso de salida · Imagen · por imagen68.494 puntos
Grok 4.7-100grok-4.7-100Modelo independientexAI · Vista previa2026-09-30Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento—Rendimiento/precio—
Sin evaluar
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens1.000.000 puntosUso de salida · por millón de Tokens12.000.000 puntos
GPT-6.1 Solgpt-6.1-solModelo independienteOpenAI · Estable2026-09-29Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated82.2Rendimiento/precio · Estimated69.2
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.4 (estimated) · 5/19 observed / reasoning 85.3 (estimated) · 3/13 observed / writing 84.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-6-astra · 1 benchmarksReference: gpt-6-luna · 1 benchmarksReference: gpt-6-sol · 1 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens200.000 puntosUso de escritura caché · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
Claude Sonnet 5.5claude-sonnet-5-5Modelo independienteAnthropic · Estable2026-09-28Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated74.4Rendimiento/precio · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 5/19 observed / reasoning 78.8 (estimated) · 3/13 observed / writing 59.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de escritura caché · 5m · por millón de Tokens5.000.000 puntosUso de escritura caché · 1h · por millón de Tokens8.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntosBúsqueda web · por 1.000 unidades de búsqueda20.000.000 puntos
Claude Sonnet 5.5-100claude-sonnet-5-5-100Modelo independienteAnthropic · Estable2026-09-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.4Rendimiento/precio · Estimated67.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 84.5 (estimated) · 0/19 observed / reasoning 78.8 (estimated) · 0/13 observed / writing 59.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5-5 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

决策模型（预览版）decision-model-previewModelo independienteQwen · Estable2026-09-24Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens0 puntos
Gemini 3.8 Live-100gemini-3.8-liveModelo independienteGoogle · Estable2026-09-24Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated76.9Rendimiento/precio · Estimated68.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.9 (estimated) · 0/19 observed / reasoning 76.8 (estimated) · 0/13 observed / writing 87.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.8-flash-high · 7 benchmarksReference: gemini-4-argon-high · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.500.000 puntosEntrada de vídeo · por millón de Tokens2.000.000 puntosUso de entrada · Audio · por millón de Tokens6.000.000 puntosUso de salida · por millón de Tokens9.000.000 puntosUso de salida · Audio · por millón de Tokens24.000.000 puntosUso de salida · Generación de vídeo · por millón de Tokens2.000.000 puntos
Claude Opus 5.5claude-opus-5-5Modelo independienteAnthropic · Estable2026-09-22Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated86.9Rendimiento/precio · Estimated69.6
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 5/19 observed / reasoning 94.0 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de escritura caché · 5m · por millón de Tokens10.000.000 puntosUso de escritura caché · 1h · por millón de Tokens16.000.000 puntosUso de salida · por millón de Tokens40.000.000 puntosBúsqueda web · por 1.000 unidades de búsqueda20.000.000 puntos
Claude Opus 5.5-100claude-opus-5-5-100Modelo independienteAnthropic · Estable2026-09-22Sin precio fijo; facturación según el servicio
Rendimiento · Estimated86.9Rendimiento/precio · Estimated75.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 91.4 (estimated) · 0/19 observed / reasoning 94.0 (estimated) · 0/13 observed / writing 75.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-5-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-6 Lunagpt-6-lunaModelo independienteOpenAI · Estable2026-09-22Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.4Rendimiento/precio · Estimated65.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.8 (estimated) · 5/19 observed / reasoning 64.0 (estimated) · 4/13 observed / writing 50.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-luna by 4.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens200.000 puntosUso por aciertos de caché · por millón de Tokens20.000 puntosUso de escritura caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens1.000.000 puntos
GPT-6 Solgpt-6-solModelo independienteOpenAI · Estable2026-09-22Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated74.3Rendimiento/precio · Estimated63.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 74.6 (estimated) · 5/19 observed / reasoning 78.4 (estimated) · 4/13 observed / writing 69.9 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.6-sol by 8.8 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de escritura caché · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
Grok 4.7grok-4.7Modelo independientexAI · Estable2026-09-21Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento—Rendimiento/precio—
Sin evaluar
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens1.000.000 puntosUso de salida · por millón de Tokens12.000.000 puntos
Qwen-Audio-3.1-Realtime-Plusqwen-audio-3.1-realtime-plusModelo independienteQwen · Estable2026-09-20Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.8-Livetranslate-Flash-Realtimeqwen3.8-livetranslate-flash-realtimeModelo independienteQwen · Estable2026-09-18Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Uniqwen-mt-uniModelo independienteQwen · Estable2026-09-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated49.4Rendimiento/precio · Estimated49.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.5 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 47.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-14b-chat · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-kimi/kimi-k2.8-previewqwen-kimi-kimi-k2.8-previewModelo independienteMoonshot AI · Estable2026-09-11Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens465.753 puntosUso de salida · por millón de Tokens7.397.260 puntos
DeepSeek V4.1 Flashdeepseek-flashModelo independienteDeepSeek · Estable2026-09-10Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated78.1Rendimiento/precio · Estimated77.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.2 (estimated) · 4/19 observed / reasoning 82.4 (estimated) · 4/13 observed / writing 70.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksEstimated value uses this exact model's reviewed off-peak public point rates and the shared text workload. Weekday peak rates double; public holidays use off-peak rates. It is not a measured charge.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens300.000 puntosUso por aciertos de caché · por millón de Tokens6000 puntosUso de salida · por millón de Tokens1.200.000 puntos
doubao-deepseek-v4-1-flashdoubao-deepseek-v4-1-flash-260910Instantánea / versión fija · Acceso únicoDeepSeek · Estable2026-09-10Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens273.973 puntosUso por aciertos de caché · por millón de Tokens5479 puntosUso de salida · por millón de Tokens1.095.890 puntos
qwen-DeepSeek V4.1 Flashqwen-deepseek-v4.1-flashModelo independienteDeepSeek · Estable2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.4Rendimiento/precio · Estimated66.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens273.973 puntosUso por aciertos de caché · por millón de Tokens27.397 puntosUso de salida · por millón de Tokens1.095.890 puntos
qwen-vanchin/deepseek-v4.1-flashqwen-vanchin-deepseek-v4.1-flashModelo independienteDeepSeek · Estable2026-09-10Sin precio fijo; facturación según el servicio
Rendimiento · Estimated61.4Rendimiento/precio · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT Image 2.5 Flaregpt-image-2.5-flareModelo independienteOpenAI · Estable2026-09-08Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento98.5Rendimiento/precio70.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens2.500.000 puntosUso de entrada · Imagen · por millón de Tokens16.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens4.000.000 puntosUso de salida · Imagen · por millón de Tokens60.000.000 puntos
GPT Image 2.5 Sunburstgpt-image-2.5-sunburstModelo independienteOpenAI · Estable2026-09-08Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento100.0Rendimiento/precio71.4
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens2.500.000 puntosUso de entrada · Imagen · por millón de Tokens16.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens4.000.000 puntosUso de salida · Imagen · por millón de Tokens60.000.000 puntos
GPT-6 Astragpt-6-astraModelo independienteOpenAI · Estable2026-09-03Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated85.4Rendimiento/precio · Estimated64.8
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 79.9 (estimated) · 5/19 observed / reasoning 92.0 (estimated) · 4/13 observed / writing 84.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens20.000.000 puntosUso por aciertos de caché · por millón de Tokens2.000.000 puntosUso de escritura caché · por millón de Tokens25.000.000 puntosUso de salida · por millón de Tokens100.000.000 puntos
Gemini 3.8 Flash-100gemini-3.8-flash-100Modelo independienteGoogle · Estable2026-09-02Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento—Rendimiento/precio—
Sin evaluar
Uso de entrada · por millón de Tokens3.000.000 puntosUso de entrada · Imagen · por millón de Tokens3.000.000 puntosUso de entrada · Audio · por millón de Tokens3.000.000 puntosEntrada de vídeo · por millón de Tokens3.000.000 puntosUso por aciertos de caché · por millón de Tokens300.000 puntosUso de salida · por millón de Tokens15.000.000 puntosUso de escritura caché · por millón de Tokens3.000.000 puntosAlmacenamiento de caché explícita · por millón de tokens-hora2.000.000 puntos
Claude Fable 5.1claude-fable-5-1Modelo independienteAnthropic · Estable2026-09-01Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated89.2Rendimiento/precio · Estimated67.4
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens20.000.000 puntosUso por aciertos de caché · por millón de Tokens500.000 puntosUso de escritura caché · 5m · por millón de Tokens25.000.000 puntosUso de escritura caché · 1h · por millón de Tokens40.000.000 puntosUso de salida · por millón de Tokens100.000.000 puntosBúsqueda web · por 1.000 unidades de búsqueda20.000.000 puntos
Claude Fable 5.1-100claude-fable-5-1-100Modelo independienteAnthropic · Estable2026-09-01Sin precio fijo; facturación según el servicio
Rendimiento · Estimated89.2Rendimiento/precio—
Shared exact-model performance from claude-fable-5-1; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 90.5 (estimated) · 5/19 observed / reasoning 93.8 (estimated) · 4/13 observed / writing 83.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Doubao-Seed-2.1-Litedoubao-seed-2-1-lite-260915Instantánea / versión fija · Acceso únicoDoubao · Estable2026-09 (solo mes oficial)Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated63.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens739.726 puntos
doubao-seedream-5-0-flashdoubao-seedream-5-0-flash-260915Instantánea / versión fija · Acceso únicoDoubao · Estable2026-09 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated65.8Rendimiento/precio · Estimated61.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-lite · 50.2Reference: seedream-5.0-pro · 85.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

千问3.7-通用文本向量-flashqwen3.7-text-embedding-flashModelo independienteAlibaba Cloud · Estable2026-09-01Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated73.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens34.247 puntos
千问3.7-通用文本重排序qwen3.7-text-rerankModelo independienteAlibaba Cloud · Estable2026-09-01Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated72.5Rendimiento/precio · Estimated80.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official
Uso de entrada · por millón de Tokens136.987 puntos
Qwen3.8-Omni-Flashqwen3.8-omni-flashModelo independienteQwen · Estable2026-09 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated61.4Rendimiento/precio · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.8-Omni-Flash-Realtimeqwen3.8-omni-flash-realtimeModelo independienteQwen · Estable2026-09 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Image-2.0qwen-mt-image-2.0Modelo independienteQwen · Estable2026-08-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated73.8Rendimiento/precio · Estimated66.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Cohere Parse v5cohere-parse-v5Modelo independienteCohere · Vista previa2026-08-27Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento79.2Rendimiento/precio85.4
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · Official
Procesamiento documental · por 1.000 páginas3.000.000 puntos
Gemini Omni 1.1 Flash Preview-100gemini-omni-1.1-flash-previewModelo independienteGoogle · Estable2026-08-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated49.9Rendimiento/precio · Estimated49.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.2 (estimated) · 0/19 observed / reasoning 44.4 (estimated) · 0/13 observed / writing 59.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-high · 7 benchmarksReference: gemini-1.5-flash-001 · 4 benchmarksReference: gemini-1.5-flash-002 · 4 benchmarksReference: gemini-1.5-flash-8b-001 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ZHIPU/GLM-5.3-Flashqwen-zhipu-glm-5.3-flashModelo independienteZhipu AI · Estable2026-08-26Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated48.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens63.014 puntosUso de salida · por millón de Tokens767.123 puntos
Qwen3.8-Flashqwen3.8-flashModelo independienteQwen · Estable2026-08-25Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.4Rendimiento/precio · Estimated67.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens27.397 puntosUso de salida · por millón de Tokens739.726 puntos
qwen-Kimi-K3qwen-kimi-k3Modelo independienteMoonshot · Estable2026-08-19Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated39.7Rendimiento/precio · Estimated38.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 35.6 (estimated) · 0/19 observed / reasoning 49.2 (estimated) · 0/13 observed / writing 34.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens5.479.452 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens27.397.260 puntos
Qwen3.8-27Bqwen3.8-27bModelo independienteQwen · Estable2026-08-17Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated65.0Rendimiento/precio · Estimated64.2
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 5/19 observed / reasoning 68.3 (estimated) · 4/13 observed / writing 62.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens164.384 puntosUso de salida · por millón de Tokens3.287.671 puntos
qwen-GLM-5.3qwen-glm-5.3Modelo independienteZhipu AI · Estable2026-08-14Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.1Rendimiento/precio · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
qwen-ZHIPU/GLM-5.3qwen-zhipu-glm-5.3Modelo independienteZhipu AI · Estable2026-08-14Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
DeepSeek V4 Prodeepseek-v4-proModelo independienteDeepSeek · Estable2026-08-13Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated64.4Rendimiento/precio · Estimated62.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 74.3 (estimated) · 0/13 observed / writing 65.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: deepseek-v4-pro · 7 benchmarksReference: deepseek-v4-pro-0813 · 7 benchmarksReference: deepseek-v4-pro · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.320.000 puntosUso por aciertos de caché · por millón de Tokens44.000 puntosUso de salida · por millón de Tokens3.960.000 puntos
GLM-5.3glm-5.3Modelo independienteZhipu · Estable2026-08-13Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated71.7Rendimiento/precio · Estimated65.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.9 (estimated) · 0/19 observed / reasoning 71.1 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.3 · 7 benchmarksReference: glm-5.2 · 6 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
GLM-5.3-Flashglm-5.3-flashModelo independienteZhipu · Estable2026-08-13Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated65.1Rendimiento/precio · Estimated70.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.5 (estimated) · 0/19 observed / reasoning 68.7 (estimated) · 0/13 observed / writing 57.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: glm-5.3-flash · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens63.014 puntosUso de salida · por millón de Tokens767.123 puntos
Grok 4.6grok-4.6Modelo independientexAI · Vista previa2026-08-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated70.4Rendimiento/precio · Estimated61.9
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens2.000.000 puntosUso de salida · por millón de Tokens24.000.000 puntos
Grok 4.6-100grok-4.6-100Modelo independientexAI · Estable2026-08-12Sin precio fijo; facturación según el servicio
Rendimiento · Estimated70.4Rendimiento/precio—
Shared exact-model performance from grok-4.6; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.3 (estimated) · 5/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 73.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

