HENGCDHENGCD INDUSTRIAL AIMODEL PRICING
Preços e pontos claros
Consulte preços, integração do conector e condições de disponibilidade numa única página. O acesso real depende da chave API e da rota do servidor.
01
Escopo da página
Consulte preços, integração do conector e condições de disponibilidade numa única página. O acesso real depende da chave API e da rota do servidor.
Esta é uma visão geral traduzida. A versão chinesa prevalece nos detalhes técnicos e contratuais.
Os números vêm das listas publicadas de cada acesso, sem duplicados dentro de um estúdio. Um modelo pode aparecer em vários estúdios. O acesso e as funções dependem das permissões da chave API, das rotas do servidor e das especificações do modelo.
Completed capability declarations: 44. Each covers its stated deployment scope; model notes retain limits and pending items.
As tarifas Token são por milhão de Tokens. Outras capacidades usam a unidade indicada. Os escalões seguem a tarifa de cada modelo. A conta reflete o consumo real; o coeficiente da API Key aplica-se apenas aos pontos da chave. Os serviços disponíveis descontam pontos conforme a utilização real. A recarga online e a emissão de faturas continuam indisponíveis.
ModeloConsumo de pontos
Os modelos independentes têm prioridade. Um snapshot ou alias só é incluído quando constitui o único acesso disponível da mesma plataforma, geração e família de capacidades. Todos os tipos permite consultar outras versões com os seus próprios códigos, preços e estados. Dados pendentes não significam indisponibilidade. Vozes e serviços não são novos modelos de base. As rotas API e certificações são preservadas.
Exibidos / total: 482 / 613Claude Haiku 5.5
Verificação pendente (UTC+8)
claude-haiku-5-5Modelo independenteAnthropic · Estável2026-10-07Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho—Custo-benefício—
Sem avaliaçãoUso de entrada · por milhão de Tokens200.000 pontosUso de acertos de cache · por milhão de Tokens20.000 pontosUso de gravação em cache · 5m · por milhão de Tokens250.000 pontosUso de gravação em cache · 1h · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens1.000.000 pontosPesquisa na Web · por 1.000 unidades de pesquisa20.000.000 pontos
Claude Haiku 5.5-100
claude-haiku-5-5-100Modelo independenteAnthropic · Estável2026-10-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.7Custo-benefício · Estimated82.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
Sem avaliação · 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.Preço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Gemini Nano Banana 2.1-100
Verificação pendente (UTC+8)
gemini-nano-banana-2.1Modelo independenteGoogle · Estável2026-10-06Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho92.5Custo-benefício · Estimated66.5
Provisório
Sem avaliação · Confidence 0%Uso de entrada · por milhão de Tokens3.000.000 pontosUso de entrada · Imagem · por milhão de Tokens3.000.000 pontosUso de acertos de cache · por milhão de Tokens300.000 pontosUso de saída · por milhão de Tokens15.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens300.000 pontosUso de saída · Imagem · por milhão de Tokens60.000.000 pontos
Qwen-Image-2.1-Pro
Verificação pendente (UTC+8)
qwen-image-2.1-proModelo independenteQwen · Estável2026-10-02Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated66.4Custo-benefício · Estimated61.5
Estimate basis
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem68.494 pontos
Grok 4.7-100
Verificação pendente (UTC+8)
grok-4.7-100Modelo independentexAI · Prévia2026-09-30Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho—Custo-benefício—
Sem avaliaçãoUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens1.000.000 pontosUso de saída · por milhão de Tokens12.000.000 pontos
GPT-6.1 Sol
Verificação pendente (UTC+8)
gpt-6.1-solModelo independenteOpenAI · Estável2026-09-29Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated82.2Custo-benefício · Estimated69.2
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens200.000 pontosUso de gravação em cache · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
Claude Sonnet 5.5
Verificação pendente (UTC+8)
claude-sonnet-5-5Modelo independenteAnthropic · Estável2026-09-28Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated74.4Custo-benefício · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de gravação em cache · 5m · por milhão de Tokens5.000.000 pontosUso de gravação em cache · 1h · por milhão de Tokens8.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontosPesquisa na Web · por 1.000 unidades de pesquisa20.000.000 pontos
Claude Sonnet 5.5-100
claude-sonnet-5-5-100Modelo independenteAnthropic · Estável2026-09-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.4Custo-benefício · Estimated67.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
决策模型（预览版）
Verificação pendente (UTC+8)
decision-model-previewModelo independenteQwen · Estável2026-09-24Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens0 pontos
Gemini 3.8 Live-100
Verificação pendente (UTC+8)
gemini-3.8-liveModelo independenteGoogle · Estável2026-09-24Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated76.9Custo-benefício · Estimated68.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.500.000 pontosEntrada de vídeo · por milhão de Tokens2.000.000 pontosUso de entrada · Áudio · por milhão de Tokens6.000.000 pontosUso de saída · por milhão de Tokens9.000.000 pontosUso de saída · Áudio · por milhão de Tokens24.000.000 pontosUso de saída · Geração de vídeo · por milhão de Tokens2.000.000 pontos
Claude Opus 5.5
Verificação pendente (UTC+8)
claude-opus-5-5Modelo independenteAnthropic · Estável2026-09-22Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated86.9Custo-benefício · Estimated69.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de gravação em cache · 5m · por milhão de Tokens10.000.000 pontosUso de gravação em cache · 1h · por milhão de Tokens16.000.000 pontosUso de saída · por milhão de Tokens40.000.000 pontosPesquisa na Web · por 1.000 unidades de pesquisa20.000.000 pontos
Claude Opus 5.5-100
claude-opus-5-5-100Modelo independenteAnthropic · Estável2026-09-22Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated86.9Custo-benefício · Estimated75.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-6 Luna
Verificação pendente (UTC+8)
gpt-6-lunaModelo independenteOpenAI · Estável2026-09-22Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.4Custo-benefício · Estimated65.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens200.000 pontosUso de acertos de cache · por milhão de Tokens20.000 pontosUso de gravação em cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens1.000.000 pontos
GPT-6 Sol
Verificação pendente (UTC+8)
gpt-6-solModelo independenteOpenAI · Estável2026-09-22Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated74.3Custo-benefício · Estimated63.7
Version comparison review13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de gravação em cache · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
Grok 4.7
Verificação pendente (UTC+8)
grok-4.7Modelo independentexAI · Estável2026-09-21Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho—Custo-benefício—
Sem avaliaçãoUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens1.000.000 pontosUso de saída · por milhão de Tokens12.000.000 pontos
Qwen-Audio-3.1-Realtime-Plus
qwen-audio-3.1-realtime-plusModelo independenteQwen · Estável2026-09-20Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.8-Livetranslate-Flash-Realtime
qwen3.8-livetranslate-flash-realtimeModelo independenteQwen · Estável2026-09-18Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Uni
qwen-mt-uniModelo independenteQwen · Estável2026-09-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated49.4Custo-benefício · Estimated49.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-kimi/kimi-k2.8-preview
Verificação pendente (UTC+8)
qwen-kimi-kimi-k2.8-previewModelo independenteMoonshot AI · Estável2026-09-11Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens465.753 pontosUso de saída · por milhão de Tokens7.397.260 pontos
DeepSeek V4.1 Flash
Verificação pendente (UTC+8)
deepseek-flashModelo independenteDeepSeek · Estável2026-09-10Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated78.1Custo-benefício · Estimated77.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens300.000 pontosUso de acertos de cache · por milhão de Tokens6.000 pontosUso de saída · por milhão de Tokens1.200.000 pontos
doubao-deepseek-v4-1-flash
Verificação pendente (UTC+8)
doubao-deepseek-v4-1-flash-260910Snapshot / versão fixa · Acesso únicoDeepSeek · Estável2026-09-10Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens273.973 pontosUso de acertos de cache · por milhão de Tokens5.479 pontosUso de saída · por milhão de Tokens1.095.890 pontos
qwen-DeepSeek V4.1 Flash
Verificação pendente (UTC+8)
qwen-deepseek-v4.1-flashModelo independenteDeepSeek · Estável2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.4Custo-benefício · Estimated66.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens273.973 pontosUso de acertos de cache · por milhão de Tokens27.397 pontosUso de saída · por milhão de Tokens1.095.890 pontos
qwen-vanchin/deepseek-v4.1-flash
qwen-vanchin-deepseek-v4.1-flashModelo independenteDeepSeek · Estável2026-09-10Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated61.4Custo-benefício · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT Image 2.5 Flare
Verificação pendente (UTC+8)
gpt-image-2.5-flareModelo independenteOpenAI · Estável2026-09-08Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho98.5Custo-benefício70.3
Uso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens2.500.000 pontosUso de entrada · Imagem · por milhão de Tokens16.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens4.000.000 pontosUso de saída · Imagem · por milhão de Tokens60.000.000 pontos
GPT Image 2.5 Sunburst
Verificação pendente (UTC+8)
gpt-image-2.5-sunburstModelo independenteOpenAI · Estável2026-09-08Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho100.0Custo-benefício71.4
Uso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens2.500.000 pontosUso de entrada · Imagem · por milhão de Tokens16.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens4.000.000 pontosUso de saída · Imagem · por milhão de Tokens60.000.000 pontos
GPT-6 Astra
Verificação pendente (UTC+8)
gpt-6-astraModelo independenteOpenAI · Estável2026-09-03Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated85.4Custo-benefício · Estimated64.8
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens20.000.000 pontosUso de acertos de cache · por milhão de Tokens2.000.000 pontosUso de gravação em cache · por milhão de Tokens25.000.000 pontosUso de saída · por milhão de Tokens100.000.000 pontos
Gemini 3.8 Flash-100
Verificação pendente (UTC+8)
gemini-3.8-flash-100Modelo independenteGoogle · Estável2026-09-02Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho—Custo-benefício—
Sem avaliaçãoUso de entrada · por milhão de Tokens3.000.000 pontosUso de entrada · Imagem · por milhão de Tokens3.000.000 pontosUso de entrada · Áudio · por milhão de Tokens3.000.000 pontosEntrada de vídeo · por milhão de Tokens3.000.000 pontosUso de acertos de cache · por milhão de Tokens300.000 pontosUso de saída · por milhão de Tokens15.000.000 pontosUso de gravação em cache · por milhão de Tokens3.000.000 pontosArmazenamento de cache explícita · por milhão de tokens-hora2.000.000 pontos
Claude Fable 5.1
Verificação pendente (UTC+8)
claude-fable-5-1Modelo independenteAnthropic · Estável2026-09-01Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated89.2Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens20.000.000 pontosUso de acertos de cache · por milhão de Tokens500.000 pontosUso de gravação em cache · 5m · por milhão de Tokens25.000.000 pontosUso de gravação em cache · 1h · por milhão de Tokens40.000.000 pontosUso de saída · por milhão de Tokens100.000.000 pontosPesquisa na Web · por 1.000 unidades de pesquisa20.000.000 pontos
Claude Fable 5.1-100
claude-fable-5-1-100Modelo independenteAnthropic · Estável2026-09-01Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated89.2Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Doubao-Seed-2.1-Lite
Verificação pendente (UTC+8)
doubao-seed-2-1-lite-260915Snapshot / versão fixa · Acesso únicoDoubao · Estável2026-09 (apenas mês oficial)Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated63.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens739.726 pontos
doubao-seedream-5-0-flash
doubao-seedream-5-0-flash-260915Snapshot / versão fixa · Acesso únicoDoubao · Estável2026-09 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated65.8Custo-benefício · Estimated61.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
千问3.7-通用文本向量-flash
Verificação pendente (UTC+8)
qwen3.7-text-embedding-flashModelo independenteAlibaba Cloud · Estável2026-09-01Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated73.6
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens34.247 pontos
千问3.7-通用文本重排序
Verificação pendente (UTC+8)
qwen3.7-text-rerankModelo independenteAlibaba Cloud · Estável2026-09-01Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated72.5Custo-benefício · Estimated80.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens136.987 pontos
Qwen3.8-Omni-Flash
qwen3.8-omni-flashModelo independenteQwen · Estável2026-09 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated61.4Custo-benefício · Estimated58.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.8-Omni-Flash-Realtime
qwen3.8-omni-flash-realtimeModelo independenteQwen · Estável2026-09 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Image-2.0
qwen-mt-image-2.0Modelo independenteQwen · Estável2026-08-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated73.8Custo-benefício · Estimated66.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Cohere Parse v5
Verificação pendente (UTC+8)
cohere-parse-v5Modelo independenteCohere · Prévia2026-08-27Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho79.2Custo-benefício85.4
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%cohere-parsebench · OfficialProcessamento de documentos · por 1.000 páginas3.000.000 pontos
Gemini Omni 1.1 Flash Preview-100
gemini-omni-1.1-flash-previewModelo independenteGoogle · Estável2026-08-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated49.9Custo-benefício · Estimated49.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ZHIPU/GLM-5.3-Flash
Verificação pendente (UTC+8)
qwen-zhipu-glm-5.3-flashModelo independenteZhipu AI · Estável2026-08-26Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated48.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens63.014 pontosUso de saída · por milhão de Tokens767.123 pontos
Qwen3.8-Flash
Verificação pendente (UTC+8)
qwen3.8-flashModelo independenteQwen · Estável2026-08-25Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.4Custo-benefício · Estimated67.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens27.397 pontosUso de saída · por milhão de Tokens739.726 pontos
qwen-Kimi-K3
Verificação pendente (UTC+8)
qwen-kimi-k3Modelo independenteMoonshot · Estável2026-08-19Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated39.7Custo-benefício · Estimated38.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens5.479.452 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens27.397.260 pontos
Qwen3.8-27B
Verificação pendente (UTC+8)
qwen3.8-27bModelo independenteQwen · Estável2026-08-17Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated65.0Custo-benefício · Estimated64.2
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens164.384 pontosUso de saída · por milhão de Tokens3.287.671 pontos
qwen-GLM-5.3
Verificação pendente (UTC+8)
qwen-glm-5.3Modelo independenteZhipu AI · Estável2026-08-14Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.1Custo-benefício · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
qwen-ZHIPU/GLM-5.3
Verificação pendente (UTC+8)
qwen-zhipu-glm-5.3Modelo independenteZhipu AI · Estável2026-08-14Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
DeepSeek V4 Pro
Verificação pendente (UTC+8)
deepseek-v4-proModelo independenteDeepSeek · Estável2026-08-13Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated64.4Custo-benefício · Estimated62.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.320.000 pontosUso de acertos de cache · por milhão de Tokens44.000 pontosUso de saída · por milhão de Tokens3.960.000 pontos
GLM-5.3
Verificação pendente (UTC+8)
glm-5.3Modelo independenteZhipu · Estável2026-08-13Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated71.7Custo-benefício · Estimated65.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
GLM-5.3-Flash
Verificação pendente (UTC+8)
glm-5.3-flashModelo independenteZhipu · Estável2026-08-13Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated65.1Custo-benefício · Estimated70.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens63.014 pontosUso de saída · por milhão de Tokens767.123 pontos
Grok 4.6
Verificação pendente (UTC+8)
grok-4.6Modelo independentexAI · Prévia2026-08-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated70.4Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens2.000.000 pontosUso de saída · por milhão de Tokens24.000.000 pontos