MAI Thinking 1mai-thinking-1Modelo independienteMicrosoft AI · Vista previa2026-08-12Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated51.7
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 4/19 observed / reasoning 60.2 (estimated) · 5/13 observed / writing 52.8 (estimated) · 3/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens16.000.000 puntos
Qwen3.8-2.4T-A95Bqwen3.8-2.4t-a95bModelo independienteQwen · Estable2026-08-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated65.0Rendimiento/precio · Estimated58.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 0/19 observed / reasoning 68.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens410.959 puntosUso de salida · por millón de Tokens9.863.014 puntos
万相3.0-视频生成wan3.0-videoModelo independienteAlibaba Cloud · Estable2026-08-06Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated92.6Rendimiento/precio · Estimated72.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan3.0 · 92.6arena · Independentarena · Independent
Generación de vídeo 480P · por segundo57.535 puntosGeneración de vídeo 720P · por segundo115.069 puntosGeneración de vídeo 1080P · por segundo230.137 puntos
Qwen3.8-Maxqwen3.8-maxModelo independienteQwen · Estable2026-08-02Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated76.0Rendimiento/precio · Estimated66.6
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 70.3 (estimated) · 5/19 observed / reasoning 82.3 (estimated) · 4/13 observed / writing 75.4 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens410.959 puntosUso de salida · por millón de Tokens9.863.014 puntos
Gemini 3.5 Transcribe Live Preview-100gemini-3.5-transcribe-live-previewModelo independienteGoogle · Estable2026-08 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Gemini 3.5 Transcribe Preview-100gemini-3.5-transcribe-previewModelo independienteGoogle · Estable2026-08 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-DeepSeek V4 Flash GA (2026-07-31)doubao-deepseek-v4-flash-ga-260731Instantánea / versión fija · Acceso únicoDeepSeek · Estable2026-07-31Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated58.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens27.397 puntosUso de salida · por millón de Tokens2.465.753 puntos
qwen-MiniMax/MiniMax-H3qwen-minimax-minimax-h3Modelo independientemini-max · Estable2026-07-31Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.0-ASR-Flashqwen-audio-3.0-asr-flashModelo independienteAlibaba Cloud · Estable2026-07-30Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated94.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Transcripción · por segundo61 puntos
qwen-audio-3.0-asr-flash-filetransqwen-audio-3.0-asr-flash-filetransModelo independienteQwen · Estable2026-07-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.0-ASR-Flash-Streamingqwen-audio-3.0-asr-flash-streamingModelo independienteQwen · Estable2026-07-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT Live Transcribegpt-live-transcribeModelo independienteOpenAI · Estable2026-07-28Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated64.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Transcripción · por hora2.040.000 puntos
GPT Transcribegpt-transcribeModelo independienteOpenAI · Estable2026-07-28Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated81.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Transcripción · por hora540.000 puntos
qwen-PixVerse-V6-r2v-omniqwen-pixverse-pixverse-v6-r2v-omniModelo independientepixverse · Estable2026-07-26Sin precio fijo; facturación según el servicio
Rendimiento · Estimated61.1Rendimiento/precio · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Claude Opus 5claude-opus-5Modelo independienteAnthropic · Estable2026-07-24Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated81.9Rendimiento/precio · Estimated65.2
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens1.000.000 puntosUso de escritura caché · 5m · por millón de Tokens12.500.000 puntosUso de escritura caché · 1h · por millón de Tokens20.000.000 puntosUso de salida · por millón de Tokens50.000.000 puntos
Claude Opus 5-100claude-opus-5-100Modelo independienteAnthropic · Estable2026-07-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated81.9Rendimiento/precio—
Shared exact-model performance from claude-opus-5; coverage refers to public model benchmarks, not tests of every platform deployment.Version comparison review13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.2 (estimated) · 5/19 observed / reasoning 86.3 (estimated) · 4/13 observed / writing 74.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-opus-5-5-100 by 5.0 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Gemini 3.5 Flash-Lite-100gemini-3.5-flash-lite-100Modelo independienteGoogle · Estable2026-07-21Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated52.3Rendimiento/precio · Estimated55.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.1 (estimated) · 0/19 observed / reasoning 52.8 (estimated) · 0/13 observed / writing 56.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.5-flash-lite-high · 7 benchmarksReference: gemini-3.5-flash-lite · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens600.000 puntosUso por aciertos de caché · por millón de Tokens60.000 puntosUso de salida · por millón de Tokens5.000.000 puntos
Qwen3.7-Flashqwen3.7-flashModelo independienteQwen · Estable2026-07-21Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.4Rendimiento/precio · Estimated73.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 32.000 TokenUso de entrada · por millón de Tokens54.795 puntosUso por aciertos de caché · por millón de Tokens10.959 puntosUso de salida · por millón de Tokens219.178 puntos
Input 32.001 – 256.000 TokenUso de entrada · por millón de Tokens164.384 puntosUso por aciertos de caché · por millón de Tokens32.877 puntosUso de salida · por millón de Tokens657.534 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens65.753 puntosUso de salida · por millón de Tokens1.315.068 puntos
Qwen-Image-3.0qwen-image-3.0Modelo independienteAlibaba Cloud · Estable2026-07-21Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated73.8Rendimiento/precio · Estimated81.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · Independent
Imagen Uso de entrada 1K · por imagen5480 puntosImagen Uso de entrada 2K · por imagen5480 puntosImagen Uso de salida 1K · por imagen49.316 puntosImagen Uso de salida 2K · por imagen49.316 puntos
Kimi K3kimi-k3Modelo independienteMoonshot · Estable2026-07-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.1Rendimiento/precio · Estimated66.4
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 81.7 (estimated) · 5/19 observed / reasoning 80.2 (estimated) · 4/13 observed / writing 78.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens5.479.452 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens27.397.260 puntos
qwen-kimi/kimi-k3qwen-kimi-kimi-k3Modelo independienteMoonshot AI · Estable2026-07-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens5.479.452 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens27.397.260 puntos
Qwen3.7-通用文本向量qwen3.7-text-embeddingModelo independienteAlibaba Cloud · Estable2026-07-15Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated53.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens136.987 puntos
Qwen-Audio-3.0-Realtime-Flashqwen-audio-3.0-realtime-flashModelo independienteQwen · Estable2026-07-14Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.0-Realtime-Plusqwen-audio-3.0-realtime-plusModelo independienteQwen · Estable2026-07-14Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5.6 Lunagpt-5.6-lunaModelo independienteOpenAI · Estable2026-07-09Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated63.7Rendimiento/precio · Estimated65.5
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.4 (estimated) · 4/19 observed / reasoning 72.6 (estimated) · 4/13 observed / writing 54.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens400.000 puntosUso por aciertos de caché · por millón de Tokens40.000 puntosUso de escritura caché · por millón de Tokens500.000 puntosUso de salida · por millón de Tokens2.400.000 puntos
GPT-5.6 Solgpt-5.6-solModelo independienteOpenAI · Estable2026-07-09Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated83.1Rendimiento/precio · Estimated67.0
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.4 (estimated) · 4/19 observed / reasoning 89.4 (estimated) · 4/13 observed / writing 82.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens800.000 puntosUso de escritura caché · por millón de Tokens10.000.000 puntosUso de salida · por millón de Tokens40.000.000 puntos
GPT-5.6 Terragpt-5.6-terraModelo independienteOpenAI · Estable2026-07-09Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated73.1Rendimiento/precio · Estimated62.5
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 65.0 (estimated) · 4/19 observed / reasoning 85.1 (estimated) · 4/13 observed / writing 69.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.6-luna-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-sol-xhigh (codex-harness) · 1 benchmarksReference: gpt-5.6-terra-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de escritura caché · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens24.000.000 puntos
gpt-live-1gpt-live-1Modelo independienteOpenAI · Estable2026-07-08Sin precio fijo; facturación según el servicio
Rendimiento · Estimated48.3Rendimiento/precio · Estimated48.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.4 (estimated) · 0/19 observed / reasoning 52.2 (estimated) · 0/13 observed / writing 41.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4-0125-preview · 10 benchmarksReference: gpt-4-1106-preview · 10 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4o · 7 benchmarksReference: gpt-5.2 · 7 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT Realtime 2.1gpt-realtime-2.1Modelo independienteOpenAI · Vista previa2026-07-06Voz y texto en tiempo real disponibles. Las imágenes y la ejecución de herramientas durante la llamada no están habilitadas.Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated45.3Rendimiento/precio · Estimated31.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · Official
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens800.000 puntosUso de salida · por millón de Tokens48.000.000 puntosUso de entrada · Imagen · por millón de Tokens10.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens1.000.000 puntosUso de entrada · Audio · por millón de Tokens64.000.000 puntosUso por aciertos de caché · Audio · por millón de Tokens800.000 puntosUso de salida · Audio · por millón de Tokens128.000.000 puntos
GPT Realtime 2.1 Minigpt-realtime-2.1-miniModelo independienteOpenAI · Vista previa2026-07-06Voz y texto en tiempo real disponibles. Las imágenes y la ejecución de herramientas durante la llamada no están habilitadas.Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated45.3Rendimiento/precio · Estimated61.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · Official
Uso de entrada · por millón de Tokens1.200.000 puntosUso por aciertos de caché · por millón de Tokens120.000 puntosUso de salida · por millón de Tokens4.800.000 puntosUso de entrada · Imagen · por millón de Tokens1.600.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens160.000 puntosUso de entrada · Audio · por millón de Tokens20.000.000 puntosUso por aciertos de caché · Audio · por millón de Tokens600.000 puntosUso de salida · Audio · por millón de Tokens40.000.000 puntos
Qwen-Audio-3.0-TTS-Flashqwen-audio-3.0-tts-flashModelo independienteAlibaba Cloud · Estable2026-07 (solo mes oficial)Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated74.4Rendimiento/precio · Estimated74.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official
Audio · por 10.000 caracteres273.973 puntos
Qwen-Audio-3.0-TTS-Plusqwen-audio-3.0-tts-plusModelo independienteAlibaba Cloud · Estable2026-07 (solo mes oficial)Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated74.4Rendimiento/precio · Estimated63.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official
Audio · por 10.000 caracteres383.562 puntos
claude-sonnet-5claude-sonnet-5Modelo independienteAnthropic · Estable2026-06-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated70.2Rendimiento/precio · Estimated64.1
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 5/19 observed / reasoning 76.6 (estimated) · 4/13 observed / writing 58.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-sonnet-5-100claude-sonnet-5-100Modelo independienteAnthropic · Estable2026-06-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated70.2Rendimiento/precio · Estimated64.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 76.0 (estimated) · 0/19 observed / reasoning 76.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-sonnet-5-5-100 by 4.2 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Doubao Seed 2.1 Turbo (2026-06-28)doubao-seed-2-1-turbo-260628Instantánea / versión fija · Acceso únicoByteDance · Estable2026-06-28Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated57.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens164.384 puntosUso de salida · por millón de Tokens4.109.589 puntos
Mistral OCR 4mistral-ocr-4-0Modelo independienteMistral AI · Vista previa2026-06-23Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento81.8Rendimiento/precio57.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Officialcohere-parsebench · Official
Procesamiento documental · por 1.000 páginas8.000.000 puntosDocumentos con anotaciones estructuradas · por 1.000 páginas10.000.000 puntos
HappyHorse-1.1-I2Vhappyhorse-1.1-i2vModelo independienteAlibaba Cloud · Estable2026-06-22Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 480P · por segundo123.288 puntosGeneración de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo328.768 puntos
HappyHorse-1.1-R2Vhappyhorse-1.1-r2vModelo independienteAlibaba Cloud · Estable2026-06-22Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 480P · por segundo123.288 puntosGeneración de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo328.768 puntos
HappyHorse-1.1-T2Vhappyhorse-1.1-t2vModelo independienteAlibaba Cloud · Estable2026-06-22Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 480P · por segundo123.288 puntosGeneración de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo328.768 puntos
doubao-GLM 5.2 (2026-06-17)doubao-glm-5-2-260617Instantánea / versión fija · Acceso únicoZhipu · Estable2026-06-17Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
qwen-HappyOyster-1.0-Adventureqwen-happyoyster-1.0-adventureModelo independientehappyoyster · Estable2026-06-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated43.2Rendimiento/precio · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GLM-5.2glm-5.2Modelo independienteZhipu · Estable2026-06-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.3
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 68.8 (estimated) · 5/19 observed / reasoning 70.9 (estimated) · 4/13 observed / writing 59.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
Qwen3.5-OCRqwen3.5-ocrModelo independienteAlibaba Cloud · Estable2026-06-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated81.8Rendimiento/precio · Estimated72.3
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · Official
Uso de entrada · por millón de Tokens136.987 puntosUso de salida · por millón de Tokens547.946 puntos
qwen-GLM-5.2qwen-glm-5.2Modelo independienteZhipu · Estable2026-06-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.1Rendimiento/precio · Estimated57.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
qwen-pixverse/pixverse-upscaleqwen-pixverse-pixverse-upscaleModelo independientepixverse · Estable2026-06-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ZHIPU/GLM-5.2qwen-zhipu-glm-5.2Modelo independienteZhipu AI · Estable2026-06-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
qwen-kimi-k2.7-codeqwen-kimi-k2.7-codeModelo independienteMoonshot · Estable2026-06-15Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated34.7Rendimiento/precio · Estimated39.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.4 (estimated) · 0/13 observed / writing 28.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens356.164 puntosUso de salida · por millón de Tokens7.397.260 puntos
Kimi K2.7 Codekimi-k2.7-codeModelo independienteMoonshot · Estable2026-06-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated46.3Rendimiento/precio · Estimated47.8
8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.8 (estimated) · 3/19 observed / reasoning 48.4 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens356.164 puntosUso de salida · por millón de Tokens7.397.260 puntos
qwen-kimi/kimi-k2.7-codeqwen-kimi-kimi-k2.7-codeModelo independienteMoonshot AI · Estable2026-06-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated29.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens356.164 puntosUso de salida · por millón de Tokens7.397.260 puntos
claude-fable-5claude-fable-5Modelo independienteAnthropic · Estable2026-06-09Sin precio fijo; facturación según el servicio
Rendimiento · Estimated87.7Rendimiento/precio · Estimated76.4
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 5/19 observed / reasoning 90.7 (estimated) · 4/13 observed / writing 86.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-fable-5-100claude-fable-5-100Modelo independienteAnthropic · Estable2026-06-09Sin precio fijo; facturación según el servicio
Rendimiento · Estimated87.7Rendimiento/precio · Estimated76.4
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 85.6 (estimated) · 0/19 observed / reasoning 90.7 (estimated) · 0/13 observed / writing 86.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-fable-5 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below claude-fable-5-1-100 by 1.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.7-Max-2026-06-08qwen3.7-max-2026-06-08Instantánea / versión fija · Acceso únicoQwen · Estable2026-06-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated64.5Rendimiento/precio · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 69.6 (estimated) · 0/13 observed / writing 73.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens657.534 puntosUso de salida · por millón de Tokens9.863.014 puntos
doubao-seedance-2-5-260628doubao-seedance-2-5-260628Instantánea / versión fija · Acceso únicoByteDance · Estable2026-06 (solo mes oficial)Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated90.4Rendimiento/precio · Estimated63.3
Version comparison review
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.5-720p · 90.4Review: below doubao-seedance-2-0-260128 by 1.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independent
Uso de salida · Generación de vídeo · por millón de Tokens19.178.083 puntos
doubao-seed-evolvingdoubao-seed-evolvingAlias · Acceso únicoDoubao · Estable2026-06 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-seedream-5-0-pro-260628doubao-seedream-5-0-pro-260628Instantánea / versión fija · Acceso únicoByteDance · Estable2026-06 (solo mes oficial)Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated85.2Rendimiento/precio · Estimated69.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-5.0-pro · 85.2arena · Independentarena · Independent
Uso de salida · Imagen · por imagen82.192 puntosUso de entrada · Imagen · por imagen5480 puntos
Fun-ASR-Flash-2026-06-15fun-asr-flash-2026-06-15Instantánea / versión fija · Acceso únicoAlibaba Cloud · Estable2026-06 (solo mes oficial)Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated94.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Transcripción · por segundo61 puntos
Qwen3.7-Plusqwen3.7-plusModelo independienteQwen · Estable2026-06-01Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.0Rendimiento/precio · Estimated60.5
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.7 (estimated) · 2/19 observed / reasoning 62.0 (estimated) · 1/13 observed / writing 55.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 256.000 TokenUso de entrada · por millón de Tokens438.356 puntosUso por aciertos de caché · por millón de Tokens87.671 puntosUso de salida · por millón de Tokens1.753.425 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens1.315.068 puntosUso por aciertos de caché · por millón de Tokens263.014 puntosUso de salida · por millón de Tokens5.260.274 puntos
qwen-MiniMax/MiniMax-M3qwen-minimax-minimax-m3Modelo independientemini-max · Estable2026-06-01Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated46.0
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksReview: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.150.685 puntosUso por aciertos de caché · por millón de Tokens230.137 puntosUso de salida · por millón de Tokens4.602.740 puntos
qwen-stepfun/step-3.7-flashqwen-stepfun-step-3.7-flashModelo independientestepfun · Estable2026-05-29Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.4Rendimiento/precio · Estimated64.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 61.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens369.863 puntosUso por aciertos de caché · por millón de Tokens73.973 puntosUso de salida · por millón de Tokens2.219.178 puntos
claude-opus-4-8claude-opus-4-8Modelo independienteAnthropic · Estable2026-05-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.3Rendimiento/precio · Estimated67.0
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 5/19 observed / reasoning 77.9 (estimated) · 4/13 observed / writing 72.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-opus-4-8-100claude-opus-4-8-100Modelo independienteAnthropic · Estable2026-05-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.3Rendimiento/precio · Estimated67.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 72.3 (estimated) · 0/19 observed / reasoning 77.9 (estimated) · 0/13 observed / writing 72.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-8 · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.7-Maxqwen3.7-maxModelo independienteQwen · Estable2026-05-21Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated64.5Rendimiento/precio · Estimated58.6
8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 3/19 observed / reasoning 69.6 (estimated) · 3/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max-preview · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarkslivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independent
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens657.534 puntosUso de salida · por millón de Tokens9.863.014 puntos
Cohere Command A Pluscohere-command-a-plus-05-2026Modelo independienteCohere · Vista previa2026-05-20Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated55.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.600.000 puntosUso de salida · por millón de Tokens6.400.000 puntos
Qwen3.7-Max-Previewqwen3.7-max-previewModelo independienteQwen · Vista previa2026-05-20Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated64.5Rendimiento/precio · Estimated58.6
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 1/19 observed / reasoning 69.6 (estimated) · 1/13 observed / writing 73.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens9.863.014 puntos
Qwen3.5-LiveTranslate-Flash-Realtimeqwen3.5-livetranslate-flash-realtimeModelo independienteQwen · Estable2026-05-19Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Grok 4.3grok-4.3Modelo independientexAI · Vista previa2026-05-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated44.8Rendimiento/precio · Estimated46.5
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens5.000.000 puntos
Mistral Medium 3.5mistral-medium-3-5Modelo independienteMistral AI · Vista previa2026-04-28Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated60.6Rendimiento/precio · Estimated55.3
6/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 3/19 observed / reasoning 70.3 (estimated) · 1/13 observed / writing 61.1 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officiallivebench · Independent
Uso de entrada · por millón de Tokens3.000.000 puntosUso de salida · por millón de Tokens15.000.000 puntos
HappyHorse-1.0-I2Vhappyhorse-1.0-i2vModelo independienteAlibaba Cloud · Estable2026-04-27Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo438.357 puntos
HappyHorse-1.0-R2Vhappyhorse-1.0-r2vModelo independienteAlibaba Cloud · Estable2026-04-27Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo438.357 puntos
HappyHorse-1.0-T2Vhappyhorse-1.0-t2vModelo independienteAlibaba Cloud · Estable2026-04-27Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.9Rendimiento/precio · Estimated56.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9arena · Independentarena · Independent
Generación de vídeo 720P · por segundo246.576 puntosGeneración de vídeo 1080P · por segundo438.357 puntos
qwen-DeepSeek-V4-Proqwen-deepseek-v4-proModelo independienteDeepSeek · Estable2026-04-24Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated70.1Rendimiento/precio · Estimated63.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.8 (estimated) · 0/19 observed / reasoning 74.5 (estimated) · 0/13 observed / writing 69.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-27b · 13 benchmarksReference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens3.287.671 puntosUso por aciertos de caché · por millón de Tokens273.973 puntosUso de salida · por millón de Tokens6.575.342 puntos
GPT-5.5gpt-5.5Modelo independienteOpenAI · Estable2026-04-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated80.5Rendimiento/precio · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 71.8 (estimated) · 4/19 observed / reasoning 88.6 (estimated) · 4/13 observed / writing 81.1 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.5 (codex-harness) · 1 benchmarksReference: gpt-5.5-high (codex-harness) · 1 benchmarksReference: gpt-5.5-xhigh (codex-harness) · 1 benchmarksarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens1.000.000 puntosUso de salida · por millón de Tokens60.000.000 puntos
qwen-xiaomi/mimo-v2.5-proqwen-xiaomi-mimo-v2.5-proModelo independienteXiaomi · Estable2026-04-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated30.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.917.808 puntosUso por aciertos de caché · por millón de Tokens383.562 puntosUso de salida · por millón de Tokens5.753.425 puntos
Qwen3.6-27Bqwen3.6-27bModelo independienteQwen · Estable2026-04-22Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated46.6Rendimiento/precio · Estimated50.5
7/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.1 (estimated) · 2/19 observed / reasoning 56.9 (estimated) · 3/13 observed / writing 42.8 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-27b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarkslivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independent
Uso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens4.931.507 puntos
GPT Image 2gpt-image-2Modelo independienteOpenAI · Estable2026-04-21Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento97.0Rendimiento/precio69.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens2.500.000 puntosUso de entrada · Imagen · por millón de Tokens16.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens4.000.000 puntosUso de salida · Imagen · por millón de Tokens60.000.000 puntos
qwen-Kimi-K2.6qwen-kimi-k2.6Modelo independienteMoonshot · Estable2026-04-21Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated34.9Rendimiento/precio · Estimated39.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens356.164 puntosUso de salida · por millón de Tokens7.397.260 puntos
Kimi K2.6kimi-k2.6Modelo independienteMoonshot · Estable2026-04-20Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated77.4Rendimiento/precio · Estimated69.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 77.8 (estimated) · 2/19 observed / reasoning 78.7 (estimated) · 1/13 observed / writing 75.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: kimi-k3 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens301.370 puntosUso de salida · por millón de Tokens7.397.260 puntos
qwen-Kimi/Kimi K2.6qwen-kimi-kimi-k2.6Modelo independienteMoonshot AI · Estable2026-04-20Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.780.822 puntosUso por aciertos de caché · por millón de Tokens301.370 puntosUso de salida · por millón de Tokens7.397.260 puntos
claude-opus-4-7claude-opus-4-7Modelo independienteAnthropic · Estable2026-04-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.1Rendimiento/precio · Estimated66.9
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 4/19 observed / reasoning 81.7 (estimated) · 4/13 observed / writing 67.0 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-opus-4-7-100claude-opus-4-7-100Modelo independienteAnthropic · Estable2026-04-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.1Rendimiento/precio · Estimated66.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 73.6 (estimated) · 0/19 observed / reasoning 81.7 (estimated) · 0/13 observed / writing 67.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-7 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.6-35B-A3Bqwen3.6-35b-a3bModelo independienteQwen · Estable2026-04-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated45.4Rendimiento/precio · Estimated51.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.0 (estimated) · 0/19 observed / reasoning 54.8 (estimated) · 0/13 observed / writing 42.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.5-122b-a10b · 5 benchmarksReference: qwen3.5-35b-a3b · 5 benchmarksReference: qwen3.5-397b-a17b · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens493.151 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens2.958.904 puntos
Qwen3.6-Flashqwen3.6-flashModelo independienteQwen · Estable2026-04-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.2Rendimiento/precio · Estimated62.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 256.000 TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens65.753 puntosUso de salida · por millón de Tokens1.972.603 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens1.315.068 puntosUso por aciertos de caché · por millón de Tokens263.014 puntosUso de salida · por millón de Tokens7.890.411 puntos
qwen-GLM-5.1qwen-glm-5.1Modelo independienteZhipu · Estable2026-04-14Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.1Rendimiento/precio · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 32.000 TokenUso de entrada · por millón de Tokens1.643.836 puntosUso por aciertos de caché · por millón de Tokens328.767 puntosUso de salida · por millón de Tokens6.575.342 puntos
Input 32.001+ TokenUso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens438.356 puntosUso de salida · por millón de Tokens7.671.233 puntos
qwen-ViduQ3-mix_reference2videoqwen-vidu-viduq3-mix_reference2videoModelo independientevidu · Estable2026-04-13Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3_reference2videoqwen-vidu-viduq3_reference2videoModelo independientevidu · Estable2026-04-13Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Turbo_reference2videoqwen-vidu-viduq3-turbo_reference2videoModelo independientevidu · Estable2026-04-13Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-C1-it2vqwen-pixverse-pixverse-c1-it2vModelo independientepixverse · Estable2026-04-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-C1-kf2vqwen-pixverse-pixverse-c1-kf2vModelo independientepixverse · Estable2026-04-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-C1-r2vqwen-pixverse-pixverse-c1-r2vModelo independientepixverse · Estable2026-04-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-C1-t2vqwen-pixverse-pixverse-c1-t2vModelo independientepixverse · Estable2026-04-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ZHIPU/GLM-5.1qwen-zhipu-glm-5.1Modelo independienteZhipu AI · Estable2026-04-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
Wan2.7-I2Vwan2.7-i2vModelo independienteAlibaba Cloud · Estable2026-04-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento78.7Rendimiento/precio63.2
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
Wan2.7-R2Vwan2.7-r2vModelo independienteAlibaba Cloud · Estable2026-04-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated69.2Rendimiento/precio · Estimated56.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6arena · Independentarena · Independent
Generación de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
Wan2.7-T2Vwan2.7-t2vModelo independienteAlibaba Cloud · Estable2026-04-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento59.6Rendimiento/precio49.8
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
qwen-Wan2.7-VideoEditwan2.7-videoeditModelo independienteWan · Estable2026-04-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated69.2Rendimiento/precio · Estimated63.4
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-i2v · 78.7Reference: wan2.7-t2v · 59.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Grok 4.20 Non-Reasoninggrok-4-20-non-reasoningModelo independientexAI · Vista previa2026-04-06Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.7
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens5.000.000 puntos
Grok 4.20 Reasoninggrok-4-20-reasoningModelo independientexAI · Vista previa2026-04-06Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.7
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens5.000.000 puntos
Gemma 4 26B A4B It-100gemma-4-26b-a4b-it-maas-001Modelo independienteGoogle · Vista previa2026-04-02Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated62.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens300.000 puntosUso por aciertos de caché · por millón de Tokens30.000 puntosUso de salida · por millón de Tokens1.200.000 puntos
Veo 3.1 Lite Generate 001-100veo-3.1-lite-generate-001Modelo independienteGoogle · Estable2026-04-02Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-seed3d-2-0-260328doubao-seed3d-2-0-260328Instantánea / versión fija · Acceso únicoByteDance · Estable2026-04 (solo mes oficial)Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento82.2Rendimiento/precio57.5
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · Official
Uso de salida · 3D · por millón de Tokens21.917.809 puntos
Qwen3.6-Plusqwen3.6-plusModelo independienteQwen · Estable2026-04-01Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated54.5Rendimiento/precio · Estimated57.7
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 4/19 observed / reasoning 60.4 (estimated) · 4/13 observed / writing 52.8 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Input 0 – 256.000 TokenUso de entrada · por millón de Tokens547.945 puntosUso por aciertos de caché · por millón de Tokens109.589 puntosUso de salida · por millón de Tokens3.287.671 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens438.356 puntosUso de salida · por millón de Tokens13.150.685 puntos
Wan2.7-Imagewan2.7-imageModelo independienteAlibaba Cloud · Estable2026-04-01Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento41.7Rendimiento/precio46.3
Version comparison review
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.6-t2i by 8.3 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independent
Uso de salida · Imagen · por imagen54.795 puntos
Wan2.7-Image-Prowan2.7-image-proModelo independienteAlibaba Cloud · Estable2026-04-01Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento44.1Rendimiento/precio30.9
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de salida · Imagen · por imagen136.987 puntos
qwen-PixVerse-V6-it2vqwen-pixverse-pixverse-v6-it2vModelo independientepixverse · Estable2026-03-29Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-V6-kf2vqwen-pixverse-pixverse-v6-kf2vModelo independientepixverse · Estable2026-03-29Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-V6-t2vqwen-pixverse-pixverse-v6-t2vModelo independientepixverse · Estable2026-03-29Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GLM-5.1glm-5.1Modelo independienteZhipu · Estable2026-03-27Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated65.1Rendimiento/precio · Estimated61.4
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.7 (estimated) · 2/19 observed / reasoning 69.9 (estimated) · 1/13 observed / writing 58.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 31.999 TokenUso de entrada · por millón de Tokens1.643.836 puntosUso por aciertos de caché · por millón de Tokens356.164 puntosUso de salida · por millón de Tokens6.575.342 puntos
Input 32.000+ TokenUso de entrada · por millón de Tokens2.191.781 puntosUso por aciertos de caché · por millón de Tokens547.945 puntosUso de salida · por millón de Tokens7.671.233 puntos
Lyria 3 Clip Preview-100lyria-3-clip-previewModelo independienteGoogle · Estable2026-03-25Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Lyria 3 Pro Preview-100lyria-3-pro-previewModelo independienteGoogle · Estable2026-03-25Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-MiniMax/MiniMax-M2.7qwen-minimax-minimax-m2.7Modelo independienteMiniMax · Estable2026-03-18Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens575.342 puntosUso por aciertos de caché · por millón de Tokens115.068 puntosUso de salida · por millón de Tokens2.301.370 puntos
GPT-5.4 Minigpt-5.4-miniModelo independienteOpenAI · Estable2026-03-17Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated47.9Rendimiento/precio · Estimated48.9
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.3 (estimated) · 4/19 observed / reasoning 53.8 (estimated) · 4/13 observed / writing 45.6 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens1.500.000 puntosUso por aciertos de caché · por millón de Tokens150.000 puntosUso de salida · por millón de Tokens9.000.000 puntos
GPT-5.4 Nanogpt-5.4-nanoModelo independienteOpenAI · Estable2026-03-17Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated48.6Rendimiento/precio · Estimated54.8
11/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 44.5 (estimated) · 3/19 observed / reasoning 57.0 (estimated) · 4/13 observed / writing 44.3 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4 · 2 benchmarksReference: gpt-5.4-high (codex-harness) · 1 benchmarksReference: gpt-5.4-mini · 1 benchmarksarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independent
Uso de entrada · por millón de Tokens400.000 puntosUso por aciertos de caché · por millón de Tokens40.000 puntosUso de salida · por millón de Tokens2.500.000 puntos
GLM-5-Turboglm-5-turboModelo independienteZhipu · Estable2026-03-14Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated56.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 31.999 TokenUso de entrada · por millón de Tokens1.369.863 puntosUso por aciertos de caché · por millón de Tokens328.767 puntosUso de salida · por millón de Tokens6.027.397 puntos
Input 32.000+ TokenUso de entrada · por millón de Tokens1.917.808 puntosUso por aciertos de caché · por millón de Tokens493.151 puntosUso de salida · por millón de Tokens7.123.288 puntos
qwen-Tripo-P1.0qwen-tripo-tripo-p1.0Modelo independientetripo · Estable2026-03-11Sin precio fijo; facturación según el servicio
Rendimiento · Estimated43.2Rendimiento/precio · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Tripo-H3.1qwen-tripo-tripo-h3.1Modelo independientetripo · Estable2026-03-06Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.9Rendimiento/precio · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5.4gpt-5.4Modelo independienteOpenAI · Estable2026-03-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated73.0Rendimiento/precio · Estimated61.5
13/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.7 (estimated) · 5/19 observed / reasoning 84.9 (estimated) · 4/13 observed / writing 75.5 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksarena · Independentarena · Independentlivebench · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Official
Uso de entrada · por millón de Tokens5.000.000 puntosUso por aciertos de caché · por millón de Tokens500.000 puntosUso de salida · por millón de Tokens30.000.000 puntos
GPT-5.4 Progpt-5.4-proModelo independienteOpenAI · Estable2026-03-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.8Rendimiento/precio · Estimated41.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 49.8 (estimated) · 0/19 observed / reasoning 67.8 (estimated) · 0/13 observed / writing 58.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-5.4 · 13 benchmarksReference: gpt-5.4-mini · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: gpt-5.4-nano · 11 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens60.000.000 puntosUso de salida · por millón de Tokens360.000.000 puntos
Qwen3.5-Omni-Flashqwen3.5-omni-flashModelo independienteQwen · Estable2026-03 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated58.2Rendimiento/precio · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.5-Omni-Flash-Realtimeqwen3.5-omni-flash-realtimeModelo independienteQwen · Estable2026-03 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.5-Omni-Plusqwen3.5-omni-plusModelo independienteQwen · Estable2026-03 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated54.5Rendimiento/precio · Estimated53.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.5-Omni-Plus-Realtimeqwen3.5-omni-plus-realtimeModelo independienteQwen · Estable2026-03 (solo mes oficial)Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-pixverse/pixverse-motioncontrolqwen-pixverse-pixverse-motioncontrolModelo independientepixverse · Estable2026-02-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5.3 Codexgpt-5.3-codexModelo independienteOpenAI · Estable2026-02-24Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.5Rendimiento/precio · Estimated52.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.4 (estimated) · 0/19 observed / reasoning 63.1 (estimated) · 0/13 observed / writing 56.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-5.4 · 9 benchmarksReference: gpt-5.2 · 8 benchmarksReference: gpt-5.2-codex · 8 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReview: below gpt-5.2-codex by 3.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens3.500.000 puntosUso por aciertos de caché · por millón de Tokens350.000 puntosUso de salida · por millón de Tokens28.000.000 puntos
qwen-MiniMax-M2.5qwen-minimax-m2.5Modelo independienteMiniMax · Estable2026-02-24Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated34.9Rendimiento/precio · Estimated44.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens575.342 puntosUso por aciertos de caché · por millón de Tokens115.068 puntosUso de salida · por millón de Tokens2.301.370 puntos
GPT Audio 1.5gpt-audio-1.5Modelo independienteOpenAI · Estable2026-02-23Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated52.6Rendimiento/precio · Estimated41.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official
Uso de entrada · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntosUso de entrada · Audio · por millón de Tokens64.000.000 puntosUso de salida · Audio · por millón de Tokens128.000.000 puntos
GPT Realtime 1.5gpt-realtime-1.5Modelo independienteOpenAI · Estable2026-02-23Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated45.3Rendimiento/precio · Estimated31.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · Official
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens800.000 puntosUso de salida · por millón de Tokens32.000.000 puntosUso de entrada · Imagen · por millón de Tokens10.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens1.000.000 puntosUso de entrada · Audio · por millón de Tokens64.000.000 puntosUso por aciertos de caché · Audio · por millón de Tokens800.000 puntosUso de salida · Audio · por millón de Tokens128.000.000 puntos
Qwen3.5-122B-A10Bqwen3.5-122b-a10bModelo independienteQwen · Estable2026-02-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated46.4Rendimiento/precio · Estimated55.2
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.9 (estimated) · 2/19 observed / reasoning 56.8 (estimated) · 1/13 observed / writing 42.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens1.753.425 puntos
Input 128.001+ TokenUso de entrada · por millón de Tokens547.945 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens4.383.562 puntos
Qwen3.5-27Bqwen3.5-27bModelo independienteQwen · Estable2026-02-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated45.7Rendimiento/precio · Estimated55.9
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.4 (estimated) · 2/19 observed / reasoning 56.1 (estimated) · 1/13 observed / writing 41.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens164.384 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens1.315.068 puntos
Input 128.001+ TokenUso de entrada · por millón de Tokens493.151 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens3.945.205 puntos
Qwen3.5-35B-A3Bqwen3.5-35b-a3bModelo independienteQwen · Estable2026-02-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated42.9Rendimiento/precio · Estimated55.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.8 (estimated) · 2/19 observed / reasoning 51.7 (estimated) · 1/13 observed / writing 40.2 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens109.589 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens876.712 puntos
Input 128.001+ TokenUso de entrada · por millón de Tokens438.356 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens3.506.849 puntos
Qwen3.5-Flashqwen3.5-flashModelo independienteQwen · Estable2026-02-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.2Rendimiento/precio · Estimated68.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 2/19 observed / reasoning 62.8 (estimated) · 1/13 observed / writing 59.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens54.795 puntosUso por aciertos de caché · por millón de Tokens10.959 puntosUso de salida · por millón de Tokens547.945 puntos
Input 128.001 – 256.000 TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens2.191.781 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens65.753 puntosUso de salida · por millón de Tokens3.287.671 puntos
qwen-GLM-5qwen-glm-5Modelo independienteZhipu · Estable2026-02-18Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.1Rendimiento/precio · Estimated60.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.8 (estimated) · 0/19 observed / reasoning 64.7 (estimated) · 0/13 observed / writing 62.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 32.000 TokenUso de entrada · por millón de Tokens1.095.890 puntosUso por aciertos de caché · por millón de Tokens219.178 puntosUso de salida · por millón de Tokens4.931.507 puntos
Input 32.001+ TokenUso de entrada · por millón de Tokens1.643.836 puntosUso por aciertos de caché · por millón de Tokens328.767 puntosUso de salida · por millón de Tokens6.027.397 puntos
claude-sonnet-4-6claude-sonnet-4-6Modelo independienteAnthropic · Estable2026-02-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated65.2Rendimiento/precio · Estimated60.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 4/19 observed / reasoning 71.9 (estimated) · 4/13 observed / writing 59.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-sonnet-4-6-100claude-sonnet-4-6-100Modelo independienteAnthropic · Estable2026-02-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated65.2Rendimiento/precio · Estimated60.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 64.0 (estimated) · 0/19 observed / reasoning 71.9 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-sonnet-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3.5-397B-A17Bqwen3.5-397b-a17bModelo independienteQwen · Estable2026-02-15Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated49.6Rendimiento/precio · Estimated56.4
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 42.6 (estimated) · 2/19 observed / reasoning 59.5 (estimated) · 1/13 observed / writing 46.6 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens1.972.603 puntos
Input 128.001+ TokenUso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens4.931.507 puntos
Qwen3.5-Plusqwen3.5-plusModelo independienteQwen · Estable2026-02-15Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated54.5Rendimiento/precio · Estimated61.5
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.4 (estimated) · 0/19 observed / reasoning 60.4 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens1.315.068 puntos
Input 128.001 – 256.000 TokenUso de entrada · por millón de Tokens547.945 puntosUso por aciertos de caché · por millón de Tokens109.589 puntosUso de salida · por millón de Tokens3.287.671 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens1.095.890 puntosUso por aciertos de caché · por millón de Tokens219.178 puntosUso de salida · por millón de Tokens6.575.342 puntos
qwen-MiniMax/MiniMax-M2.5qwen-minimax-minimax-m2.5Modelo independienteMiniMax · Estable2026-02-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens575.342 puntosUso por aciertos de caché · por millón de Tokens57.534 puntosUso de salida · por millón de Tokens2.301.370 puntos
qwen-PixVerse-V5.6-r2vqwen-pixverse-pixverse-v5.6-r2vModelo independientepixverse · Estable2026-02-12Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ZHIPU/GLM-5qwen-zhipu-glm-5Modelo independienteZhipu AI · Estable2026-02-12Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated31.2
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.643.836 puntosUso por aciertos de caché · por millón de Tokens410.959 puntosUso de salida · por millón de Tokens6.027.397 puntos
qwen-ViduQ3-Pro_start-end2videoqwen-vidu-viduq3-pro_start-end2videoModelo independientevidu · Estable2026-02-11Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Turbo_img2videoqwen-vidu-viduq3-turbo_img2videoModelo independientevidu · Estable2026-02-11Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Turbo_start-end2videoqwen-vidu-viduq3-turbo_start-end2videoModelo independientevidu · Estable2026-02-11Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Turbo_text2videoqwen-vidu-viduq3-turbo_text2videoModelo independientevidu · Estable2026-02-11Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GLM-5glm-5Modelo independienteZhipu · Estable2026-02-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated60.9
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.4 (estimated) · 2/19 observed / reasoning 66.5 (estimated) · 1/13 observed / writing 56.9 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 31.999 TokenUso de entrada · por millón de Tokens1.095.890 puntosUso por aciertos de caché · por millón de Tokens273.973 puntosUso de salida · por millón de Tokens4.931.507 puntos
Input 32.000+ TokenUso de entrada · por millón de Tokens1.643.836 puntosUso por aciertos de caché · por millón de Tokens410.959 puntosUso de salida · por millón de Tokens6.027.397 puntos
Qwen-Image-2.0qwen-image-2.0Modelo independienteAlibaba Cloud · Estable2026-02-10Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated73.8Rendimiento/precio · Estimated68.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8arena · Independentarena · Independent
Uso de salida · Imagen · por imagen54.795 puntos
claude-opus-4-6claude-opus-4-6Modelo independienteAnthropic · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated70.8Rendimiento/precio · Estimated64.6
12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 4/19 observed / reasoning 75.9 (estimated) · 4/13 observed / writing 70.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-opus-4-6-100claude-opus-4-6-100Modelo independienteAnthropic · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated70.8Rendimiento/precio · Estimated64.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 66.4 (estimated) · 0/19 observed / reasoning 75.9 (estimated) · 0/13 observed / writing 70.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: claude-opus-4-6 · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Kling Image 3.0qwen-kling-kling-v3-image-generationModelo independientekling · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated73.8Rendimiento/precio · Estimated66.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Kling Image 3.0 Omniqwen-kling-kling-v3-omni-image-generationModelo independientekling · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Kling Video 3.0 Omniqwen-kling-kling-v3-omni-video-generationModelo independientekling · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated41.7Rendimiento/precio · Estimated44.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.7 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 37.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b · 4 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-vl-235b-a22b-instruct · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Kling Video 3.0qwen-kling-kling-v3-video-generationModelo independientekling · Estable2026-02-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Kimi-K2.5qwen-kimi-k2.5Modelo independienteMoonshot · Estable2026-01-30Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated34.9Rendimiento/precio · Estimated41.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 41.8 (estimated) · 0/13 observed / writing 28.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2.5-72b-instruct · 4 benchmarksReference: qwen2.5-coder-32b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.095.890 puntosUso por aciertos de caché · por millón de Tokens219.178 puntosUso de salida · por millón de Tokens5.753.425 puntos
Fun-ASR-Flash-8k实时语音识别fun-asr-flash-8k-realtimeModelo independienteQwen · Estable2026-01-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Pro_reference2videoqwen-vidu-viduq2-pro_reference2videoModelo independientevidu · Estable2026-01-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Pro_img2videoqwen-vidu-viduq3-pro_img2videoModelo independientevidu · Estable2026-01-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Pro_text2videoqwen-vidu-viduq3-pro_text2videoModelo independientevidu · Estable2026-01-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-VL-Plusqwen3-vl-plusModelo independienteQwen · Estable2026-01-26Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated42.7Rendimiento/precio · Estimated51.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.3 (estimated) · 0/19 observed / reasoning 44.7 (estimated) · 0/13 observed / writing 38.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 32.000 TokenUso de entrada · por millón de Tokens273.973 puntosUso por aciertos de caché · por millón de Tokens54.795 puntosUso de salida · por millón de Tokens2.739.726 puntos
Input 32.001 – 128.000 TokenUso de entrada · por millón de Tokens410.959 puntosUso por aciertos de caché · por millón de Tokens82.192 puntosUso de salida · por millón de Tokens4.109.589 puntos
Input 128.001+ TokenUso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens164.384 puntosUso de salida · por millón de Tokens8.219.178 puntos
qwen-PixVerse-V5.6-it2vqwen-pixverse-pixverse-v5.6-it2vModelo independientepixverse · Estable2026-01-26Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-V5.6-kf2vqwen-pixverse-pixverse-v5.6-kf2vModelo independientepixverse · Estable2026-01-26Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-V5.6-t2vqwen-pixverse-pixverse-v5.6-t2vModelo independientepixverse · Estable2026-01-26Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Virtual Try On 001-100virtual-try-on-001Modelo independienteGoogle · Estable2026-01-23Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5.2 Codexgpt-5.2-codexModelo independienteOpenAI · Estable2026-01-14Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.0Rendimiento/precio · Estimated54.5
Version comparison review8/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.8 (estimated) · 3/19 observed / reasoning 68.2 (estimated) · 3/13 observed / writing 58.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 4 benchmarksReference: gpt-5.2-chat-latest-20260210 · 4 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1-codex by 1.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independent
Uso de entrada · por millón de Tokens3.500.000 puntosUso por aciertos de caché · por millón de Tokens350.000 puntosUso de salida · por millón de Tokens28.000.000 puntos
qwen-MiniMax/MiniMax-M2.1qwen-minimax-minimax-m2.1Modelo independienteMiniMax · Estable2025-12-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens575.342 puntosUso por aciertos de caché · por millón de Tokens57.534 puntosUso de salida · por millón de Tokens2.301.370 puntos
GLM-4.7glm-4.7Modelo independienteZhipu · Estable2025-12-22Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated60.2Rendimiento/precio · Estimated60.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.3 (estimated) · 2/19 observed / reasoning 63.5 (estimated) · 1/13 observed / writing 53.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-5.2 · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Input 0 – 31.999 Token · Output 0 – 199 TokenUso de entrada · por millón de Tokens547.945 puntosUso por aciertos de caché · por millón de Tokens109.589 puntosUso de salida · por millón de Tokens2.191.781 puntos
Input 0 – 31.999 Token · Output 200+ TokenUso de entrada · por millón de Tokens821.918 puntosUso por aciertos de caché · por millón de Tokens164.384 puntosUso de salida · por millón de Tokens3.835.616 puntos
Input 32.000+ TokenUso de entrada · por millón de Tokens1.095.890 puntosUso por aciertos de caché · por millón de Tokens219.178 puntosUso de salida · por millón de Tokens4.383.562 puntos
GPT Image 1.5gpt-image-1.5Modelo independienteOpenAI · Estable2025-12-16Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento76.0Rendimiento/precio53.2
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · por millón de Tokens10.000.000 puntosUso por aciertos de caché · por millón de Tokens2.500.000 puntosUso de entrada · Imagen · por millón de Tokens16.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens4.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntosUso de salida · Imagen · por millón de Tokens64.000.000 puntos
Wan2.6-I2Vwan2.6-i2vModelo independienteAlibaba Cloud · Estable2025-12-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento53.2Rendimiento/precio45.3
Version comparison review
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%Review: below wan2.5-i2v-preview by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independent
Generación de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
Wan2.6-Imagewan2.6-imageModelo independienteAlibaba Cloud · Estable2025-12-16Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento31.6Rendimiento/precio39.2
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Uso de salida · Imagen · por imagen54.795 puntos
qwen-Wan2.6-R2Vwan2.6-r2vModelo independienteWan · Estable2025-12-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated55.3Rendimiento/precio · Estimated53.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Wan2.6-T2Iwan2.6-t2iModelo independienteAlibaba Cloud · Estable2025-12-16Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento50.0Rendimiento/precio52.1
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Uso de salida · Imagen · por imagen54.795 puntos
Wan2.6-T2Vwan2.6-t2vModelo independienteAlibaba Cloud · Estable2025-12-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento57.4Rendimiento/precio48.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
Cohere Rerank v4.0 Procohere-rerank-v4.0-proModelo independienteCohere · Estable2025-12-11Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated65.8Rendimiento/precio · Estimated61.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-0.6B · 68.8Reference: gte-multilingual-reranker-base · 62.7Reference: BGE-reranker-v2-m3 · 57.7qwen-rerank-public · Official
Reordenación · por 1.000 unidades de búsqueda5.000.000 puntos
GPT-5.2gpt-5.2Modelo independienteOpenAI · Estable2025-12-11Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated61.7Rendimiento/precio · Estimated54.3
Version comparison review12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 52.5 (estimated) · 4/19 observed / reasoning 73.8 (estimated) · 4/13 observed / writing 58.7 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksReview: below gpt-5.1 by 2.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent
Uso de entrada · por millón de Tokens3.500.000 puntosUso por aciertos de caché · por millón de Tokens350.000 puntosUso de salida · por millón de Tokens28.000.000 puntos
GPT-5.1 Codex Maxgpt-5.1-codex-maxModelo independienteOpenAI · Estable2025-12-04Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated72.5Rendimiento/precio · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 69.3 (estimated) · 0/19 observed / reasoning 78.4 (estimated) · 0/13 observed / writing 69.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-6-sol-max · 12 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.4 · 1 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
Mistral Large 3mistral-large-3Modelo independienteMistral AI · Estable2025-12-02Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated60.6Rendimiento/precio · Estimated60.8
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.7 (estimated) · 2/19 observed / reasoning 66.7 (estimated) · 1/13 observed / writing 60.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.000.000 puntosUso de salida · por millón de Tokens3.000.000 puntos
qwen-ViduQ2-Pro-fast_img2videoqwen-vidu-viduq2-pro-fast_img2videoModelo independientevidu · Estable2025-12-02Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-LiveTranslate-Flashqwen3-livetranslate-flashModelo independienteQwen · Estable2025-12-01Sin precio fijo; facturación según el servicio
Rendimiento · Estimated58.2Rendimiento/precio · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-Omni-Flashqwen3-omni-flashModelo independienteQwen · Estable2025-12-01Sin precio fijo; facturación según el servicio
Rendimiento · Estimated58.2Rendimiento/precio · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-SiliconFlow DeepSeek-V3.2qwen-siliconflow-deepseek-v3.2Modelo independienteDeepSeek · Estable2025-12-01Sin precio fijo; facturación según el servicio
Rendimiento · Estimated45.8Rendimiento/precio · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vanchin/DeepSeek-V3.2-thinkqwen-vanchin-deepseek-v3.2-thinkModelo independienteDeepSeek · Estable2025-12-01Sin precio fijo; facturación según el servicio
Rendimiento · Estimated45.8Rendimiento/precio · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.1 (estimated) · 0/19 observed / reasoning 54.2 (estimated) · 0/13 observed / writing 45.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.2-exp · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-TTS-Flash-Realtimeqwen3-tts-flash-realtimeModelo independienteQwen · Estable2025-11-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Z-Image-Turboz-image-turboModelo independienteAlibaba Cloud · Estable2025-11-26Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento28.8Rendimiento/precio50.2
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Uso de salida · Imagen · por imagen27.398 puntos
FLUX.2 [flex]flux.2-flexModelo independienteBlack Forest Labs · Estable2025-11-25Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento46.8Rendimiento/precio32.8
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · Imagen · por megapíxel100.000 puntosUso de salida · Imagen · por megapíxel100.000 puntos
FLUX.2 Proflux.2-proModelo independienteBlack Forest Labs · Estable2025-11-25Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento49.9Rendimiento/precio64.9
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Megapíxel inicial · por megapíxel60.000 puntosMegapíxel adicional · por megapíxel30.000 puntos
claude-opus-4-5claude-opus-4-5Modelo independienteAnthropic · Estable2025-11-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated67.9Rendimiento/precio—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-opus-4-5-100claude-opus-4-5-100Modelo independienteAnthropic · Estable2025-11-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated67.9Rendimiento/precio—
Shared exact-model performance from claude-opus-4-5; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 63.9 (estimated) · 0/19 observed / reasoning 71.8 (estimated) · 0/13 observed / writing 67.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-opus-4-6 · 7 benchmarksReference: claude-opus-4-5-20251101 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Grok 4.1 Fast Non-Reasoninggrok-4-1-fast-non-reasoningModelo independientexAI · Estable2025-11-19Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated62.1
Shared exact-model performance from grok-4-1-fast-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens400.000 puntosUso por aciertos de caché · por millón de Tokens100.000 puntosUso de salida · por millón de Tokens1.000.000 puntos
Grok 4.1 Fast Reasoninggrok-4-1-fast-reasoningModelo independientexAI · Estable2025-11-19Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.5Rendimiento/precio · Estimated64.1
Shared exact-model performance from grok-4-1-fast-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.3 (estimated) · 2/19 observed / reasoning 65.8 (estimated) · 1/13 observed / writing 59.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens400.000 puntosUso por aciertos de caché · por millón de Tokens100.000 puntosUso de salida · por millón de Tokens1.000.000 puntos
Gemini 3 Pro Preview-100gemini-3-pro-previewModelo independienteGoogle · Estable2025-11-18Sin precio fijo; facturación según el servicio
Rendimiento · Estimated69.4Rendimiento/precio · Estimated63.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.1 (estimated) · 0/19 observed / reasoning 77.5 (estimated) · 0/13 observed / writing 82.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gemini-3.1-pro-preview-high · 7 benchmarksReference: gemini-3-pro · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Veo 3.1 Fast Generate 001-100veo-3.1-fast-generate-001Modelo independienteGoogle · Estable2025-11-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Veo 3.1 Generate 001-100veo-3.1-generate-001Modelo independienteGoogle · Estable2025-11-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5.1gpt-5.1Modelo independienteOpenAI · Estable2025-11-13Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated63.8Rendimiento/precio · Estimated57.2
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.9 (estimated) · 2/19 observed / reasoning 73.2 (estimated) · 1/13 observed / writing 63.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
GPT-5.1 Codexgpt-5.1-codexModelo independienteOpenAI · Estable2025-11-13Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated63.6Rendimiento/precio · Estimated57.1
1/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.2 (estimated) · 1/19 observed / reasoning 70.3 (estimated) · 0/13 observed / writing 62.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.1 · 4 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
GPT-5.1 Codex Minigpt-5.1-codex-miniModelo independienteOpenAI · Estable2025-11-13Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated43.1Rendimiento/precio · Estimated49.4
1/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 0/13 observed / writing 40.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5-mini · 4 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens500.000 puntosUso por aciertos de caché · por millón de Tokens50.000 puntosUso de salida · por millón de Tokens4.000.000 puntos
Lyria 002-100lyria-002Modelo independienteGoogle · Estable2025-10-27Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2_reference2videoqwen-vidu-viduq2_reference2videoModelo independientevidu · Estable2025-10-21Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2_text2videoqwen-vidu-viduq2_text2videoModelo independientevidu · Estable2025-10-21Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vanchin/DeepSeek-OCRqwen-vanchin-deepseek-ocrModelo independienteDeepSeek · Estable2025-10-20Sin precio fijo; facturación según el servicio
Rendimiento · Estimated81.8Rendimiento/precio · Estimated72.3
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-haiku-4-5claude-haiku-4-5Modelo independienteAnthropic · Estable2025-10-15Sin precio fijo; facturación según el servicio
Rendimiento · Estimated60.4Rendimiento/precio · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

claude-haiku-4-5-100claude-haiku-4-5-100Modelo independienteAnthropic · Estable2025-10-15Sin precio fijo; facturación según el servicio
Rendimiento · Estimated60.4Rendimiento/precio · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.5 (estimated) · 0/19 observed / reasoning 63.8 (estimated) · 0/13 observed / writing 60.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-haiku-4-5-20251001 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5 Progpt-5-proModelo independienteOpenAI · Estable2025-10-06Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.5Rendimiento/precio · Estimated41.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.9 (estimated) · 0/19 observed / reasoning 61.9 (estimated) · 0/13 observed / writing 51.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens20.000.000 puntosUso de salida · por millón de Tokens240.000.000 puntos
GPT Audio Minigpt-audio-miniModelo independienteOpenAI · Estable2025-10-06Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated52.6Rendimiento/precio · Estimated66.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official
Uso de entrada · por millón de Tokens1.200.000 puntosUso de salida · por millón de Tokens4.800.000 puntosUso de entrada · Audio · por millón de Tokens20.000.000 puntosUso de salida · Audio · por millón de Tokens40.000.000 puntos
GPT Image 1 Minigpt-image-1-miniModelo independienteOpenAI · Estable2025-10-06Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento20.1Rendimiento/precio44.1
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independentarena · Independent
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de entrada · Imagen · por millón de Tokens5.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens500.000 puntosUso de salida · Imagen · por millón de Tokens16.000.000 puntos
GPT Realtime Minigpt-realtime-miniModelo independienteOpenAI · Estable2025-10-06Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated54.0Rendimiento/precio · Estimated67.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3openai-realtime-public · Official
Uso de entrada · por millón de Tokens1.200.000 puntosUso por aciertos de caché · por millón de Tokens120.000 puntosUso de salida · por millón de Tokens4.800.000 puntosUso de entrada · Imagen · por millón de Tokens1.600.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens160.000 puntosUso de entrada · Audio · por millón de Tokens20.000.000 puntosUso por aciertos de caché · Audio · por millón de Tokens600.000 puntosUso de salida · Audio · por millón de Tokens40.000.000 puntos
Gemini 2.5 Flash TTS-100gemini-2.5-flash-ttsModelo independienteGoogle · Estable2025-09-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated87.1Rendimiento/precio · Estimated76.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-flash · 87.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Gemini 2.5 Pro TTS-100gemini-2.5-pro-ttsModelo independienteGoogle · Estable2025-09-30Sin precio fijo; facturación según el servicio
Rendimiento · Estimated82.6Rendimiento/precio · Estimated72.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sora 2sora-2Modelo independienteOpenAI · Vista previa2025-09-30Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento66.0Rendimiento/precio50.4
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo · por segundo200.000 puntos
claude-sonnet-4-5claude-sonnet-4-5Modelo independienteAnthropic · Estable2025-09-29Sin precio fijo; facturación según el servicio
Rendimiento · Estimated61.6Rendimiento/precio · Estimated58.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 58.8 (estimated) · 0/19 observed / reasoning 66.2 (estimated) · 0/13 observed / writing 59.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: claude-sonnet-4-6 · 7 benchmarksReference: claude-sonnet-4-5-20250929 · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Pro_img2videoqwen-vidu-viduq2-pro_img2videoModelo independientevidu · Estable2025-09-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Pro_start-end2videoqwen-vidu-viduq2-pro_start-end2videoModelo independientevidu · Estable2025-09-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Turbo_img2videoqwen-vidu-viduq2-turbo_img2videoModelo independientevidu · Estable2025-09-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Turbo_start-end2videoqwen-vidu-viduq2-turbo_start-end2videoModelo independientevidu · Estable2025-09-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-5 Codexgpt-5-codexModelo independienteOpenAI · Estable2025-09-23Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.1Rendimiento/precio · Estimated53.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 59.5 (estimated) · 0/19 observed / reasoning 63.0 (estimated) · 0/13 observed / writing 54.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5 · 5 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
qwen-SiliconFlow DeepSeek-V3.1-Terminusqwen-siliconflow-deepseek-v3.1-terminusModelo independienteDeepSeek · Estable2025-09-22Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.9Rendimiento/precio · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vanchin/DeepSeek-V3.1-Terminusqwen-vanchin-deepseek-v3.1-terminusModelo independienteDeepSeek · Estable2025-09-22Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.9Rendimiento/precio · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.4 (estimated) · 0/19 observed / reasoning 54.4 (estimated) · 0/13 observed / writing 42.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-v3.1 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-TTS-Flashqwen3-tts-flashModelo independienteAlibaba Cloud · Estable2025-09 (solo mes oficial)Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated74.4Rendimiento/precio · Estimated82.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4qwen-tts-public · Official
Audio · por 10.000 caracteres219.179 puntos
Chirp 3-100chirp-3Modelo independienteGoogle · Estable2025-08-29Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT Realtimegpt-realtimeModelo independienteOpenAI · Estable2025-08-28Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.9Rendimiento/precio · Estimated41.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official
Uso de entrada · por millón de Tokens8.000.000 puntosUso por aciertos de caché · por millón de Tokens800.000 puntosUso de salida · por millón de Tokens32.000.000 puntosUso de entrada · Imagen · por millón de Tokens10.000.000 puntosUso por aciertos de caché · Imagen · por millón de Tokens1.000.000 puntosUso de entrada · Audio · por millón de Tokens64.000.000 puntosUso por aciertos de caché · Audio · por millón de Tokens800.000 puntosUso de salida · Audio · por millón de Tokens128.000.000 puntos
GPT-5gpt-5Modelo independienteOpenAI · Estable2025-08-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.7Rendimiento/precio · Estimated53.6
5/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 54.6 (estimated) · 2/19 observed / reasoning 65.6 (estimated) · 1/13 observed / writing 56.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.5-preview-2025-02-27 · 7 benchmarksReference: gpt-5.2 · 7 benchmarksReference: gpt-5.2-codex · 7 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
GPT-5 Minigpt-5-miniModelo independienteOpenAI · Estable2025-08-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated43.1Rendimiento/precio · Estimated49.4
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 39.6 (estimated) · 1/19 observed / reasoning 48.9 (estimated) · 1/13 observed / writing 40.7 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 7 benchmarksReference: gpt-5.4-mini · 7 benchmarksReference: gpt-5.1-codex-mini · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens500.000 puntosUso por aciertos de caché · por millón de Tokens50.000 puntosUso de salida · por millón de Tokens4.000.000 puntos
GPT-5 Nanogpt-5-nanoModelo independienteOpenAI · Estable2025-08-07Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated44.4Rendimiento/precio · Estimated57.0
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 43.4 (estimated) · 1/19 observed / reasoning 50.3 (estimated) · 1/13 observed / writing 39.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-nano-2025-04-14 · 7 benchmarksReference: gpt-5.4-nano · 7 benchmarksReference: gpt-5 · 1 benchmarksReference: gpt-5.4 · 1 benchmarksarena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens100.000 puntosUso por aciertos de caché · por millón de Tokens10.000 puntosUso de salida · por millón de Tokens800.000 puntos
GPT-OSS 120B-100openai-gpt-oss-120b-maas-001Modelo independienteOpenAI · Estable2025-08-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated57.3Rendimiento/precio · Estimated55.1
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.4 (estimated) · 1/19 observed / reasoning 63.0 (estimated) · 1/13 observed / writing 51.5 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-Coder-Flashqwen3-coder-flashModelo independienteQwen · Estable2025-08-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated58.2Rendimiento/precio · Estimated64.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 51.9 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 7 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 32.000 TokenUso de entrada · por millón de Tokens273.973 puntosUso por aciertos de caché · por millón de Tokens54.795 puntosUso de salida · por millón de Tokens1.095.890 puntos
Input 32.001 – 128.000 TokenUso de entrada · por millón de Tokens410.959 puntosUso por aciertos de caché · por millón de Tokens82.192 puntosUso de salida · por millón de Tokens1.643.836 puntos
Input 128.001 – 256.000 TokenUso de entrada · por millón de Tokens684.932 puntosUso por aciertos de caché · por millón de Tokens136.986 puntosUso de salida · por millón de Tokens2.739.726 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens1.369.863 puntosUso por aciertos de caché · por millón de Tokens273.973 puntosUso de salida · por millón de Tokens6.849.315 puntos
Qwen-Flashqwen-flashModelo independienteQwen · Estable2025-08-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.4Rendimiento/precio · Estimated70.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.4 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens41.096 puntosUso por aciertos de caché · por millón de Tokens8219 puntosUso de salida · por millón de Tokens410.959 puntos
Input 128.001 – 256.000 TokenUso de entrada · por millón de Tokens164.384 puntosUso por aciertos de caché · por millón de Tokens32.877 puntosUso de salida · por millón de Tokens1.643.836 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens65.753 puntosUso de salida · por millón de Tokens3.287.671 puntos
doubao-glm-4-5-airdoubao-glm-4-5-air-20250728Instantánea / versión fija · Acceso únicoZhipu AI · Estable2025-07-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GLM-4.5-Airglm-4.5-airModelo independienteZhipu · Estable2025-07-27Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.3Rendimiento/precio · Estimated64.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.9 (estimated) · 0/19 observed / reasoning 64.2 (estimated) · 0/13 observed / writing 55.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: glm-4.5-air · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 31.999 Token · Output 0 – 199 TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens547.945 puntos
Input 0 – 31.999 Token · Output 200+ TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens1.643.836 puntos
Input 32.000+ TokenUso de entrada · por millón de Tokens328.767 puntosUso por aciertos de caché · por millón de Tokens65.753 puntosUso de salida · por millón de Tokens2.191.781 puntos
qwen-pixverse/pixverse-lipsyncqwen-pixverse-pixverse-lipsyncModelo independientepixverse · Estable2025-07-14Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Plusqwen-plusModelo independienteQwen · Estable2025-06-24Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated44.2Rendimiento/precio · Estimated55.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.6 (estimated) · 0/19 observed / reasoning 46.7 (estimated) · 0/13 observed / writing 40.3 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-plus · 8 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Input 0 – 128.000 TokenUso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens547.945 puntos
Input 128.001 – 256.000 TokenUso de entrada · por millón de Tokens657.534 puntosUso por aciertos de caché · por millón de Tokens131.507 puntosUso de salida · por millón de Tokens5.479.452 puntos
Input 256.001+ TokenUso de entrada · por millón de Tokens1.315.068 puntosUso por aciertos de caché · por millón de Tokens263.014 puntosUso de salida · por millón de Tokens13.150.685 puntos
qwen-SiliconFlow DeepSeek-R1-0528qwen-siliconflow-deepseek-r1-0528Modelo independienteDeepSeek · Estable2025-05-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated43.2Rendimiento/precio · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Mistral OCR 2505-100mistralai-mistral-ocr-2505-001Modelo independienteMistral AI · Estable2025-05-22Sin precio fijo; facturación según el servicio
Rendimiento · Estimated81.8Rendimiento/precio · Estimated72.3
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