Grok 4.6-100
grok-4.6-100Modelo independentexAI · Estável2026-08-12Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated70.4Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
MAI Thinking 1
Verificação pendente (UTC+8)
mai-thinking-1Modelo independenteMicrosoft AI · Prévia2026-08-12Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated51.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens16.000.000 pontos
Qwen3.8-2.4T-A95B
Verificação pendente (UTC+8)
qwen3.8-2.4t-a95bModelo independenteQwen · Estável2026-08-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated65.0Custo-benefício · Estimated58.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens410.959 pontosUso de saída · por milhão de Tokens9.863.014 pontos
万相3.0-视频生成
Verificação pendente (UTC+8)
wan3.0-videoModelo independenteAlibaba Cloud · Estável2026-08-06Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated92.6Custo-benefício · Estimated72.9
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo57.535 pontosGeração de vídeo 720P · por segundo115.069 pontosGeração de vídeo 1080P · por segundo230.137 pontos
Qwen3.8-Max
Verificação pendente (UTC+8)
qwen3.8-maxModelo independenteQwen · Estável2026-08-02Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated76.0Custo-benefício · Estimated66.6
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens410.959 pontosUso de saída · por milhão de Tokens9.863.014 pontos
Gemini 3.5 Transcribe Live Preview-100
gemini-3.5-transcribe-live-previewModelo independenteGoogle · Estável2026-08 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Gemini 3.5 Transcribe Preview-100
gemini-3.5-transcribe-previewModelo independenteGoogle · Estável2026-08 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-DeepSeek V4 Flash GA (2026-07-31)
Verificação pendente (UTC+8)
doubao-deepseek-v4-flash-ga-260731Snapshot / versão fixa · Acesso únicoDeepSeek · Estável2026-07-31Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated58.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens27.397 pontosUso de saída · por milhão de Tokens2.465.753 pontos
qwen-MiniMax/MiniMax-H3
qwen-minimax-minimax-h3Modelo independentemini-max · Estável2026-07-31Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.0-ASR-Flash
Verificação pendente (UTC+8)
qwen-audio-3.0-asr-flashModelo independenteAlibaba Cloud · Estável2026-07-30Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated94.0
Estimate basis
2026-10-08 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 · IndependentTranscrição · por segundo61 pontos
qwen-audio-3.0-asr-flash-filetrans
qwen-audio-3.0-asr-flash-filetransModelo independenteQwen · Estável2026-07-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.0-ASR-Flash-Streaming
qwen-audio-3.0-asr-flash-streamingModelo independenteQwen · Estável2026-07-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT Live Transcribe
Verificação pendente (UTC+8)
gpt-live-transcribeModelo independenteOpenAI · Estável2026-07-28Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated64.0
Estimate basis
2026-10-08 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 · IndependentTranscrição · por hora2.040.000 pontos
GPT Transcribe
Verificação pendente (UTC+8)
gpt-transcribeModelo independenteOpenAI · Estável2026-07-28Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated81.7
Estimate basis
2026-10-08 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 · IndependentTranscrição · por hora540.000 pontos
qwen-PixVerse-V6-r2v-omni
qwen-pixverse-pixverse-v6-r2v-omniModelo independentepixverse · Estável2026-07-26Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated61.1Custo-benefício · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Claude Opus 5
Verificação pendente (UTC+8)
claude-opus-5Modelo independenteAnthropic · Estável2026-07-24Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated81.9Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens1.000.000 pontosUso de gravação em cache · 5m · por milhão de Tokens12.500.000 pontosUso de gravação em cache · 1h · por milhão de Tokens20.000.000 pontosUso de saída · por milhão de Tokens50.000.000 pontos
Claude Opus 5-100
claude-opus-5-100Modelo independenteAnthropic · Estável2026-07-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated81.9Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Gemini 3.5 Flash-Lite-100
Verificação pendente (UTC+8)
gemini-3.5-flash-lite-100Modelo independenteGoogle · Estável2026-07-21Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated52.3Custo-benefício · Estimated55.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens600.000 pontosUso de acertos de cache · por milhão de Tokens60.000 pontosUso de saída · por milhão de Tokens5.000.000 pontos
Qwen3.7-Flash
Verificação pendente (UTC+8)
qwen3.7-flashModelo independenteQwen · Estável2026-07-21Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.4Custo-benefício · Estimated73.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 32.000 TokenUso de entrada · por milhão de Tokens54.795 pontosUso de acertos de cache · por milhão de Tokens10.959 pontosUso de saída · por milhão de Tokens219.178 pontos
Input 32.001 – 256.000 TokenUso de entrada · por milhão de Tokens164.384 pontosUso de acertos de cache · por milhão de Tokens32.877 pontosUso de saída · por milhão de Tokens657.534 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens65.753 pontosUso de saída · por milhão de Tokens1.315.068 pontos
Qwen-Image-3.0
Verificação pendente (UTC+8)
qwen-image-3.0Modelo independenteAlibaba Cloud · Estável2026-07-21Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated73.8Custo-benefício · Estimated81.7
Estimate basis
2026-10-08 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 · IndependentImagem Uso de entrada 1K · por imagem5.480 pontosImagem Uso de entrada 2K · por imagem5.480 pontosImagem Uso de saída 1K · por imagem49.316 pontosImagem Uso de saída 2K · por imagem49.316 pontos
Kimi K3
Verificação pendente (UTC+8)
kimi-k3Modelo independenteMoonshot · Estável2026-07-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.1Custo-benefício · Estimated66.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens5.479.452 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens27.397.260 pontos
qwen-kimi/kimi-k3
Verificação pendente (UTC+8)
qwen-kimi-kimi-k3Modelo independenteMoonshot AI · Estável2026-07-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens5.479.452 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens27.397.260 pontos
Qwen3.7-通用文本向量
Verificação pendente (UTC+8)
qwen3.7-text-embeddingModelo independenteAlibaba Cloud · Estável2026-07-15Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated53.1
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens136.987 pontos
Qwen-Audio-3.0-Realtime-Flash
qwen-audio-3.0-realtime-flashModelo independenteQwen · Estável2026-07-14Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.0-Realtime-Plus
qwen-audio-3.0-realtime-plusModelo independenteQwen · Estável2026-07-14Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5.6 Luna
Verificação pendente (UTC+8)
gpt-5.6-lunaModelo independenteOpenAI · Estável2026-07-09Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated63.7Custo-benefício · Estimated65.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens400.000 pontosUso de acertos de cache · por milhão de Tokens40.000 pontosUso de gravação em cache · por milhão de Tokens500.000 pontosUso de saída · por milhão de Tokens2.400.000 pontos
GPT-5.6 Sol
Verificação pendente (UTC+8)
gpt-5.6-solModelo independenteOpenAI · Estável2026-07-09Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated83.1Custo-benefício · Estimated67.0
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens800.000 pontosUso de gravação em cache · por milhão de Tokens10.000.000 pontosUso de saída · por milhão de Tokens40.000.000 pontos
GPT-5.6 Terra
Verificação pendente (UTC+8)
gpt-5.6-terraModelo independenteOpenAI · Estável2026-07-09Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated73.1Custo-benefício · Estimated62.5
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de gravação em cache · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens24.000.000 pontos
gpt-live-1
gpt-live-1Modelo independenteOpenAI · Estável2026-07-08Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated48.3Custo-benefício · Estimated48.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT Realtime 2.1
Verificação pendente (UTC+8)