mistral-medium-2505mistral-medium-2505Modelo independienteMistral AI · Estable2025-05-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated54.1Rendimiento/precio · Estimated52.9
Version comparison review4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.4 (estimated) · 1/19 observed / reasoning 59.7 (estimated) · 1/13 observed / writing 55.3 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below mistral-medium-3-5 by 6.5 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Phi-4 Reasoningphi-4-reasoningModelo independienteMicrosoft · Estable2025-04-30Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens250.000 puntosUso de salida · por millón de Tokens1.000.000 puntos
o3o3Modelo independienteOpenAI · Estable2025-04-16Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.8Rendimiento/precio · Estimated56.1
7/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 18%coding 57.9 (estimated) · 1/19 observed / reasoning 70.4 (estimated) · 4/13 observed / writing 60.0 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: o3-2025-04-16 · 4 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksReference: DeepSeek V4 Pro (High) (0813) · 1 benchmarksopenai-simple-evals · Officialmicrosoft-mai-report · Officialmistral-codestral · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens4.000.000 puntosUso por aciertos de caché · por millón de Tokens1.000.000 puntosUso de salida · por millón de Tokens16.000.000 puntos
Veo 2.0 Generate 001-100veo-2.0-generate-001Modelo independienteGoogle · Estable2025-04-09Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Llama 4 Maverick 17B 128Ellama-4-maverick-17b-128e-instruct-fp8Modelo independienteMeta · Estable2025-04-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated60.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens500.000 puntosUso de salida · por millón de Tokens2.000.000 puntos
Llama 4 Maverick 17B 128E-100llama-4-maverick-17b-128e-instruct-maas-100Modelo independienteMeta · Estable2025-04-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Llama 4 Scout 17B 16E Instruct-100meta-llama-4-scout-17b-16e-instruct-maas-001Modelo independienteMeta · Estable2025-04-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated53.1Rendimiento/precio · Estimated52.2
4/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.1 (estimated) · 1/19 observed / reasoning 56.7 (estimated) · 1/13 observed / writing 47.4 (estimated) · 2/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksReference: deepseek-v4-pro-0813 · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-SiliconFlow DeepSeek-V3-0324qwen-siliconflow-deepseek-v3-0324Modelo independienteDeepSeek · Estable2025-03-24Sin precio fijo; facturación según el servicio
Rendimiento · Estimated39.9Rendimiento/precio · Estimated42.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 36.0 (estimated) · 0/19 observed / reasoning 48.3 (estimated) · 0/13 observed / writing 35.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-coder-480b-a35b-instruct · 5 benchmarksReference: qwen3-30b-a3b · 4 benchmarksReference: qwen3-32b · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 4.6 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

GPT-4o Mini Transcribegpt-4o-mini-transcribeModelo independienteOpenAI · Estable2025-03-20Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated94.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Uso de entrada · Audio · por millón de Tokens6.000.000 puntosUso de entrada · por millón de Tokens2.500.000 puntosUso de salida · por millón de Tokens10.000.000 puntos
GPT-4o Mini TTSgpt-4o-mini-ttsModelo independienteOpenAI · Estable2025-03-20Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.8Rendimiento/precio · Estimated56.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: GPT-4o-mini-tts · 59.8qwen-tts-public · Official
Uso de entrada · por millón de Tokens1.200.000 puntosUso de salida · Audio · por millón de Tokens24.000.000 puntos
GPT-4o Transcribegpt-4o-transcribeModelo independienteOpenAI · Estable2025-03-20Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento91.4Rendimiento/precio64.0
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · Independent
Uso de entrada · Audio · por millón de Tokens12.000.000 puntosUso de entrada · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
mistral-small-2503mistral-small-2503Modelo independienteMistral AI · Estable2025-03-17Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.0Rendimiento/precio—
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Mistral Small 3.1-100mistral-small-2503-100Modelo independienteGoogle · Vista previa2025-03-17Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.0Rendimiento/precio · Estimated64.3
Shared exact-model performance from mistral-small-2503; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.7 (estimated) · 0/19 observed / reasoning 59.2 (estimated) · 0/13 observed / writing 52.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: mistral-small-2506 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens200.000 puntosUso de salida · por millón de Tokens600.000 puntos
Text Embedding Large Exp 03 07-100text-embedding-large-exp-03-07Modelo independienteGoogle · Estable2025-03-07Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-DeepSeek-R1-Distill-Qwen-1.5Bqwen-deepseek-r1-distill-qwen-1.5bModelo independienteDeepSeek · Estable2025-01-20Sin precio fijo; facturación según el servicio
Rendimiento · Estimated43.2Rendimiento/precio · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Codestral 2501codestral-2501Modelo independienteMistral AI · Estable2025-01-13Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated60.1
9/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 18%coding 56.8 (estimated) · 9/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksReference: smaug-flash · 3 benchmarksmistral-codestral · Officialmicrosoft-mai-report · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens600.000 puntosUso de salida · por millón de Tokens1.800.000 puntos
Ministral-3Bministral-3bModelo independienteMistral AI · Estable2024-10-16Sin precio fijo; facturación según el servicio
Rendimiento · Estimated49.2Rendimiento/precio · Estimated49.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 53.8 (estimated) · 0/19 observed / reasoning 50.7 (estimated) · 0/13 observed / writing 43.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: ministral-8b-2410 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: smaug-flash · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Longqwen-longModelo independienteQwen · Estable2024-05-20Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated52.5Rendimiento/precio · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 48.7 (estimated) · 0/19 observed / reasoning 58.7 (estimated) · 0/13 observed / writing 50.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksReference: qwen-glm-4.5 · 4 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens136.986 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens547.945 puntos
Text Embedding 3 Largetext-embedding-3-largeModelo independienteOpenAI · Estable2024-01-25Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento64.6Rendimiento/precio45.2
Provisional2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Entrada vectorial · por millón de Tokens260.000 puntos
Text Embedding 3 Smalltext-embedding-3-smallModelo independienteOpenAI · Estable2024-01-25Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento62.3Rendimiento/precio71.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Entrada vectorial · por millón de Tokens40.000 puntos
Cohere-embed-v3-englishcohere-embed-v3-englishModelo independienteCohere · Estable2023-11-02Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Cohere-embed-v3-multilingualcohere-embed-v3-multilingualModelo independienteCohere · Estable2023-11-02Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Text Embedding Ada 002text-embedding-ada-002Modelo independienteOpenAI · Estable2022-12-15Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento61.0Rendimiento/precio46.6
Provisional2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · Official
Entrada vectorial · por millón de Tokens200.000 puntos
Qwen-Image-2.1-Turboqwen-image-2.1-turboModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-14Sin precio fijo; facturación según el servicio
Rendimiento—Rendimiento/precio—
Sin evaluar

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Chirp 2-100chirp-2-001Modelo independienteGoogle · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

语音生成CosyVoice-v3.5-flash大模型cosyvoice-v3.5-flashModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated75.4Rendimiento/precio · Estimated67.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

语音生成CosyVoice-v3.5-plus大模型cosyvoice-v3.5-plusModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated75.4Rendimiento/precio · Estimated67.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-GLM-5.3-Flashdoubao-glm-5-3-flash-260828Instantánea / versión fija · Acceso únicoZhipu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 56.6microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens63.014 puntosUso de salida · por millón de Tokens767.123 puntos
qwen2-5-72bdoubao-qwen2-5-72b-20240919Instantánea / versión fija · Acceso únicoQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen3-0-6bdoubao-qwen3-0-6b-20250429Instantánea / versión fija · Acceso únicoQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen3-14bdoubao-qwen3-14b-20250429Instantánea / versión fija · Acceso únicoQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen3-32bdoubao-qwen3-32b-20250429Instantánea / versión fija · Acceso únicoQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen3-8bdoubao-qwen3-8b-20250429Instantánea / versión fija · Acceso únicoQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-seed-translationdoubao-seed-translation-250915Instantánea / versión fija · Acceso únicoDoubao · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

doubao-smart-routerdoubao-smart-router-250928Instantánea / versión fija · Acceso únicoDoubao · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated50.0Rendimiento/precio · Estimated50.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

FaceChain人物图像检测facechain-facedetectModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Fun-ASR语音识别fun-asrModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Fun-ASR实时语音识别fun-asr-realtimeModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

音乐生成 Previewfun-music-previewModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

音乐生成fun-music-v1Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Grok 4.20 Non-Reasoning-100grok-4-20-non-reasoning-100Modelo independientexAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio—
Shared exact-model performance from grok-4-20-non-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens2.500.000 puntosUso por aciertos de caché · por millón de Tokens400.000 puntosUso de salida · por millón de Tokens5.000.000 puntos
Grok 4.20 Reasoning-100grok-4-20-reasoning-100Modelo independientexAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio—
Shared exact-model performance from grok-4-20-reasoning; coverage refers to public model benchmarks, not tests of every platform deployment.0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Grok 4.3-100grok-4.3-100Modelo independientexAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.8Rendimiento/precio—
Shared exact-model performance from grok-4.3; coverage refers to public model benchmarks, not tests of every platform deployment.12/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.8 (estimated) · 4/19 observed / reasoning 48.3 (estimated) · 4/13 observed / writing 47.2 (estimated) · 4/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: gpt-4.1 · 2 benchmarksReference: o1-mini · 2 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independentlivebench · Independentmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-HappyHorse-1.0-Video-Edithappyhorse-1.0-video-editModelo independienteHappyHorse · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated80.9Rendimiento/precio · Estimated71.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: happyhorse-1.0 · 80.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

图像擦除补全image-erase-completionModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

人物实例分割image-instance-segmentationModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Codestral 2-100mistralai-codestral-2-001Modelo independienteMistral AI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Mistral Medium 3-100mistralai-mistral-medium-3-001Modelo independienteMistral AI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Paraformer语音识别-8k-v2paraformer-8k-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Paraformer实时语音识别-8k-v2paraformer-realtime-8k-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Paraformer实时语音识别-v2paraformer-realtime-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Paraformer语音识别-v2paraformer-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-ASR-Flash-Filetransqwen3-asr-flash-filetransModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen3-ASR-Flash-Realtimeqwen3-asr-flash-realtimeModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.6Rendimiento/precio · Estimated51.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-realtime-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-ASR-Flashqwen-audio-3.1-asr-flashModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-ASR-Flash-Filetransqwen-audio-3.1-asr-flash-filetransModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-ASR-Flash-Messageqwen-audio-3.1-asr-flash-messageModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-ASR-Flash-Streamingqwen-audio-3.1-asr-flash-streamingModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated91.4Rendimiento/precio · Estimated79.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-asr-report · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-TTS-Flashqwen-audio-3.1-tts-flashModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.4Rendimiento/precio · Estimated67.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Audio-3.1-TTS-Nextqwen-audio-3.1-tts-nextModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated74.4Rendimiento/precio · Estimated67.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.qwen-tts-public · Official