gpt-realtime-2.1Modelo independenteOpenAI · Prévia2026-07-06Voz e texto em tempo real disponíveis. Imagens e execução de ferramentas durante a chamada não estão ativadas.Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated45.3Custo-benefício · Estimated31.7
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens800.000 pontosUso de saída · por milhão de Tokens48.000.000 pontosUso de entrada · Imagem · por milhão de Tokens10.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens1.000.000 pontosUso de entrada · Áudio · por milhão de Tokens64.000.000 pontosUso de acertos de cache · Áudio · por milhão de Tokens800.000 pontosUso de saída · Áudio · por milhão de Tokens128.000.000 pontos
GPT Realtime 2.1 Mini
Verificação pendente (UTC+8)
gpt-realtime-2.1-miniModelo independenteOpenAI · Prévia2026-07-06Voz e texto em tempo real disponíveis. Imagens e execução de ferramentas durante a chamada não estão ativadas.Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated45.3Custo-benefício · Estimated61.7
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens1.200.000 pontosUso de acertos de cache · por milhão de Tokens120.000 pontosUso de saída · por milhão de Tokens4.800.000 pontosUso de entrada · Imagem · por milhão de Tokens1.600.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens160.000 pontosUso de entrada · Áudio · por milhão de Tokens20.000.000 pontosUso de acertos de cache · Áudio · por milhão de Tokens600.000 pontosUso de saída · Áudio · por milhão de Tokens40.000.000 pontos
Qwen-Audio-3.0-TTS-Flash
Verificação pendente (UTC+8)
qwen-audio-3.0-tts-flashModelo independenteAlibaba Cloud · Estável2026-07 (apenas mês oficial)Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated74.4Custo-benefício · Estimated74.8
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres273.973 pontos
Qwen-Audio-3.0-TTS-Plus
Verificação pendente (UTC+8)
qwen-audio-3.0-tts-plusModelo independenteAlibaba Cloud · Estável2026-07 (apenas mês oficial)Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated74.4Custo-benefício · Estimated63.8
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres383.562 pontos
claude-sonnet-5
claude-sonnet-5Modelo independenteAnthropic · Estável2026-06-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated70.2Custo-benefício · Estimated64.1
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-sonnet-5-100
claude-sonnet-5-100Modelo independenteAnthropic · Estável2026-06-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated70.2Custo-benefício · Estimated64.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Doubao Seed 2.1 Turbo (2026-06-28)
Verificação pendente (UTC+8)
doubao-seed-2-1-turbo-260628Snapshot / versão fixa · Acesso únicoByteDance · Estável2026-06-28Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated57.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens164.384 pontosUso de saída · por milhão de Tokens4.109.589 pontos
Mistral OCR 4
Verificação pendente (UTC+8)
mistral-ocr-4-0Modelo independenteMistral AI · Prévia2026-06-23Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho81.8Custo-benefício57.3
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 25%mistral-ocr · Officialcohere-parsebench · OfficialProcessamento de documentos · por 1.000 páginas8.000.000 pontosDocumentos com anotações estruturadas · por 1.000 páginas10.000.000 pontos
HappyHorse-1.1-I2V
Verificação pendente (UTC+8)
happyhorse-1.1-i2vModelo independenteAlibaba Cloud · Estável2026-06-22Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo123.288 pontosGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo328.768 pontos
HappyHorse-1.1-R2V
Verificação pendente (UTC+8)
happyhorse-1.1-r2vModelo independenteAlibaba Cloud · Estável2026-06-22Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo123.288 pontosGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo328.768 pontos
HappyHorse-1.1-T2V
Verificação pendente (UTC+8)
happyhorse-1.1-t2vModelo independenteAlibaba Cloud · Estável2026-06-22Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo123.288 pontosGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo328.768 pontos
doubao-GLM 5.2 (2026-06-17)
Verificação pendente (UTC+8)
doubao-glm-5-2-260617Snapshot / versão fixa · Acesso únicoZhipu · Estável2026-06-17Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated54.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
qwen-HappyOyster-1.0-Adventure
qwen-happyoyster-1.0-adventureModelo independentehappyoyster · Estável2026-06-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated43.2Custo-benefício · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GLM-5.2
Verificação pendente (UTC+8)
glm-5.2Modelo independenteZhipu · Estável2026-06-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated66.4Custo-benefício · Estimated61.3
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
Qwen3.5-OCR
Verificação pendente (UTC+8)
qwen3.5-ocrModelo independenteAlibaba Cloud · Estável2026-06-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated81.8Custo-benefício · Estimated72.3
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens136.987 pontosUso de saída · por milhão de Tokens547.946 pontos
qwen-GLM-5.2
Verificação pendente (UTC+8)
qwen-glm-5.2Modelo independenteZhipu · Estável2026-06-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.1Custo-benefício · Estimated57.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
qwen-pixverse/pixverse-upscale
qwen-pixverse-pixverse-upscaleModelo independentepixverse · Estável2026-06-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ZHIPU/GLM-5.2
Verificação pendente (UTC+8)
qwen-zhipu-glm-5.2Modelo independenteZhipu AI · Estável2026-06-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
qwen-kimi-k2.7-code
Verificação pendente (UTC+8)
qwen-kimi-k2.7-codeModelo independenteMoonshot · Estável2026-06-15Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated34.7Custo-benefício · Estimated39.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens356.164 pontosUso de saída · por milhão de Tokens7.397.260 pontos
Kimi K2.7 Code
Verificação pendente (UTC+8)
kimi-k2.7-codeModelo independenteMoonshot · Estável2026-06-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated46.3Custo-benefício · Estimated47.8
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens356.164 pontosUso de saída · por milhão de Tokens7.397.260 pontos
qwen-kimi/kimi-k2.7-code
Verificação pendente (UTC+8)
qwen-kimi-kimi-k2.7-codeModelo independenteMoonshot AI · Estável2026-06-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated29.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens356.164 pontosUso de saída · por milhão de Tokens7.397.260 pontos
claude-fable-5
claude-fable-5Modelo independenteAnthropic · Estável2026-06-09Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated87.7Custo-benefício · Estimated76.4
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-fable-5-100
claude-fable-5-100Modelo independenteAnthropic · Estável2026-06-09Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated87.7Custo-benefício · Estimated76.4
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.7-Max-2026-06-08
Verificação pendente (UTC+8)
qwen3.7-max-2026-06-08Snapshot / versão fixa · Acesso únicoQwen · Estável2026-06-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated64.5Custo-benefício · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens657.534 pontosUso de saída · por milhão de Tokens9.863.014 pontos
doubao-seedance-2-5-260628
Verificação pendente (UTC+8)
doubao-seedance-2-5-260628Snapshot / versão fixa · Acesso únicoByteDance · Estável2026-06 (apenas mês oficial)Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated90.4Custo-benefício · Estimated63.3
Version comparison reviewEstimate basis
2026-10-08 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 · IndependentUso de saída · Geração de vídeo · por milhão de Tokens19.178.083 pontos
doubao-seed-evolving
doubao-seed-evolvingAlias · Acesso únicoDoubao · Estável2026-06 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-seedream-5-0-pro-260628
Verificação pendente (UTC+8)
doubao-seedream-5-0-pro-260628Snapshot / versão fixa · Acesso únicoByteDance · Estável2026-06 (apenas mês oficial)Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated85.2Custo-benefício · Estimated69.2
Estimate basis
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem82.192 pontosUso de entrada · Imagem · por imagem5.480 pontos
Fun-ASR-Flash-2026-06-15
Verificação pendente (UTC+8)
fun-asr-flash-2026-06-15Snapshot / versão fixa · Acesso únicoAlibaba Cloud · Estável2026-06 (apenas mês oficial)Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated94.0
Estimate basis