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Doc-Turboqwen-doc-turboModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated48.7Rendimiento/precio · Estimated49.1
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.8 (estimated) · 0/19 observed / reasoning 52.3 (estimated) · 0/13 observed / writing 47.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens164.384 puntosUso por aciertos de caché · por millón de Tokens32.877 puntosUso de salida · por millón de Tokens273.973 puntos
Qwen-Flash-Characterqwen-flash-characterModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated59.9Rendimiento/precio · Estimated70.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 57.1 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens68.493 puntosUso por aciertos de caché · por millón de Tokens13.699 puntosUso de salida · por millón de Tokens410.959 puntos
qwen-Kling Video 3.0 Turboqwen-kling-kling-v3-turbo-video-generationModelo independientekling · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-speech-02-hdqwen-minimax-speech-02-hdModelo independientemini-max · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated32.9Rendimiento/precio · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-speech-02-turboqwen-minimax-speech-02-turboModelo independientemini-max · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated34.1Rendimiento/precio · Estimated38.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 34.1 (estimated) · 0/19 observed / reasoning 39.8 (estimated) · 0/13 observed / writing 28.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-speech-2.8-hdqwen-minimax-speech-2.8-hdModelo independientemini-max · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.1Rendimiento/precio · Estimated45.9
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 38.0 (estimated) · 0/19 observed / reasoning 53.2 (estimated) · 0/13 observed / writing 41.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-instruct-2507 · 4 benchmarksReference: qwen3-235b-a22b-thinking-2507 · 4 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-speech-2.8-turboqwen-minimax-speech-2.8-turboModelo independientemini-max · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated46.9Rendimiento/precio · Estimated47.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 40.0 (estimated) · 0/19 observed / reasoning 56.2 (estimated) · 0/13 observed / writing 44.6 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen3-30b-a3b-instruct-2507 · 4 benchmarksReference: qwen3-max-2025-09-23 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Flashqwen-mt-flashModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated59.4Rendimiento/precio · Estimated56.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 55.6 (estimated) · 0/19 observed / reasoning 62.8 (estimated) · 0/13 observed / writing 59.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: qwen3.5-flash · 5 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Imageqwen-mt-imageModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated34.1Rendimiento/precio · Estimated38.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image · 20.0Reference: qwen-image-prompt-extend · 23.8Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Liteqwen-mt-liteModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.3Rendimiento/precio · Estimated54.4
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 50.2 (estimated) · 0/19 observed / reasoning 60.6 (estimated) · 0/13 observed / writing 58.1 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.7-max · 8 benchmarksReference: qwen3.8-max · 8 benchmarksReference: qwen3.6-plus · 7 benchmarksReference: qwen-glm-4.6 · 5 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-MT-Plusqwen-mt-plusModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated46.7Rendimiento/precio · Estimated47.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 46.9 (estimated) · 0/19 observed / reasoning 50.1 (estimated) · 0/13 observed / writing 43.2 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-PixVerse-V6-r2vqwen-pixverse-pixverse-v6-r2vModelo independientepixverse · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Plus-Characterqwen-plus-characterModelo independienteqwen-domain-model · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated46.9Rendimiento/precio · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 47.0 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 43.4 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: qwen3.6-plus · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen-plus-0125 · 4 benchmarksReference: qwen2.5-plus-1127 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens219.178 puntosUso por aciertos de caché · por millón de Tokens43.836 puntosUso de salida · por millón de Tokens547.945 puntos
qwen-stepfun/step-5-previewqwen-stepfun-step-5-previewModelo independienteStepFun · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated30.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens1.917.808 puntosUso por aciertos de caché · por millón de Tokens95.890 puntosUso de salida · por millón de Tokens5.479.452 puntos
qwen-unisound/unisound-u2qwen-unisound-unisound-u2Modelo independienteunisound · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated32.9Rendimiento/precio · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 32.7 (estimated) · 0/19 observed / reasoning 39.5 (estimated) · 0/13 observed / writing 26.5 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen2-72b-instruct · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vanchin/DeepSeek-R1qwen-vanchin-deepseek-r1Modelo independienteDeepSeek · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated43.2Rendimiento/precio · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.0 (estimated) · 0/19 observed / reasoning 50.8 (estimated) · 0/13 observed / writing 41.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vanchin/DeepSeek-V3qwen-vanchin-deepseek-v3Modelo independienteDeepSeek · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated42.6Rendimiento/precio · Estimated44.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 37.2 (estimated) · 0/19 observed / reasoning 51.7 (estimated) · 0/13 observed / writing 39.0 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen3-235b-a22b-no-thinking · 4 benchmarksReference: qwen3-next-80b-a3b-thinking · 4 benchmarksReference: qwen3-vl-235b-a22b-thinking · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.Review: below qwen-deepseek-r1-0528 by 1.9 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-vanchin/deepseek-v4-proqwen-vanchin-deepseek-v4-proModelo independienteDeepSeek · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated71.1Rendimiento/precio · Estimated64.8
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 67.0 (estimated) · 0/19 observed / reasoning 75.3 (estimated) · 0/13 observed / writing 70.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen3.8-max · 13 benchmarksReference: mai-thinking-1 · 12 benchmarksReference: qwen3.8-27b · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-flash-next · 8 benchmarksReference: gpt-4.1-mini · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vidu-image-lite_reference2imageqwen-vidu-vidu-image-lite_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vidu-image-pro_reference2imageqwen-vidu-vidu-image-pro_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Vidu-image_reference2imageqwen-vidu-vidu-image_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated73.8Rendimiento/precio · Estimated66.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.1 · 73.8Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-fast_reference2imageqwen-vidu-viduq2-fast_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ2-Pro_reference2imageqwen-vidu-viduq2-pro_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated66.4Rendimiento/precio · Estimated61.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Ad_reference2videoqwen-vidu-viduq3-ad_reference2videoModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Drama_reference2videoqwen-vidu-viduq3-drama_reference2videoModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-fast_reference2imageqwen-vidu-viduq3-fast_reference2imageModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated85.0Rendimiento/precio · Estimated74.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-3.0-pro · 85.0Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ViduQ3-Pro-fast_img2videoqwen-vidu-viduq3-pro-fast_img2videoModelo independientevidu · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Qwen-Voice-Enrollmentqwen-voice-enrollmentEntrada de servicio independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 45.7 (estimated) · 0/19 observed / reasoning 56.4 (estimated) · 0/13 observed / writing 50.9 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: qwen3.8-27b · 8 benchmarksReference: qwen3.6-27b · 7 benchmarksReference: qwen-deepseek-r1 · 4 benchmarksReference: qwen-deepseek-r1-0528 · 4 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-ZHIPU/GLM-5.3-FlashXqwen-zhipu-glm-5.3-flashxModelo independienteZhipu AI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated41.0Rendimiento/precio · Estimated37.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 0%coding 36.2 (estimated) · 0/19 observed / reasoning 50.2 (estimated) · 0/13 observed / writing 36.7 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: · 41.0Review: below qwen-minimax-speech-2.8-hd by 3.1 points. Check matching benchmarks, configurations and estimates; this advisory does not alter the score.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens547.945 puntosUso por aciertos de caché · por millón de Tokens156.164 puntosUso de salida · por millón de Tokens1.917.808 puntos
Sambert语音合成-Bethsambert-beth-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Bettysambert-betty-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Briansambert-brian-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Callysambert-cally-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Camilasambert-camila-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Cindysambert-cindy-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Clarasambert-clara-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Donnasambert-donna-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Evasambert-eva-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Hannasambert-hanna-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Indahsambert-indah-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Perlasambert-perla-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-Waansambert-waan-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知厨sambert-zhichu-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知达sambert-zhida-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知德sambert-zhide-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知飞sambert-zhifei-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知柜sambert-zhigui-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知浩sambert-zhihao-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知佳sambert-zhijia-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知婧sambert-zhijing-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知伦sambert-zhilun-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知猫sambert-zhimao-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知妙（多情感）sambert-zhimiao-emo-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知茗sambert-zhiming-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知墨sambert-zhimo-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知楠sambert-zhinan-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知娜sambert-zhina-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知倩sambert-zhiqian-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知琪sambert-zhiqi-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知茹sambert-zhiru-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知硕sambert-zhishuo-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知树sambert-zhishu-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知莎sambert-zhistella-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知婷sambert-zhiting-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知薇sambert-zhiwei-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知祥sambert-zhixiang-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知笑sambert-zhixiao-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知雅sambert-zhiya-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知晔sambert-zhiye-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知颖sambert-zhiying-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知媛sambert-zhiyuan-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Sambert语音合成-知悦sambert-zhiyue-v1Entrada de voz independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

鞋靴模特shoemodel-v1Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

语音识别热词speech-biasingEntrada de servicio independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

通用文本向量-async-v1text-embedding-async-v1Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

通用文本向量-async-v2text-embedding-async-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

意图分类模型tongyi-intent-detect-v3Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

伶鹊-对话分析-flashtongyi-xiaomi-analysis-flashModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens54.795 puntosUso por aciertos de caché · por millón de Tokens10.959 puntosUso de salida · por millón de Tokens109.589 puntos
伶鹊-对话分析-protongyi-xiaomi-analysis-proModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens273.973 puntosUso por aciertos de caché · por millón de Tokens54.795 puntosUso de salida · por millón de Tokens739.726 puntos
Translate LLM-100translate-llmModelo independienteGoogle · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

声动人像VideoRetalkvideoretalkModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

视频风格重绘video-style-transformModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.0Rendimiento/precio · Estimated50.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: seedance-v1.5-pro · 53.2Reference: wan2.6-i2v · 53.2Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

虚拟模特V2virtualmodel-v2Modelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated44.5Rendimiento/precio · Estimated46.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.7-image-pro · 44.1Reference: krea-2-medium · 45.0Reference: reve-v1.1 · 43.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

大模型声音复刻及声音设计voice-enrollmentEntrada de servicio independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated56.6Rendimiento/precio · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksComparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.microsoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-Animate-Mixwan2.2-animate-mixModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-Animate-Movewan2.2-animate-moveModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-KF2V-Flashwan2.2-kf2v-flashModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-通义万相2.2-数字人-S2Vwan2.2-s2vModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-S2V-Detectwan2.2-s2v-detectModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-T2I-Flashwan2.2-t2i-flashModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.2-T2I-Pluswan2.2-t2i-plusModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.5-I2I-Previewwan2.5-i2i-previewModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated52.7Rendimiento/precio · Estimated51.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.5-T2I-Previewwan2.5-t2i-previewModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated51.5Rendimiento/precio · Estimated51.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.5-t2v-preview · 48.9Reference: wan2.5-i2v-preview · 55.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.6-R2V-Flashwan2.6-r2v-flashModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated55.3Rendimiento/precio · Estimated53.7
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.0-T2I-Turbowanx2.0-t2i-turboModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.1-ImageEditwanx2.1-imageeditModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.1-KF2V-Pluswanx2.1-kf2v-plusModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.1-T2I-Pluswanx2.1-t2i-plusModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.1-T2I-Turbowanx2.1-t2i-turboModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-Wan2.1-VACE-Pluswanx2.1-vace-plusModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-创意海报生成wanx-poster-generation-v1Modelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-万相-涂鸦作画wanx-sketch-to-image-liteModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated34.8Rendimiento/precio · Estimated39.4
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-人像风格重绘wanx-style-repaint-v1Modelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-wanx-t2iwanx-v1Modelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-虚拟模特wanx-virtualmodelModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated36.9Rendimiento/precio · Estimated40.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

qwen-万相-图像局部重绘wanx-x-paintingModelo independienteWan · EstableAñadido al catálogo (lanzamiento pendiente): 2026-10-05Sin precio fijo; facturación según el servicio
Rendimiento · Estimated37.0Rendimiento/precio · Estimated40.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7Reference: wan2.5-i2v-preview · 55.3Reference: wan2.5-t2v-preview · 48.9Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.arena · Independentarena · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

语音生成cosyvoice-v2大模型cosyvoice-v2Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated75.4Rendimiento/precio · Estimated52.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official
Audio · por 10.000 caracteres547.946 puntos
语音生成CosyVoice-v3-flash大模型cosyvoice-v3-flashModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated75.4Rendimiento/precio · Estimated75.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official
Audio · por 10.000 caracteres273.973 puntos
语音生成CosyVoice-v3-plus大模型cosyvoice-v3-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated75.4Rendimiento/precio · Estimated52.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3TTS-25Hz-1.7B-CustomVoice · 75.4Reference: Qwen3TTS-12Hz-1.7B-CustomVoice · 73.4Reference: Gemini-pro · 82.6qwen-tts-public · Official
Audio · por 10.000 caracteres547.946 puntos
GUI-Plusgui-plusModelo independienteQwen · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated56.6Rendimiento/precio · Estimated61.7
0/41 fixed-panel observations; remaining cells are marked estimates
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%coding 56.8 (estimated) · 0/19 observed / reasoning 60.2 (estimated) · 0/13 observed / writing 52.8 (estimated) · 0/9 observedEvery chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mai-thinking-1 · 12 benchmarksReference: codestral-2501 · 9 benchmarksReference: gpt-4.1-mini · 3 benchmarksReference: gpt-4o-2024-05-13 · 3 benchmarksReference: o1-mini · 3 benchmarksReference: o1-preview · 3 benchmarksmicrosoft-mai-report · Officialmistral-codestral · Officialopenai-simple-evals · Officialarena · Independentarena · Independentarena · Independentlivebench · Independent
Uso de entrada · por millón de Tokens410.959 puntosUso por aciertos de caché · por millón de Tokens0 puntosUso de salida · por millón de Tokens1.232.877 puntos
通用多模态向量multimodal-embedding-v1Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated48.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens191.781 puntosUso de entrada · Imagen · por millón de Tokens246.576 puntosEntrada de vídeo · por millón de Tokens246.576 puntos
Qwen2.5-VL-Embeddingqwen2.5-vl-embeddingModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated48.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens191.781 puntosUso de entrada · Imagen · por millón de Tokens493.151 puntos
Qwen3-ASR-Flashqwen3-asr-flashModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated94.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Transcripción · por segundo61 puntos
千问3-Rerankqwen3-rerankModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated72.5Rendimiento/precio · Estimated80.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official
Uso de entrada · por millón de Tokens136.987 puntos
Qwen3-VL-Embeddingqwen3-vl-embeddingModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated48.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens191.781 puntosUso de entrada · Imagen · por millón de Tokens493.151 puntos
Qwen3-VL-Rerankqwen3-vl-rerankModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated72.5Rendimiento/precio · Estimated80.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: Qwen3-Reranker-4B · 73.9Reference: Qwen3-Reranker-8B · 74.2Reference: Qwen3-Reranker-0.6B · 68.8qwen-rerank-public · Official
Uso de entrada · por millón de Tokens136.987 puntosEntrada de vídeo · por millón de Tokens493.154 puntos

Tarifa estimada de responsabilidad para entrada de vídeo, confirmada por el cliente. El proveedor no ha publicado un precio oficial de vídeo ni la conversión de fotogramas a Token. Solo se usa en el catálogo y para reservar pruebas; no se registra como coste del proveedor ni modifica facturas históricas.

Qwen-Image-2.0-Proqwen-image-2.0-proModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated66.4Rendimiento/precio · Estimated46.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: qwen-image-2.0-pro-2026-06-22 · 66.4arena · Independentarena · Independent
Uso de salida · Imagen · por imagen136.987 puntos
Qwen-Image-3.0-Proqwen-image-3.0-proModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento85.0Rendimiento/precio59.5
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Imagen Uso de entrada 1K · por imagen5480 puntosImagen Uso de entrada 2K · por imagen5480 puntosImagen Uso de salida 1K · por imagen68.494 puntosImagen Uso de salida 2K · por imagen136.987 puntos
QwenVL-OCRqwen-vl-ocrModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated81.8Rendimiento/precio · Estimated72.3
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: mistral-ocr-4-0 · 81.8Reference: cohere-parse-v5 · 79.2Reference: mistral-document-ai-2512 · 96.1Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.mistral-ocr · Officialcohere-parsebench · Officialmistral-ocr · Official
Uso de entrada · por millón de Tokens82.192 puntosUso de salida · por millón de Tokens136.987 puntos
通用文本向量-v1text-embedding-v1Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento58.3Rendimiento/precio45.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Entrada vectorial · por millón de Tokens191.781 puntos
通用文本向量-v2text-embedding-v2Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento60.1Rendimiento/precio46.6
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Entrada vectorial · por millón de Tokens191.781 puntos
通用文本向量-v3text-embedding-v3Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento63.4Rendimiento/precio53.9
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Entrada vectorial · por millón de Tokens136.987 puntos
通用文本向量-v4text-embedding-v4Modelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento71.6Rendimiento/precio59.6
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · Official
Entrada vectorial · por millón de Tokens136.987 puntos
视觉向量-flashtongyi-embedding-vision-flashModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated70.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens41.096 puntos
视觉向量-plustongyi-embedding-vision-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated62.3Rendimiento/precio · Estimated53.1
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: text-embedding-3-small · 62.3Reference: text-embedding-v3 · 63.4Reference: text-embedding-ada-002 · 61.0openai-embedding · Officialaliyun-embedding · Official
Entrada vectorial · por millón de Tokens136.987 puntos
Wan2.2-I2V-Flashwan2.2-i2v-flashModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated38.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 480P · por segundo27.398 puntosGeneración de vídeo 720P · por segundo54.795 puntosGeneración de vídeo 1080P · por segundo131.507 puntos
Wan2.2-I2V-Pluswan2.2-i2v-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 480P · por segundo38.357 puntosGeneración de vídeo 1080P · por segundo191.781 puntos
Wan2.2-T2V-Pluswan2.2-t2v-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated23.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 480P · por segundo38.357 puntosGeneración de vídeo 1080P · por segundo191.781 puntos
Wan2.5-I2V-Previewwan2.5-i2v-previewModelo independienteAlibaba Cloud · Vista previaAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento55.3Rendimiento/precio46.8
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo 480P · por segundo82.192 puntosGeneración de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
Wan2.5-T2V-Previewwan2.5-t2v-previewModelo independienteAlibaba Cloud · Vista previaAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento48.9Rendimiento/precio42.3
Provisional2026-10-08 16:22 (UTC+8) · Confidence 45%arena · Independent
Generación de vídeo 480P · por segundo82.192 puntosGeneración de vídeo 720P · por segundo164.384 puntosGeneración de vídeo 1080P · por segundo273.973 puntos
wan2.6-I2V-flashwan2.6-i2v-flashModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated54.9Rendimiento/precio · Estimated60.3
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan2.6-i2v · 53.2Reference: wan2.6-t2v · 57.4arena · Independentarena · Independent
Generación de vídeo 720P · por segundo82.192 puntosGeneración de vídeo 1080P · por segundo136.987 puntos
Wan2.1-I2V-Pluswanx2.1-i2v-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated13.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 720P · por segundo191.781 puntos
Wan2.1-I2V-Turbowanx2.1-i2v-turboModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated34.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 480P · por segundo65.754 puntosGeneración de vídeo 720P · por segundo65.754 puntos
Wan2.1-T2V-Pluswanx2.1-t2v-plusModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated13.2
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 720P · por segundo191.781 puntos
Wan2.1-T2V-Turbowanx2.1-t2v-turboModelo independienteAlibaba Cloud · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-10Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated11.7Rendimiento/precio · Estimated34.6
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: wan-v2.2-a14b · 11.7arena · Independentarena · Independent
Generación de vídeo 480P · por segundo65.754 puntosGeneración de vídeo 720P · por segundo65.754 puntos
doubao-hitem3d-2-0-251223doubao-hitem3d-2-0-251223Instantánea / versión fija · Acceso únicoHitem3D · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated82.2Rendimiento/precio · Estimated57.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · Official
Uso de salida · 3D · por millón de Tokens21.917.809 puntos
doubao-hyper3d-gen2-260112doubao-hyper3d-gen2-260112Instantánea / versión fija · Acceso únicoHyper3D · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated82.2Rendimiento/precio · Estimated87.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: doubao-seed3d-2-0-260328 · 82.2seed3d-public · Official
Uso de salida · 3D · por millón de Tokens16.438.357 puntos
doubao-seedance-2-0-260128doubao-seedance-2-0-260128Instantánea / versión fija · Acceso únicoByteDance · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.5Rendimiento/precio · Estimated68.5
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · Independent
Uso de salida · Generación de vídeo · por millón de Tokens12.602.740 puntos
doubao-seedance-2-0-fast-260128doubao-seedance-2-0-fast-260128Instantánea / versión fija · Acceso únicoByteDance · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.5Rendimiento/precio · Estimated70.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · Independent
Uso de salida · Generación de vídeo · por millón de Tokens7.602.740 puntos
doubao-seedance-2-0-mini-260615doubao-seedance-2-0-mini-260615Instantánea / versión fija · Acceso únicoByteDance · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.5Rendimiento/precio · Estimated75.9
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: dreamina-seedance-2.0-720p · 91.5arena · Independentarena · Independent
Uso de salida · Generación de vídeo · por millón de Tokens2.520.548 puntos
doubao-seedream-5-0-260128doubao-seedream-5-0-260128Instantánea / versión fija · Acceso únicoByteDance · EstableAñadido al catálogo (lanzamiento pendiente): 2026-09-09Disponible · generación y ediciónÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated54.4Rendimiento/precio · Estimated53.4
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: seedream-4.5 · 54.4arena · Independentarena · Independent
Uso de salida · Imagen · por imagen60.274 puntos
GPT-4o Transcribe Diarizegpt-4o-transcribe-diarizeModelo independienteOpenAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-08-28Disponible · herramientas de audioÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated91.4Rendimiento/precio · Estimated64.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 24%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-transcribe · 91.4qwen-asr-report · Independent
Uso de entrada · Audio · por millón de Tokens12.000.000 puntosUso de entrada · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntos
GPT Audiogpt-audioModelo independienteOpenAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-08-28Capacidades completasÚltima verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento · Estimated52.6Rendimiento/precio · Estimated36.8
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: gpt-4o-realtime-preview-2024-12-17 · 45.3Reference: gpt-realtime-2025-08-28 · 59.9openai-realtime-public · Official
Uso de entrada · por millón de Tokens5.000.000 puntosUso de salida · por millón de Tokens20.000.000 puntosUso de entrada · Audio · por millón de Tokens80.000.000 puntosUso de salida · Audio · por millón de Tokens160.000.000 puntos
Mistral Document AI 2512mistral-document-ai-2512Modelo independienteMistral AI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-08-28Última verificación del precio
Pendiente de verificación (UTC+8)
Rendimiento96.1Rendimiento/precio76.1
Provisional2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · Official
Procesamiento documental · por 1.000 páginas6.000.000 puntos
Model Routermodel-routerServicio de enrutamiento independienteOpenAI · EstableAñadido al catálogo (lanzamiento pendiente): 2026-08-28Sin precio fijo; facturación según el servicio
Rendimiento · Estimated50.0Rendimiento/precio · Estimated50.0
Estimate basis2026-10-08 16:22 (UTC+8) · Confidence 12%Every chat model uses the same benchmark panel and weights. Missing cells are estimated from the same base version first, then nearby same-purpose models.Reference: o1-mini · 50.0Reference: qwen3.6-plus · 50.2Reference: gemini-2.0-flash-001 · 50.3Comparable price unavailable; value is estimated with a neutral cost component and is excluded from value defaults.openai-simple-evals · Officialarena · Independentarena · Independentlivebench · Independent

Precio dinámico: recargo de entrada del router más los puntos del modelo realmente elegido.

Capacidades verificadas · 44
Claude Fable 5.1: complete within the verified, safely available deployment scope

Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.

  • Five adaptive efforts, high by default. Native/shared tools, structured output, real Codex continuation, image/PDF, cache and Key-owned files were verified.
  • Code execution uses the HCD free-combination billing bridge, adding fetch restricted to a non-resolving domain while preserving client tools. Execution/extremes are not live-tested (high-cost exemption); standalone native timing metering is not claimed.
  • Performance71.6/value55.1 are estimates:7 direct and34 estimated metrics in the fixed41-panel, using exact LiveBench max data.
Claude Haiku 5.5：Complete within the verified deployment scope

The exact available scope is verified; optional parameters and resources retain explicit bounds.

  • none disables thinking; low/medium/high/xhigh/max remain their real values; medium is the default. Native between_tools is rejected for this exact model.
  • Native Messages and the shared Chat/Responses path, strict tool schemas, inline image/PDF, SSE and signed history passed. The actual Codex complete tools, MCP echo and saved-thread continuation passed.
  • Bounded hosted search/fetch with citations and one-use owned remote MCP passed and settled once. Arbitrary remote URLs and unconstrained hosted execution are not enabled.
  • Ordinary input, output, cache reads and 5m/1h writes have separate rates. Input including cache reads/writes above100K uses the whole-request long-context tier at5x; the threshold boundary was checked offline.
  • The current deployment has no Files/Batch/container/skills API. Client function tools run on the client; no new native computer/browser toolset, durable background Responses resource or native compaction pass is claimed.
  • 1M context and HCD128000 output limits retain safe reservation/settlement. Expensive extremes were not live-tested (high-cost exemption).
  • Performance55.1 and value61.9 are estimated:8 directly attributed fixed-panel cells and33 estimates out of41. Benchmark effort high is separate from the medium inference default.
Claude Opus 5.5: complete verified deployment scope

Text, image/PDF, tools, thinking, cache and web access through Messages, Chat, Responses and Codex compatibility.

  • Adaptive thinking is always on; medium is the default. Only temperature 1 is supported; top_p/top_k are unavailable.
  • Verified client bridging supplies tool discovery. Native server tool search returned a safety refusal and is not claimed passed.
  • 1M context and 128K output. Expensive limits are not live-tested (high-cost exemption).
  • Files, Batch, code execution and native background jobs are not exposed. URL media generation is verified; token counting accepts supported inline inputs.
  • Client-side compaction and same-thread continuation are verified; unpriced server compaction remains closed.
  • Performance and value scores await exact-model evidence.
Claude Sonnet 5.5: complete within the verified, safely available deployment scope

Completion covers the exact model’s available scope. Optional hosted capabilities, resource quantities and budgets retain explicit bounds.

  • none, low, medium, high, xhigh and max; high is default. none uses between_tools: no up-front thinking, while progress between tools is retained. none is never aliased to low.
  • Native Messages and shared Chat/Responses conversion, strict structured output, advisory task-budget beta, functions, original SSE/signed thinking history, inline image/PDF, both cache TTLs and cache reads were verified.
  • Actual Codex complete default tools, discovery, top-level composed-schema bridging, an in-memory MCP round trip and a persisted second turn passed. Advanced beta controls require the corresponding official header.
  • Basic hosted search/fetch, citations and actual-usage accounting passed. No provider-native server Tool Search pass is claimed; client discovery bridging passed.
  • A funded owned remote-MCP HTTPS echo and Key/project lifecycle were verified; its lease was closed. Arbitrary remote URLs, variable results and external credential management remain closed.
  • The offering has no Batch, Files, code execution/containers/skills or new computer/browser toolsets. Messages has no native durable background-response resource. Native compaction remains closed; HCD’s existing client context path is reused without claiming an additional Sonnet compaction-generation live test.
  • Official 1M context and 128K output use uniform full-context rates. Expensive extremes are not live-tested (high-cost exemption); offline limits, safe holds and settlement remain enforced.
  • Performance 70.6 and value 61.1 are explicitly estimated: exact-model LiveBench observations cover 7 of the fixed 41-panel metrics at max effort. Value uses the same current official points tariff.
Codestral 2501: complete within the verified dedicated deployment scope

Verified Codestral-2501 native text chat, fill-in-the-middle, prefix/suffix completion, streaming and sampling through a dedicated code-tool entry.

  • It is a text/code tool, not a function-tool-capable Codex main or subagent model.
  • Exact FIM rejects metadata, prompt_cache_key and explicit null sampling/suffix values; HCD rejects them before dispatch rather than silently dropping them.
  • Native responses and actual token usage are retained. Estimated scores are not derived from this interface acceptance.
Cohere Parse v5: complete within the verified dedicated deployment scope

Verified Cohere Parse v5 dedicated image parsing with text/Markdown, blocks, tables, image regions and coordinates. The public directory labels it preview.

  • The Parse API accepts images only. PDF is rejected before upload; no hidden rasterization or fallback model is used.
  • Image regions contain original source pixels from returned boxes, not generated images. This is document parsing, not ordinary chat.
Cohere Rerank v4.0 Pro: complete within the verified dedicated deployment scope

Verified Cohere Rerank v4.0 Pro dedicated multilingual document reranking with structured text, top_n, priority and ranked scores.

  • Reranking only: chat and coding-agent requests are not admitted, regardless of misleading deployment metadata.
  • The provider truncates document tails at max_tokens_per_doc; HCD does not rewrite source text and discloses that policy. Estimated scores are separate from capability acceptance.
decision-model-preview: Full structured decisions (verified deployment scope)

Classification, yes/no probabilities and ordinal scoring preserve original probabilities, confidence and input usage; no chat text is generated.

  • Text, object or array state. HCD:1–16 questions, up to255 choices,2–10 score levels,32768 UTF-8 bytes total. Provider input context:65536 tokens.
  • Rounded probabilities and sums remain unchanged, without normalization. Confidence is not verified accuracy. Currently limited-time free; normal account/Key authorization, metering and single settlement apply.
  • No chat, streaming, tools, search, cache, Batch, media or persistent jobs. Maximum context not live-tested (high-cost exemption). Generic fixed-panel estimate:0/41 direct coverage, not decision accuracy; value uses this model own input tariff and decision workload.
DeepSeek V4.1 Flash: complete within the verified dedicated deployment scope

Verified DeepSeek Flash text reasoning, tools, streaming/history/cache, native Chat prefix FIM and image input within the exact deployed scope.

  • Image files use Key-owned authorization and lifecycle handling; compatibility media URLs require HTTPS. Hosted web/file search, native namespace discovery, encrypted reasoning and native background jobs are not exposed.
  • Official maximum context/output and large-media bounds use guards and offline checks; expensive extremes are not live-tested (high-cost exemption).
  • Earlier 74.9/75.3 figures were incomplete-panel estimates, not exact-model acceptance scores. Public composite performance/value scores await exact evidence.
  • Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.
DeepSeek V4 Pro: complete in the verified deployment scope

Verified text, structured output, reasoning, functions/client tool discovery and real Codex continuation; native Chat streaming/Prefix, Messages and FIM.

  • Hosted web search, image/file input and upstream stored/background state are unsupported; the model profile disables web search.
  • Performance69.3 and value65.7 are estimates:7 exact0813 public metrics and34 estimates in the fixed41-metric panel.
  • Maximum context/output/concurrency: not live-tested (high-cost exemption); official limits and offline guards apply.
  • Current exact protocol output bounds:393216 tokens for Chat/Responses and4096 for FIM. Former384000 corrected from exact schema; no extreme live test.
doubao-deepseek-v4-1-flash: verified deployment scope

Text, image and video; four reasoning levels, JSON Schema, functions, streaming and saved history. Actual Codex tools and continuation verified. Native remote MCP and owned Responses; HCD owned-file and controlled web-search bridges.

  • Context 1,048,576 tokens; input maximum 1,048,576; default/maximum output 393,216 including thought, within the combined context. Compatibility image limit 1,500; native 3,600; each media item 50 MiB, request 64 MiB. Owned inline files: 5 MiB each, 24-hour retention.
  • Implicit cache is metered. Explicit cache, native hosted search, Flex, Batch and background generation are closed and rejected. HCD MCP search reserves and bills separately. Actual Work client remains unverified. Performance 77.5/value 76.8 are estimates over 41 metrics, 12 direct model sources, no direct offering benchmark. Expensive boundaries checked offline.
doubao-DeepSeek V4 Flash GA (2026-07-31) — Full integration (verified deployment scope)

Verified text, none/low/high/max, JSON Schema, functions, bounded search, full tool history, MCP, implicit/explicit cache and native response resources. Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.

  • Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
  • Default low. Deleting a response does not end cache storage liability before TTL. Performance56.6/value58.8 estimated,0/41 direct; high-cost extremes not live-tested.
  • Account points/M tokens, standard input/output/cache:821918/2465753/27397; flex:410959/1232877/27397. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.
doubao-DeepSeek V4 Pro GA (2026-08-13) — Full integration (verified deployment scope)

Verified text, none/low/high/max, JSON Schema, functions, bounded search, full tool history, MCP, implicit/explicit cache and native response resources. Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch. Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.

  • Native knowledge search has no authorized resource and is closed. Cache with context edits, unregistered native MCP servers, Batch/background/images are closed and rejected before dispatch.
  • Default low. Deleting a response does not end cache storage liability before TTL. Performance59.4/value56.2 estimated,7/41 direct; high-cost extremes not live-tested.
  • Account points/M tokens, standard input/output/cache:2465753/7397260/82192; flex:1232877/3698630/82192. No extra token cache-write fee. Storage4658 points/M-token/hour; search5480 points/call. Key multiplier and per-item rounding apply separately.
  • Flex returned upstream ModelLoading and is not verified or open; rejected before dispatch. Its reviewed rate is reference only. Cache continuation must explicitly stay within the original TTL; cross-model references, context edits and native hosted tools are rejected. Missing reasoning breakdown keeps a funded storage upper bound without posting an estimated charge.
FLUX.2 Pro: complete within the verified dedicated deployment scope

Verified FLUX.2 Pro dedicated image generation, editing and up to eight reference images. The public directory currently marks it as planned.

  • PNG/JPEG output and the model-specific prompt enhancement mapping were checked; tuning fields from another model are explicitly rejected.
  • Image streaming, transparent output, mask editing and steps/guidance controls are outside this exact interface. Image acceptance is neither a quality score nor a chat-route claim.
Google Gemini 3.8 Flash-100: fully reviewed deployed scope

Native GenerateContent, Chat and Interactions support text, image, audio, video and PDF input, thinking, JSON, functions, streaming and continuation. Codex uses the HCD Responses bridge.

  • Knowledge Studio adds isolated Python (NumPy, SymPy and Matplotlib), URL reading, video-frame inspection and controlled web search. These are HCD bridges; native hosted code, search and AGENTIC video loops are not enabled. Computer use returns proposed actions only.
  • Combined context: 1,048,576 tokens; no disclosed independent input maximum. Default and maximum output: 65,536 tokens including thinking, subject to remaining context. Explicit cache read/delete/expiry and owned HCD files, background responses and Batch preserve original results. Batch uses standard call prices.
  • Per million tokens: input 3,000,000 points, cache hits 300,000 and output including thinking 15,000,000. Explicit cache creation uses the input rate; storage costs 2,000,000 points per million token-hours. Supplier promotional credits have not been received and do not promise customer refunds. Performance 76.6 and value 66.1 are estimates: 12 model-wide public metrics and 29 estimated metrics, with no direct performance measurement for this offering. Expensive limits were checked offline.
  • Work Responses live web search uses an HCD controlled bridge. In auto mode the model decides whether to search, at most once per response; model and search usage are metered separately from original receipts. Authenticated actual Work client and search roundtrip verification remains pending.
  • Gemini 3.8 Flash-100 supports HCD summary views: auto keeps the provider automatic summary; detailed shows the full available provider summary; concise explicitly shows an HCD bounded extract and truncation status; none hides the public summary. These views do not control provider summary length or add model calls. Thinking tokens retain original receipt billing. Actual remote Work roundtrip verification is pending.
Gemini 3.8 Live-100 · Current deployment fully integrated

Realtime audio/video, camera/images, prebuilt Avatar, function follow-ups, native resume, interruption and bounded web search.

  • Custom Avatar is unavailable on this deployment and rejected before provider contact. The user explicitly deferred and exempted it from full certification; no application was submitted.
  • Search and automatic VAD use bounded HCD bridges; provider-native search is not exposed.
  • Google supplier rates per1M tokens: TEXT/IMAGE-VIDEO/AUDIO input0.75/1/3USD; TEXT/AUDIO/VIDEO output4.5/12/1USD. Thinking uses text-output rates; transcription and retained history remain in original meters. Search has a separate quote.
  • Performance77.2 and value84.0 are estimates; direct panel coverage0/41. Audio/Avatar quality not benchmarked. Extreme contexts/media: not live-tested (high-cost exemption).
Google Gemini 4 Argon: verified deployed capabilities

Text, image, audio, video and PDF input; three reasoning levels, JSON, function tools and streaming. Codex tools and continuation are verified. HCD knowledge tools provide isolated Python, URL reading, video-frame inspection and separately billed controlled search. Responses builtin web_search uses the bounded HCD compatibility bridge; actual Work client verification remains pending. Preview search and unmapped explicit controls are rejected.

  • Combined context is 1,048,576 tokens; the independent input limit is not disclosed. Native GenerateContent defaults to and permits 1,048,576 total output tokens through manual owner-bound continuationToken requests; each segment permits 32,768 non-streaming or 65,536 streaming tokens. Responses, Chat and Interactions default and maximum per-call outputs are 32,768 non-streaming / 65,536 streaming, including reasoning within combined context. Explicit cache is unsupported; implicit cache is metered. Owned HCD files, background responses and Batch retain lifecycle controls; Batch uses standard call prices.
  • Per million tokens: 8,000,000 input points, 400,000 cache-hit points and 40,000,000 output/reasoning points. Full input, output and tool liabilities are reserved against both account and Key before submission; each explicit continuation is separately reserved and settled. Performance 77.2 and value 62.5 are estimates: 6 model-wide public metrics plus 35 estimates in a fixed 41-metric panel, with no direct offering performance measurement. Expensive boundaries were checked offline. Supplier promotional credits are not treated as received.
Gemini Nano Banana 2.1-100: Complete within verified deployment scope

Complete verified image-studio scope; HCD bounds are distinct from manufacturer maxima.

  • Image generation/editing, streaming and private-reference continuation; 1K/2K/4K, 15 aspect ratios, minimal/medium/high, up to32768 output tokens and native system instructions. One PNG/JPEG result per request.
  • Up to14 PNG/JPEG/WebP/HEIC/HEIF references:7MiB each,40MiB combined media,64MiB complete request/history. One PDF/UTF8 file up to8MiB/30 PDF pages, or one silent MP4/WebM up to16MiB/60s with crop and fps(0,24].
  • HCD controlled webpage/source-image search with sources, not Google native search or an image index. The cumulative50 CNY platform risk allowance uses conservative metered supplier upper bounds:30 CNY held per request, concurrency1; new search may stop before actual spending reaches50 CNY. It is not customer credit, free usage or an upstream bill cap.
  • Search and image components settle once from their original receipts. A successful search may remain charged when later image processing fails. Submitted jobs and result reading continue after the risk stop; ordinary generation/editing works independently.
  • HCD durable batches support create, disconnect, undispatched restart, status, cancellation and results.1..2 sequential items only:1K/1:1/minimal ormedium/max4096 output/one PNG-JPEG reference/no search. Standard realtime per-item rates apply, without Google native Batch discounts.
  • Native countTokens is advisory, not generation billing or the sole reservation bound. Input, implicit cache reads, text/thought output and image output are metered separately. Explicit cache/file URI/YouTube/native Batch storage are unavailable; upstream audio/function calling/structured output are unsupported. Original image bytes and provider provenance are preserved.
  • 4K and maximum context/output/14-reference extremes: not live-tested (high-cost exemption); exact model evidence and offline resource boundaries verified. Performance92.5 comes from two public image benchmarks; value66.5 is estimated from standard prices, not route performance testing.
GPT-5.6 Luna: complete within the verified safe deployment scope

The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.

  • Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
  • Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering is unavailable for this model.
  • A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
  • The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
  • Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
  • Current performance 64.2 and value 65.8 derive from public evaluations and coherent pricing, not an HCD live quality score.
GPT-5.6 Sol: complete within the verified safe deployment scope

Completion covers the exact model and verified safe deployment. Optional hosted capabilities and expensive boundaries retain explicit limits. Reservations, settled charges and unresolved liability stay separate.

  • Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, native Chat functions with explicit none, Responses functions, real Codex default tools and two-turn saved history were verified.
  • Raw streams, cache writes and reads, background completion after delivery disconnect, owned GET, stream replay and DELETE were accepted. WebSocket scope is text, low/default, 64 output tokens, one ordinary response.create continuation and two responses. This model does not support response.steer. The connector continues to use HTTP/SSE.
  • A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict full-context liability or are rejected before provider contact when funds are insufficient.
  • The long-context tier starts above 272,000 total input tokens, including cache, and applies to the whole request across input, cache reads, cache writes and output. Account and Key math was checked offline on both sides of the threshold. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
  • Pro, multi-agent, arbitrary remote MCP, indexed file search, containers, hosted Shell/Skills, hosted image generation and unverified sampling parameters remain closed; no parameter is silently discarded. Model audio/video input and direct non-text output are unsupported.
  • Existing performance 88.2 and value 70.5 use public evaluation evidence and coherent reviewed pricing, not HCD live quality scores.
GPT-5.6 Terra: complete within the verified safe deployment scope

The exact model is integrated across its verified safe deployment scope. Expensive limits and unpriced optional hosted features retain explicit restrictions.