2026-10-08 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 · IndependentTranscrição · por segundo61 pontos
Qwen3.7-Plus
Verificação pendente (UTC+8)
qwen3.7-plusModelo independenteQwen · Estável2026-06-01Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.0Custo-benefício · Estimated60.5
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 256.000 TokenUso de entrada · por milhão de Tokens438.356 pontosUso de acertos de cache · por milhão de Tokens87.671 pontosUso de saída · por milhão de Tokens1.753.425 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens1.315.068 pontosUso de acertos de cache · por milhão de Tokens263.014 pontosUso de saída · por milhão de Tokens5.260.274 pontos
qwen-MiniMax/MiniMax-M3
Verificação pendente (UTC+8)
qwen-minimax-minimax-m3Modelo independentemini-max · Estável2026-06-01Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated46.0
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.150.685 pontosUso de acertos de cache · por milhão de Tokens230.137 pontosUso de saída · por milhão de Tokens4.602.740 pontos
qwen-stepfun/step-3.7-flash
Verificação pendente (UTC+8)
qwen-stepfun-step-3.7-flashModelo independentestepfun · Estável2026-05-29Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.4Custo-benefício · Estimated64.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens369.863 pontosUso de acertos de cache · por milhão de Tokens73.973 pontosUso de saída · por milhão de Tokens2.219.178 pontos
claude-opus-4-8
claude-opus-4-8Modelo independenteAnthropic · Estável2026-05-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.3Custo-benefício · Estimated67.0
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-opus-4-8-100
claude-opus-4-8-100Modelo independenteAnthropic · Estável2026-05-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.3Custo-benefício · Estimated67.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.7-Max
Verificação pendente (UTC+8)
qwen3.7-maxModelo independenteQwen · Estável2026-05-21Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated64.5Custo-benefício · Estimated58.6
8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens657.534 pontosUso de saída · por milhão de Tokens9.863.014 pontos
Cohere Command A Plus
Verificação pendente (UTC+8)
cohere-command-a-plus-05-2026Modelo independenteCohere · Prévia2026-05-20Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated55.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.600.000 pontosUso de saída · por milhão de Tokens6.400.000 pontos
Qwen3.7-Max-Preview
Verificação pendente (UTC+8)
qwen3.7-max-previewModelo independenteQwen · Prévia2026-05-20Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated64.5Custo-benefício · Estimated58.6
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens9.863.014 pontos
Qwen3.5-LiveTranslate-Flash-Realtime
qwen3.5-livetranslate-flash-realtimeModelo independenteQwen · Estável2026-05-19Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Grok 4.3
Verificação pendente (UTC+8)
grok-4.3Modelo independentexAI · Prévia2026-05-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated44.8Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens5.000.000 pontos
Mistral Medium 3.5
Verificação pendente (UTC+8)
mistral-medium-3-5Modelo independenteMistral AI · Prévia2026-04-28Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated60.6Custo-benefício · Estimated55.3
6/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.000.000 pontosUso de saída · por milhão de Tokens15.000.000 pontos
HappyHorse-1.0-I2V
Verificação pendente (UTC+8)
happyhorse-1.0-i2vModelo independenteAlibaba Cloud · Estável2026-04-27Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo438.357 pontos
HappyHorse-1.0-R2V
Verificação pendente (UTC+8)
happyhorse-1.0-r2vModelo independenteAlibaba Cloud · Estável2026-04-27Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo438.357 pontos
HappyHorse-1.0-T2V
Verificação pendente (UTC+8)
happyhorse-1.0-t2vModelo independenteAlibaba Cloud · Estável2026-04-27Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.9Custo-benefício · Estimated56.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo246.576 pontosGeração de vídeo 1080P · por segundo438.357 pontos
qwen-DeepSeek-V4-Pro
Verificação pendente (UTC+8)
qwen-deepseek-v4-proModelo independenteDeepSeek · Estável2026-04-24Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated70.1Custo-benefício · Estimated63.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.287.671 pontosUso de acertos de cache · por milhão de Tokens273.973 pontosUso de saída · por milhão de Tokens6.575.342 pontos
GPT-5.5
Verificação pendente (UTC+8)
gpt-5.5Modelo independenteOpenAI · Estável2026-04-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated80.5Custo-benefício · Estimated63.8
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens1.000.000 pontosUso de saída · por milhão de Tokens60.000.000 pontos
qwen-xiaomi/mimo-v2.5-pro
Verificação pendente (UTC+8)
qwen-xiaomi-mimo-v2.5-proModelo independenteXiaomi · Estável2026-04-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated30.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.917.808 pontosUso de acertos de cache · por milhão de Tokens383.562 pontosUso de saída · por milhão de Tokens5.753.425 pontos
Qwen3.6-27B
Verificação pendente (UTC+8)
qwen3.6-27bModelo independenteQwen · Estável2026-04-22Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated46.6Custo-benefício · Estimated50.5
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens4.931.507 pontos
GPT Image 2
Verificação pendente (UTC+8)
gpt-image-2Modelo independenteOpenAI · Estável2026-04-21Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho97.0Custo-benefício69.3
Uso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens2.500.000 pontosUso de entrada · Imagem · por milhão de Tokens16.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens4.000.000 pontosUso de saída · Imagem · por milhão de Tokens60.000.000 pontos
qwen-Kimi-K2.6
Verificação pendente (UTC+8)
qwen-kimi-k2.6Modelo independenteMoonshot · Estável2026-04-21Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated34.9Custo-benefício · Estimated39.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens356.164 pontosUso de saída · por milhão de Tokens7.397.260 pontos
Kimi K2.6
Verificação pendente (UTC+8)
kimi-k2.6Modelo independenteMoonshot · Estável2026-04-20Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated77.4Custo-benefício · Estimated69.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens301.370 pontosUso de saída · por milhão de Tokens7.397.260 pontos
qwen-Kimi/Kimi K2.6
Verificação pendente (UTC+8)
qwen-kimi-kimi-k2.6Modelo independenteMoonshot AI · Estável2026-04-20Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated29.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.780.822 pontosUso de acertos de cache · por milhão de Tokens301.370 pontosUso de saída · por milhão de Tokens7.397.260 pontos
claude-opus-4-7
claude-opus-4-7Modelo independenteAnthropic · Estável2026-04-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.1Custo-benefício · Estimated66.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-opus-4-7-100
claude-opus-4-7-100Modelo independenteAnthropic · Estável2026-04-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.1Custo-benefício · Estimated66.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.6-35B-A3B
Verificação pendente (UTC+8)
qwen3.6-35b-a3bModelo independenteQwen · Estável2026-04-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated45.4Custo-benefício · Estimated51.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens493.151 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens2.958.904 pontos
Qwen3.6-Flash
Verificação pendente (UTC+8)
qwen3.6-flashModelo independenteQwen · Estável2026-04-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.2Custo-benefício · Estimated62.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 256.000 TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens65.753 pontosUso de saída · por milhão de Tokens1.972.603 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens1.315.068 pontosUso de acertos de cache · por milhão de Tokens263.014 pontosUso de saída · por milhão de Tokens7.890.411 pontos
qwen-GLM-5.1
Verificação pendente (UTC+8)
qwen-glm-5.1Modelo independenteZhipu · Estável2026-04-14Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.1Custo-benefício · Estimated58.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 32.000 TokenUso de entrada · por milhão de Tokens1.643.836 pontosUso de acertos de cache · por milhão de Tokens328.767 pontosUso de saída · por milhão de Tokens6.575.342 pontos