  • Text and image input with text output; reasoning supports none, low, medium, high, xhigh and max, with medium as the default. Structured output, functions, real Codex default tools and a saved-history second turn were verified.
  • Raw streams and cache metering, background completion after disconnect, owned GET, replay and DELETE were accepted. WebSocket supports a verified two-response response.create chain; mid-response steering remains closed pending exact-model verification.
  • A small valid image was tested for transport, meaning and metering. Bounded images reserve the full documented image-token ceiling. Unknown media and files retain strict liability bounds and may be rejected before dispatch when funds are insufficient.
  • The long-context tier starts above 272,000 total input tokens, including cache, and prices the whole request. Account and Key calculations for input, cache reads, cache writes and output were checked offline across the boundary. Maximum context/output, live threshold crossing and large media are not live-tested (high-cost exemption).
  • Pro, multi-agent work, arbitrary remote MCP, indexed search, containers, hosted tools and image generation remain closed where price or lifecycle bounds are unverified. Parameters are not silently discarded. Model audio/video input and direct non-text output are unsupported.
  • Current performance 73.8 and value 62.9 derive from public evaluations and coherent pricing, not an HCD live quality score.
GPT-6 Astra: complete within the verified, safely available deployment scope

Completion covers the verified deployment scope, not every optional hosted capability. Known prices and provable quantity bounds govern availability. Holds and settled charges remain separate; authorization and budget gates remain active.

  • Verified text, low/medium/high/xhigh/max reasoning, structured output, Responses functions/namespaces/parallel and async tools, tool search, client computer/patch protocols, streaming, saved and encrypted history, cache, compaction and background resource lifecycle. Actual Codex default tools and saved-history continuation were independently tested.
  • PNG and bounded simple single-frame WebP/non-animated GIF were verified. The latter use low detail, dimensions up to 512 pixels and files up to 1 MiB. JPEG transport and metering passed, but a red fixture was described as Purple; that semantic case failed. Unknown media and remote URLs retain strict holds or rejection.
  • WebSocket scope is text, low reasoning, 64 output tokens, one queued steer and an automatic second response. The original response completes normally; immediate interruption and unverified tool/history combinations are not enabled.
  • The deployment rejects temperature on native Responses, and logit_bias/function tools on native Chat. Local guards remain. Other sampling controls and max_tokens are not verified; use max_completion_tokens for Chat and max_output_tokens for Responses.
  • file_search index size and retention bounds remain unresolved. Code Interpreter/container pricing has conflicting minute versus Session units. Pro/multi_agent aggregate quantities and costs lack proven bounds. These features remain restricted or disabled.
  • Hosted remote MCP was tested only with an owned fixed HTTPS echo, same-Key/project approval and two metered responses. Its temporary entry is closed. Arbitrary remote servers, variable results, credentials and broader lifecycle are not enabled; local MCP tests are not substitutes.
  • Batch, Flex and Fast/Priority are not offered by this deployment. Audio/video input and direct media output are outside its verified scope. Unavailable hosted image generation, Shell/Skills and other optional tools remain gated.
  • The 272,000-token tier uses total input including cache. An actual 272,022-input-token long-tier receipt was verified. Maximum context/output and other expensive boundaries retain offline checks and explicit high-cost live-test exemptions, not claims of maximum-size live generation.
GPT-6 Luna: complete within the verified, safely available deployment scope

Completion covers the verified safe deployment. Optional upstream features remain limited where bounds are unproved. Reservation and settlement stay separate, with exact-model authorization and cost gates.

  • Verified text, default medium and none/max, structured output, original streams, Chat functions with none, Responses async functions, a small image semantic case, actual Codex default tools and in-memory MCP across two turns, cache usage, background disconnect/completion/retrieve/stream replay/delete, and bounded WebSocket steering with two responses.
  • Reasoning choices are none, low, medium, high, xhigh and max, with medium as default. Chat functions require explicit none; max uses Responses.
  • WebSocket is limited to native text, low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector uses HTTP/SSE.
  • Maximum context/output, long-context threshold, large media and high-output compaction use official limits and offline checks: not live-tested (high-cost exemption). A small image was tested, but unknown media retains full-context reservation; no low-cost image bound is claimed.
  • Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills stay restricted where safe cost or lifecycle bounds are unproved. Model audio/video input and direct non-text model output are unsupported. Unverified sampling parameters are explicitly rejected.
  • Some exact-model public benchmarks exist, but the fixed 41-cell scoring panel has not passed a like-for-like review. Composite performance and value scores remain pending; no other model's estimate is reused.
GPT-6 Sol: complete within the verified, safely available deployment scope

Completion covers the verified safe deployment, not all optional official capabilities. Reservation bounds and actual settlement remain separate; exact-model authorization and cost gates remain active.

  • Verified text, default medium and none/max parameters, structured output, original streams, Chat function calling with none, Responses async functions, actual Codex default tools and in-memory MCP with two persisted turns, cache usage, and background disconnect/completion/replay/retrieve/delete.
  • Reasoning choices are none, low, medium, high, xhigh and max, with medium as the model default. Chat functions require explicit none; max uses Responses.
  • WebSocket availability is native text with low reasoning, default tier, 64 output tokens, one queued steer and two responses. The connector continues to use HTTP/SSE.
  • Maximum context/output, long-context thresholds, large media and high-output compaction use exact official limits and offline boundary checks: not live-tested (high-cost exemption). Unknown media retains full-context reservation; no low-cost or live image-understanding claim is made.
  • Conflicting official sampling descriptions remains unresolved, so those parameters are rejected. Pro, multi-agent, automatic compaction, arbitrary remote MCP, indexed file search, containers and hosted Shell/Skills remain restricted where safe cost or lifecycle bounds are unproved. Model audio/video inputs and direct non-text model outputs are unsupported.
  • Composite performance and value scores are marked estimated: 13 of 41 panel cells have exact-model public observations and 28 use same-metric peer estimates. These are not HCD deployment tests. Value uses reviewed public account-point rates, not actual charges. Rankings against GPT-5.6 Sol and other models apply only to this fixed panel; overlapping estimate ranges do not establish general capability order. Image semantics and dedicated tool-search/computer/apply-patch semantic cases were not separately live-tested.
GPT-6.1 Sol: complete within the verified deployment scope

The exact model is integrated across its currently verified scope. Expensive boundaries and unpriced hosted capabilities retain explicit restrictions.

  • Text and image input, text output. Five reasoning efforts: low, medium, high, xhigh and max; medium is default. none/minimal and native Chat tool calling are unsupported; use Responses for tools.
  • Strict structured output, functions and async options, streams and cache metering, real Codex default tools, an in-memory MCP round trip and a persisted second turn were verified.
  • Background completion after delivery disconnect, owned GET, stream replay and DELETE were verified. Narrow WebSocket allows one ordinary response.create continuation; steer remains pending and closed. Codex uses HTTP/SSE.
  • Points use the user-approved exact-model official tariff as an estimate. Supplier formal rates remain unconfirmed. Estimated pricing is used for reservation and account/Key service settlement, not confirmed supplier charges.
  • The whole request switches to long-context pricing above 272,000 total input tokens including cache. Maximum context/output, threshold crossing and large media are not live-tested (high-cost exemption); official limits and offline boundaries apply.
  • Unknown media/files retain full-context liability bounds and are rejected before dispatch when budgets are insufficient. Unpriced Pro, multi-agent, automatic compaction and hosted resources stay closed. Performance and value await exact numerical evidence.
GPT Audio: complete within the verified dedicated deployment scope

Verified dedicated audio inference with text/audio input and text/audio output, streaming and function calls. The public directory currently marks this entry as planned; access depends on the actual entry permissions.

  • This is acceptance of the exact audio interface, not a general Codex conversation-model claim. Image I/O, realtime sockets, structured-output schemas and discounted prompt cache are outside the verified scope.
  • Signed input limits bound resources; unsupported parameters are rejected before submission. Capability acceptance is not a quality benchmark, and directory scores retain their stated evidence grade.
GPT Audio 1.5: complete within the verified dedicated deployment scope

Verified GPT Audio 1.5 dedicated audio inference: text/audio input and text/audio output, streaming and function calls. The public directory currently marks it as planned.

  • Acceptance covers this exact audio interface; it does not activate a general Codex chat route. Images, realtime sockets, structured-output schemas and discounted cache pricing are outside scope.
  • Signed input contracts bound resources and reject unsupported parameters before submission. Directory scores are separate from this capability acceptance.
GPT Audio Mini: complete within the verified dedicated deployment scope

Verified GPT Audio Mini dedicated text/audio I/O, streaming and function calls. The public directory currently marks it as planned.

  • This is not a general Codex chat integration. Image I/O, realtime sockets and structured-output schemas are outside scope.
  • Cache hints and native usage reporting were verified, but live calls reported zero cached tokens; no actual hit or discount was proven. Unpublished discounted rates are not guessed.
  • Functional acceptance is not a quality benchmark; estimated directory scores remain estimates.
GPT Live Transcribe: complete within the verified dedicated deployment scope

Verified dedicated live audio transcription with context hints and streaming. The public directory currently marks it as planned.

  • This is a transcription entry, not general chat, function tools, a file-transcription endpoint or audio generation.
  • Signed contracts bound inputs and reject unsupported fields; capability acceptance is not a transcription-quality score.
GPT Realtime: complete within the verified dedicated deployment scope

Verified dedicated realtime text/audio/image input, text/audio output, streaming, functions and prompt caching. The public directory currently marks it as planned.

  • The entry uses HCD browser audio transport and a WebSocket proxy; it does not establish full WebSocket support for ordinary Codex chat clients.
  • Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are not offered. Functional acceptance is not a quality score.
GPT Realtime 1.5: complete within the verified dedicated deployment scope

Verified GPT Realtime 1.5 dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.

  • Acceptance covers browser audio transport and its WebSocket proxy, not full WebSocket capability in general Codex clients.
  • Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable; directory scores are separate from this acceptance.
GPT Realtime Mini: complete within the verified dedicated deployment scope

Verified GPT Realtime Mini dedicated realtime text/audio/image input, text/audio output, streaming, functions and caching. The public directory currently marks it as planned.

  • Scope is browser audio transport and its WebSocket proxy, not full WebSocket support for ordinary Codex clients.
  • Generated image/video output, structured-output schemas, reasoning-effort control, external SIP and hosted remote MCP are unavailable. Capability acceptance and estimated scores are separate.
Grok 4.7 — Full verified deployment scope

Native Chat, automatic-reasoning Responses and a four-effort Codex Chat bridge support text/images, JSON, tools and saved-thread history.

  • low, medium, high and xhigh passed live; high is the default and none is unsupported. Codex uses the Chat bridge; native Responses uses automatic reasoning.
  • Output includes reasoning tokens. Input including cache reads above200000 tokens applies the2x long-context tariff to the whole request. Cache hints are explicitly not forwarded; cache hits are not promised.
  • Actual full Codex tools, MCP echo and saved-thread continuation passed. Performance70.3 and value61.4 are estimates with0/41 direct coverage. Expensive context/media limits were not live-tested.
  • No provider-hosted Web/X/code tools or encrypted state claimed for this deployment. Google-100 has its own reviewed scope and prices.
  • xAI states No text output limit: no separate text-output cap. The500000 combined context still applies; HCD uses a finite supported ceiling and upstream actual-token handling, never reduces the default using fee estimates or claims a second independent500000 output budget.
Google Grok 4.7-100 — Fully reviewed deployed scope

Native Responses and Chat: text/images, four reasoning levels, JSON, complete tools and encrypted continuation.

  • low, medium, high and xhigh reviewed; high is the default and reasoning cannot be disabled. Adjustable native Google Responses was live verified.
  • Actual connector-generated Codex configuration, complete tools, MCP echo and same saved-thread continuation passed. Encrypted reasoning was replayed unchanged; cache keys and real cache hits were verified.
  • Performance70.3 and value61.4 are estimates, direct coverage0/41. Expensive context/media extremes were checked offline. Provider-hosted Web/X/code tools, Batch, upstream files, reasoning summaries and cache retention are not exposed.
  • Combined context524288 tokens; independent output maximum not disclosed. HCD context_bound support and default are constrained by remaining context, not a published independent output maximum.
MAI Thinking 1: complete within the verified dedicated deployment scope

Verified MAI Thinking 1 native text reasoning, function tools, history continuation, streaming/nonstreaming and token usage for a dedicated text-tool conversation.

  • The Responses bridge validates a complete result before replay; incremental Responses delivery is not implemented. Native API streaming preserves original events.
  • The directory labels it preview. Client support follows the verified entry and does not imply that every Codex function is exposed.
Mistral Medium 3.5: complete within the verified dedicated deployment scope

Verified Mistral Medium 3.5 native text/image input, text chat, JSON objects, streaming, multiple candidates and sampling through a dedicated text/code-tool entry.

  • The exact hosted offering does not advertise tool calling; HCD rejects tool fields before generation and does not present it as an ordinary Codex tool agent.
  • Explicit temperature=null or top_p=null is rejected locally after upstream rejection; omission uses defaults. The directory labels it preview, and estimated scores are separate.
Mistral OCR 4: complete within the verified dedicated deployment scope

Verified Mistral OCR 4.0 dedicated image/PDF recognition, text/table/image extraction, layout, page selection and multilingual OCR. This is a document entry, not a chat model.

  • The exact deployment accepts token, word and page confidence granularity; upstream rejects block granularity with 422, so it is rejected before submission.
  • The public directory labels it preview. Capability acceptance and performance/value score evidence remain separate.
通用多模态向量: complete within the verified dedicated deployment scope

Verified Multimodal Embedding v1 dedicated independent text, image and video vectors with ordered mixed batches. The public directory currently marks it as planned.

  • At most 20 inputs per batch, each producing a fixed 1024-dimensional vector. The provider processes at most 512 tokens per text item and truncates longer text; HCD preserves the submitted text and discloses this behavior.
  • Dense output, image URL/local input and relevant parameter forwarding are supported. No measured retrieval gain, modality fusion, variable dimensions, streaming or async Batch is claimed.
  • Performance 62.3 and value 48.1 remain low-confidence estimates, not direct exact-model evaluation. Media reservations and settled charges are separate.
qwen-DeepSeek-V4-Flash-0731：Verified integration (currently open scope)

Full integration within the verified open deployment scope: text, none/low/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.

  • Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
  • Original search receipts and historical charges are preserved; hosted search is currently closed. Own prices and scores unchanged.
  • Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
qwen-DeepSeek-V4-Pro · Verified open deployment scope

Full integration within the verified open deployment scope: text, none/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.

  • Performance 61.3, value 56.9: estimated fixed panel with 7 model-wide public observations and 34 estimates. Own standard tariff 3287671/6575342/cache273973 points per million tokens; no peak/off-peak tariff. Provider alias has no declared immutable snapshot. Separate Responses thinking reservation uses a conservative deployed output upper bound; expensive limits not live-tested. Supplier invoice cash remains unknown.
  • Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
qwen-DeepSeek-V4-Pro-0813 · Verified open deployment scope

Full integration within the verified open deployment scope: text, none/low/high/max, structured output, functions, complete default Codex tools, pure in-memory MCP, explicit saved-thread continuation and implicit cache. Hosted search/extraction/interpreter and native storage/response-ID/conversation/background are closed and explicitly rejected before provider dispatch.

  • Closed because aggregate agent iteration/charge bounds are unverified. max_output_tokens limits reply only; undocumented max_tool_calls is not a hard cap. The separate393216 reasoning-token maximum is reserved; high-cost extremes are not live-tested.
  • Performance71.7/value67.7 estimated;7 exact public model metrics and34 estimates in41 fixed panel. Value uses this offering's reviewed off-peak base workload; cache separate. Off-peak22:00–08:00 UTC+8; peak token rates x2. Supplier invoice cash unknown.
  • Current official reply/reasoning total shares393216; reservation uses that shared ceiling, preserving separate raw usage and once-only settlement.
Qwen-Image-2.1-Pro：complete within the verified deployment scope

Image-studio-only model; completion covers verified generation, editing, parameters, metering and native task lifecycle.

  • Unified generation/editing, up to10 reference images and1–6 outputs; transparent images, seed, prompt enhancement, Direct/Agent, enable_thinking and watermark. Agent is generation-only.
  • Static PNG/JPEG/WebP/BMP/TIFF/GIF inputs; native PNG output, with HCD JPEG/WebP conversion. Masks guide reference editing; HCD completion events are not native partial-image streaming.
  • Native async tasks return result_ref and continue after client disconnect. Original usage settles once; same-Key original-result reads are free. Provider results expire after24 hours; save returned images.
  • HCD bounds:18,000 prompt characters,10MB per image,64MiB aggregate,40M input pixels,8000-pixel sides and10:1 input ratio. Output area512²–2048² and ratio1:8–8:1. Six-output/ten-reference extremes use offline checks and high-cost live exemptions.
  • No ordinary Chat, function tools, web search, context cache or native Batch inference. Performance is a same-family public-data estimate, separate from functional acceptance.
Qwen3-VL-Rerank: complete within the verified dedicated deployment scope

Verified Qwen3 VL Rerank synchronous text, image, video and mixed-input reranking. The public directory currently marks it as planned.

  • Image queries, top_n, instructions, returned documents and native responses are supported. Video fps is strictly 0 < fps <= 1; exact deployment rejects zero and HCD rejects it before provider dispatch.
  • Official 4,000 query and 8,000 per-item token descriptions conflict. Exact limits remain upstream-enforced pending clarification; no invented truncation is applied.
  • 493154 points per million tokens for video-containing requests is an approved liability estimate, not a published supplier tariff or verified supplier cost. This synchronous entry has no streaming, Batch or file jobs.
千问3.7-通用文本重排序: complete within the verified dedicated deployment scope

Verified Qwen3.7 Text Rerank synchronous text reranking, instructions, top_n, all results and large candidate sets. The public directory currently marks it as planned.

  • Each document is limited to 50,000 characters; over-limit input is rejected before submission without truncation.
  • This dedicated reranking entry has no image/video, streaming, hosted tools, uploaded files or async jobs. Parameters from other models are not substituted. Estimated scores are not quality results from this acceptance.

LÍMITE ACTUAL

Límite actual

Se añaden 32 modelos ajenos a Google: 27 de texto, Mistral Document AI, tres de embeddings y Sora 2. Actualice al conector 1.0.86.0 y active cada plugin y permiso de la clave API. API de texto: 34 modelos; menú Codex: 32 con herramientas. Phi y Llama solo ofrecen consultas por API. Documentos: 30 MB y 30 páginas. Búsqueda con citas en textos locales seleccionados e índices reutilizables. Vídeo: 4/8/12 segundos, 720p, imágenes de referencia y remezcla de vídeos terminados. Descargue los vídeos pronto. Se factura el uso completado; leer la caché es gratis. Google y model-router siguen excluidos. Identidades, protocolos, datos, agentes y control permanecen en entornos locales, edge o privados autorizados por el cliente. El sitio público solo presenta el servicio; no controla equipos desde la nube.

Consulta de proyectoIniciar sesión