Input 32.001+ TokenUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens438.356 pontosUso de saída · por milhão de Tokens7.671.233 pontos
qwen-ViduQ3-mix_reference2video
qwen-vidu-viduq3-mix_reference2videoModelo independentevidu · Estável2026-04-13Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3_reference2video
qwen-vidu-viduq3_reference2videoModelo independentevidu · Estável2026-04-13Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Turbo_reference2video
qwen-vidu-viduq3-turbo_reference2videoModelo independentevidu · Estável2026-04-13Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-C1-it2v
qwen-pixverse-pixverse-c1-it2vModelo independentepixverse · Estável2026-04-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-C1-kf2v
qwen-pixverse-pixverse-c1-kf2vModelo independentepixverse · Estável2026-04-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-C1-r2v
qwen-pixverse-pixverse-c1-r2vModelo independentepixverse · Estável2026-04-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-C1-t2v
qwen-pixverse-pixverse-c1-t2vModelo independentepixverse · Estável2026-04-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ZHIPU/GLM-5.1
Verificação pendente (UTC+8)
qwen-zhipu-glm-5.1Modelo independenteZhipu AI · Estável2026-04-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated28.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
Wan2.7-I2V
Verificação pendente (UTC+8)
wan2.7-i2vModelo independenteAlibaba Cloud · Estável2026-04-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho78.7Custo-benefício63.2
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
Wan2.7-R2V
Verificação pendente (UTC+8)
wan2.7-r2vModelo independenteAlibaba Cloud · Estável2026-04-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated69.2Custo-benefício · Estimated56.5
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
Wan2.7-T2V
Verificação pendente (UTC+8)
wan2.7-t2vModelo independenteAlibaba Cloud · Estável2026-04-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho59.6Custo-benefício49.8
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
qwen-Wan2.7-VideoEdit
wan2.7-videoeditModelo independenteWan · Estável2026-04-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated69.2Custo-benefício · Estimated63.4
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Grok 4.20 Non-Reasoning
Verificação pendente (UTC+8)
grok-4-20-non-reasoningModelo independentexAI · Prévia2026-04-06Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens5.000.000 pontos
Grok 4.20 Reasoning
Verificação pendente (UTC+8)
grok-4-20-reasoningModelo independentexAI · Prévia2026-04-06Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens5.000.000 pontos
Gemma 4 26B A4B It-100
Verificação pendente (UTC+8)
gemma-4-26b-a4b-it-maas-001Modelo independenteGoogle · Prévia2026-04-02Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated62.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens300.000 pontosUso de acertos de cache · por milhão de Tokens30.000 pontosUso de saída · por milhão de Tokens1.200.000 pontos
Veo 3.1 Lite Generate 001-100
veo-3.1-lite-generate-001Modelo independenteGoogle · Estável2026-04-02Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-seed3d-2-0-260328
Verificação pendente (UTC+8)
doubao-seed3d-2-0-260328Snapshot / versão fixa · Acesso únicoByteDance · Estável2026-04 (apenas mês oficial)Última verificação do preçoVerificação pendente (UTC+8)
Desempenho82.2Custo-benefício57.5
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%seed3d-public · OfficialUso de saída · 3D · por milhão de Tokens21.917.809 pontos
Qwen3.6-Plus
Verificação pendente (UTC+8)
qwen3.6-plusModelo independenteQwen · Estável2026-04-01Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated54.5Custo-benefício · Estimated57.7
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 256.000 TokenUso de entrada · por milhão de Tokens547.945 pontosUso de acertos de cache · por milhão de Tokens109.589 pontosUso de saída · por milhão de Tokens3.287.671 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens438.356 pontosUso de saída · por milhão de Tokens13.150.685 pontos
Wan2.7-Image
Verificação pendente (UTC+8)
wan2.7-imageModelo independenteAlibaba Cloud · Estável2026-04-01Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho41.7Custo-benefício46.3
Version comparison reviewProvisório
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem54.795 pontos
Wan2.7-Image-Pro
Verificação pendente (UTC+8)
wan2.7-image-proModelo independenteAlibaba Cloud · Estável2026-04-01Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho44.1Custo-benefício30.9
Uso de saída · Imagem · por imagem136.987 pontos
qwen-PixVerse-V6-it2v
qwen-pixverse-pixverse-v6-it2vModelo independentepixverse · Estável2026-03-29Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-V6-kf2v
qwen-pixverse-pixverse-v6-kf2vModelo independentepixverse · Estável2026-03-29Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-V6-t2v
qwen-pixverse-pixverse-v6-t2vModelo independentepixverse · Estável2026-03-29Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GLM-5.1
Verificação pendente (UTC+8)
glm-5.1Modelo independenteZhipu · Estável2026-03-27Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated65.1Custo-benefício · Estimated61.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 31.999 TokenUso de entrada · por milhão de Tokens1.643.836 pontosUso de acertos de cache · por milhão de Tokens356.164 pontosUso de saída · por milhão de Tokens6.575.342 pontos
Input 32.000+ TokenUso de entrada · por milhão de Tokens2.191.781 pontosUso de acertos de cache · por milhão de Tokens547.945 pontosUso de saída · por milhão de Tokens7.671.233 pontos
Lyria 3 Clip Preview-100
lyria-3-clip-previewModelo independenteGoogle · Estável2026-03-25Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Lyria 3 Pro Preview-100
lyria-3-pro-previewModelo independenteGoogle · Estável2026-03-25Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-MiniMax/MiniMax-M2.7
Verificação pendente (UTC+8)
qwen-minimax-minimax-m2.7Modelo independenteMiniMax · Estável2026-03-18Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens575.342 pontosUso de acertos de cache · por milhão de Tokens115.068 pontosUso de saída · por milhão de Tokens2.301.370 pontos
GPT-5.4 Mini
Verificação pendente (UTC+8)
gpt-5.4-miniModelo independenteOpenAI · Estável2026-03-17Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated47.9Custo-benefício · Estimated48.9
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.500.000 pontosUso de acertos de cache · por milhão de Tokens150.000 pontosUso de saída · por milhão de Tokens9.000.000 pontos
GPT-5.4 Nano
Verificação pendente (UTC+8)
gpt-5.4-nanoModelo independenteOpenAI · Estável2026-03-17Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated48.6Custo-benefício · Estimated54.8
11/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens400.000 pontosUso de acertos de cache · por milhão de Tokens40.000 pontosUso de saída · por milhão de Tokens2.500.000 pontos
GLM-5-Turbo
Verificação pendente (UTC+8)
glm-5-turboModelo independenteZhipu · Estável2026-03-14Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated56.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 31.999 TokenUso de entrada · por milhão de Tokens1.369.863 pontosUso de acertos de cache · por milhão de Tokens328.767 pontosUso de saída · por milhão de Tokens6.027.397 pontos
Input 32.000+ TokenUso de entrada · por milhão de Tokens1.917.808 pontosUso de acertos de cache · por milhão de Tokens493.151 pontosUso de saída · por milhão de Tokens7.123.288 pontos
qwen-Tripo-P1.0
qwen-tripo-tripo-p1.0Modelo independentetripo · Estável2026-03-11Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated43.2Custo-benefício · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Tripo-H3.1
qwen-tripo-tripo-h3.1Modelo independentetripo · Estável2026-03-06Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.9Custo-benefício · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5.4
Verificação pendente (UTC+8)
gpt-5.4Modelo independenteOpenAI · Estável2026-03-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated73.0Custo-benefício · Estimated61.5
13/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens5.000.000 pontosUso de acertos de cache · por milhão de Tokens500.000 pontosUso de saída · por milhão de Tokens30.000.000 pontos
GPT-5.4 Pro
Verificação pendente (UTC+8)
gpt-5.4-proModelo independenteOpenAI · Estável2026-03-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.8Custo-benefício · Estimated41.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens60.000.000 pontosUso de saída · por milhão de Tokens360.000.000 pontos
Qwen3.5-Omni-Flash
qwen3.5-omni-flashModelo independenteQwen · Estável2026-03 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated58.2Custo-benefício · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.5-Omni-Flash-Realtime
qwen3.5-omni-flash-realtimeModelo independenteQwen · Estável2026-03 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.5-Omni-Plus
qwen3.5-omni-plusModelo independenteQwen · Estável2026-03 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated54.5Custo-benefício · Estimated53.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.5-Omni-Plus-Realtime
qwen3.5-omni-plus-realtimeModelo independenteQwen · Estável2026-03 (apenas mês oficial)Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-pixverse/pixverse-motioncontrol
qwen-pixverse-pixverse-motioncontrolModelo independentepixverse · Estável2026-02-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5.3 Codex
Verificação pendente (UTC+8)
gpt-5.3-codexModelo independenteOpenAI · Estável2026-02-24Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.5Custo-benefício · Estimated52.1
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.500.000 pontosUso de acertos de cache · por milhão de Tokens350.000 pontosUso de saída · por milhão de Tokens28.000.000 pontos
qwen-MiniMax-M2.5
Verificação pendente (UTC+8)
qwen-minimax-m2.5Modelo independenteMiniMax · Estável2026-02-24Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated34.9Custo-benefício · Estimated44.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens575.342 pontosUso de acertos de cache · por milhão de Tokens115.068 pontosUso de saída · por milhão de Tokens2.301.370 pontos
GPT Audio 1.5
Verificação pendente (UTC+8)
gpt-audio-1.5Modelo independenteOpenAI · Estável2026-02-23Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated52.6Custo-benefício · Estimated41.6
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontosUso de entrada · Áudio · por milhão de Tokens64.000.000 pontosUso de saída · Áudio · por milhão de Tokens128.000.000 pontos
GPT Realtime 1.5
Verificação pendente (UTC+8)
gpt-realtime-1.5Modelo independenteOpenAI · Estável2026-02-23Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated45.3Custo-benefício · Estimated31.7
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens800.000 pontosUso de saída · por milhão de Tokens32.000.000 pontosUso de entrada · Imagem · por milhão de Tokens10.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens1.000.000 pontosUso de entrada · Áudio · por milhão de Tokens64.000.000 pontosUso de acertos de cache · Áudio · por milhão de Tokens800.000 pontosUso de saída · Áudio · por milhão de Tokens128.000.000 pontos
Qwen3.5-122B-A10B
Verificação pendente (UTC+8)
qwen3.5-122b-a10bModelo independenteQwen · Estável2026-02-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated46.4Custo-benefício · Estimated55.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens1.753.425 pontos
Input 128.001+ TokenUso de entrada · por milhão de Tokens547.945 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens4.383.562 pontos
Qwen3.5-27B
Verificação pendente (UTC+8)
qwen3.5-27bModelo independenteQwen · Estável2026-02-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated45.7Custo-benefício · Estimated55.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens164.384 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens1.315.068 pontos
Input 128.001+ TokenUso de entrada · por milhão de Tokens493.151 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens3.945.205 pontos
Qwen3.5-35B-A3B
Verificação pendente (UTC+8)
qwen3.5-35b-a3bModelo independenteQwen · Estável2026-02-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated42.9Custo-benefício · Estimated55.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens109.589 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens876.712 pontos
Input 128.001+ TokenUso de entrada · por milhão de Tokens438.356 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens3.506.849 pontos
Qwen3.5-Flash
Verificação pendente (UTC+8)
qwen3.5-flashModelo independenteQwen · Estável2026-02-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.2Custo-benefício · Estimated68.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens54.795 pontosUso de acertos de cache · por milhão de Tokens10.959 pontosUso de saída · por milhão de Tokens547.945 pontos
Input 128.001 – 256.000 TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens2.191.781 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens65.753 pontosUso de saída · por milhão de Tokens3.287.671 pontos
qwen-GLM-5
Verificação pendente (UTC+8)
qwen-glm-5Modelo independenteZhipu · Estável2026-02-18Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.1Custo-benefício · Estimated60.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 32.000 TokenUso de entrada · por milhão de Tokens1.095.890 pontosUso de acertos de cache · por milhão de Tokens219.178 pontosUso de saída · por milhão de Tokens4.931.507 pontos
Input 32.001+ TokenUso de entrada · por milhão de Tokens1.643.836 pontosUso de acertos de cache · por milhão de Tokens328.767 pontosUso de saída · por milhão de Tokens6.027.397 pontos
claude-sonnet-4-6
claude-sonnet-4-6Modelo independenteAnthropic · Estável2026-02-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated65.2Custo-benefício · Estimated60.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-sonnet-4-6-100
claude-sonnet-4-6-100Modelo independenteAnthropic · Estável2026-02-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated65.2Custo-benefício · Estimated60.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3.5-397B-A17B
Verificação pendente (UTC+8)
qwen3.5-397b-a17bModelo independenteQwen · Estável2026-02-15Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated49.6Custo-benefício · Estimated56.4
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens1.972.603 pontos
Input 128.001+ TokenUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens4.931.507 pontos
Qwen3.5-Plus
Verificação pendente (UTC+8)
qwen3.5-plusModelo independenteQwen · Estável2026-02-15Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated54.5Custo-benefício · Estimated61.5
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens1.315.068 pontos
Input 128.001 – 256.000 TokenUso de entrada · por milhão de Tokens547.945 pontosUso de acertos de cache · por milhão de Tokens109.589 pontosUso de saída · por milhão de Tokens3.287.671 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens1.095.890 pontosUso de acertos de cache · por milhão de Tokens219.178 pontosUso de saída · por milhão de Tokens6.575.342 pontos
qwen-MiniMax/MiniMax-M2.5
Verificação pendente (UTC+8)
qwen-minimax-minimax-m2.5Modelo independenteMiniMax · Estável2026-02-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens575.342 pontosUso de acertos de cache · por milhão de Tokens57.534 pontosUso de saída · por milhão de Tokens2.301.370 pontos
qwen-PixVerse-V5.6-r2v
qwen-pixverse-pixverse-v5.6-r2vModelo independentepixverse · Estável2026-02-12Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ZHIPU/GLM-5
Verificação pendente (UTC+8)
qwen-zhipu-glm-5Modelo independenteZhipu AI · Estável2026-02-12Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated31.2
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.643.836 pontosUso de acertos de cache · por milhão de Tokens410.959 pontosUso de saída · por milhão de Tokens6.027.397 pontos
qwen-ViduQ3-Pro_start-end2video
qwen-vidu-viduq3-pro_start-end2videoModelo independentevidu · Estável2026-02-11Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Turbo_img2video
qwen-vidu-viduq3-turbo_img2videoModelo independentevidu · Estável2026-02-11Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Turbo_start-end2video
qwen-vidu-viduq3-turbo_start-end2videoModelo independentevidu · Estável2026-02-11Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Turbo_text2video
qwen-vidu-viduq3-turbo_text2videoModelo independentevidu · Estável2026-02-11Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GLM-5
Verificação pendente (UTC+8)
glm-5Modelo independenteZhipu · Estável2026-02-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated60.9
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 31.999 TokenUso de entrada · por milhão de Tokens1.095.890 pontosUso de acertos de cache · por milhão de Tokens273.973 pontosUso de saída · por milhão de Tokens4.931.507 pontos
Input 32.000+ TokenUso de entrada · por milhão de Tokens1.643.836 pontosUso de acertos de cache · por milhão de Tokens410.959 pontosUso de saída · por milhão de Tokens6.027.397 pontos
Qwen-Image-2.0
Verificação pendente (UTC+8)
qwen-image-2.0Modelo independenteAlibaba Cloud · Estável2026-02-10Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated73.8Custo-benefício · Estimated68.7
Estimate basis
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem54.795 pontos
claude-opus-4-6
claude-opus-4-6Modelo independenteAnthropic · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated70.8Custo-benefício · Estimated64.6
12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-opus-4-6-100
claude-opus-4-6-100Modelo independenteAnthropic · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated70.8Custo-benefício · Estimated64.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Kling Image 3.0
qwen-kling-kling-v3-image-generationModelo independentekling · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated73.8Custo-benefício · Estimated66.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Kling Image 3.0 Omni
qwen-kling-kling-v3-omni-image-generationModelo independentekling · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Kling Video 3.0 Omni
qwen-kling-kling-v3-omni-video-generationModelo independentekling · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated41.7Custo-benefício · Estimated44.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Kling Video 3.0
qwen-kling-kling-v3-video-generationModelo independentekling · Estável2026-02-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Kimi-K2.5
Verificação pendente (UTC+8)
qwen-kimi-k2.5Modelo independenteMoonshot · Estável2026-01-30Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated34.9Custo-benefício · Estimated41.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.095.890 pontosUso de acertos de cache · por milhão de Tokens219.178 pontosUso de saída · por milhão de Tokens5.753.425 pontos
Fun-ASR-Flash-8k实时语音识别
fun-asr-flash-8k-realtimeModelo independenteQwen · Estável2026-01-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Pro_reference2video
qwen-vidu-viduq2-pro_reference2videoModelo independentevidu · Estável2026-01-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Pro_img2video
qwen-vidu-viduq3-pro_img2videoModelo independentevidu · Estável2026-01-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Pro_text2video
qwen-vidu-viduq3-pro_text2videoModelo independentevidu · Estável2026-01-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-VL-Plus
Verificação pendente (UTC+8)
qwen3-vl-plusModelo independenteQwen · Estável2026-01-26Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated42.7Custo-benefício · Estimated51.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 32.000 TokenUso de entrada · por milhão de Tokens273.973 pontosUso de acertos de cache · por milhão de Tokens54.795 pontosUso de saída · por milhão de Tokens2.739.726 pontos
Input 32.001 – 128.000 TokenUso de entrada · por milhão de Tokens410.959 pontosUso de acertos de cache · por milhão de Tokens82.192 pontosUso de saída · por milhão de Tokens4.109.589 pontos
Input 128.001+ TokenUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens164.384 pontosUso de saída · por milhão de Tokens8.219.178 pontos
qwen-PixVerse-V5.6-it2v
qwen-pixverse-pixverse-v5.6-it2vModelo independentepixverse · Estável2026-01-26Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-V5.6-kf2v
qwen-pixverse-pixverse-v5.6-kf2vModelo independentepixverse · Estável2026-01-26Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-V5.6-t2v
qwen-pixverse-pixverse-v5.6-t2vModelo independentepixverse · Estável2026-01-26Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Virtual Try On 001-100
virtual-try-on-001Modelo independenteGoogle · Estável2026-01-23Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5.2 Codex
Verificação pendente (UTC+8)
gpt-5.2-codexModelo independenteOpenAI · Estável2026-01-14Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.0Custo-benefício · Estimated54.5
Version comparison review8/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.500.000 pontosUso de acertos de cache · por milhão de Tokens350.000 pontosUso de saída · por milhão de Tokens28.000.000 pontos
qwen-MiniMax/MiniMax-M2.1
Verificação pendente (UTC+8)
qwen-minimax-minimax-m2.1Modelo independenteMiniMax · Estável2025-12-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated36.6
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens575.342 pontosUso de acertos de cache · por milhão de Tokens57.534 pontosUso de saída · por milhão de Tokens2.301.370 pontos
GLM-4.7
Verificação pendente (UTC+8)
glm-4.7Modelo independenteZhipu · Estável2025-12-22Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated60.2Custo-benefício · Estimated60.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 31.999 Token · Output 0 – 199 TokenUso de entrada · por milhão de Tokens547.945 pontosUso de acertos de cache · por milhão de Tokens109.589 pontosUso de saída · por milhão de Tokens2.191.781 pontos
Input 0 – 31.999 Token · Output 200+ TokenUso de entrada · por milhão de Tokens821.918 pontosUso de acertos de cache · por milhão de Tokens164.384 pontosUso de saída · por milhão de Tokens3.835.616 pontos
Input 32.000+ TokenUso de entrada · por milhão de Tokens1.095.890 pontosUso de acertos de cache · por milhão de Tokens219.178 pontosUso de saída · por milhão de Tokens4.383.562 pontos
GPT Image 1.5
Verificação pendente (UTC+8)
gpt-image-1.5Modelo independenteOpenAI · Estável2025-12-16Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho76.0Custo-benefício53.2
Uso de entrada · por milhão de Tokens10.000.000 pontosUso de acertos de cache · por milhão de Tokens2.500.000 pontosUso de entrada · Imagem · por milhão de Tokens16.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens4.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontosUso de saída · Imagem · por milhão de Tokens64.000.000 pontos
Wan2.6-I2V
Verificação pendente (UTC+8)
wan2.6-i2vModelo independenteAlibaba Cloud · Estável2025-12-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho53.2Custo-benefício45.3
Version comparison reviewProvisório
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
Wan2.6-Image
Verificação pendente (UTC+8)
wan2.6-imageModelo independenteAlibaba Cloud · Estável2025-12-16Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho31.6Custo-benefício39.2
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUso de saída · Imagem · por imagem54.795 pontos
qwen-Wan2.6-R2V
wan2.6-r2vModelo independenteWan · Estável2025-12-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated55.3Custo-benefício · Estimated53.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Wan2.6-T2I
Verificação pendente (UTC+8)
wan2.6-t2iModelo independenteAlibaba Cloud · Estável2025-12-16Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho50.0Custo-benefício52.1
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUso de saída · Imagem · por imagem54.795 pontos
Wan2.6-T2V
Verificação pendente (UTC+8)
wan2.6-t2vModelo independenteAlibaba Cloud · Estável2025-12-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho57.4Custo-benefício48.3
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
Cohere Rerank v4.0 Pro
Verificação pendente (UTC+8)
cohere-rerank-v4.0-proModelo independenteCohere · Estável2025-12-11Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated65.8Custo-benefício · Estimated61.1
Estimate basis
2026-10-08 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 · OfficialReordenação · por 1.000 unidades de pesquisa5.000.000 pontos
GPT-5.2
Verificação pendente (UTC+8)
gpt-5.2Modelo independenteOpenAI · Estável2025-12-11Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated61.7Custo-benefício · Estimated54.3
Version comparison review12/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens3.500.000 pontosUso de acertos de cache · por milhão de Tokens350.000 pontosUso de saída · por milhão de Tokens28.000.000 pontos
GPT-5.1 Codex Max
Verificação pendente (UTC+8)
gpt-5.1-codex-maxModelo independenteOpenAI · Estável2025-12-04Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated72.5Custo-benefício · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
Mistral Large 3
Verificação pendente (UTC+8)
mistral-large-3Modelo independenteMistral AI · Estável2025-12-02Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated60.6Custo-benefício · Estimated60.8
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.000.000 pontosUso de saída · por milhão de Tokens3.000.000 pontos
qwen-ViduQ2-Pro-fast_img2video
qwen-vidu-viduq2-pro-fast_img2videoModelo independentevidu · Estável2025-12-02Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-LiveTranslate-Flash
qwen3-livetranslate-flashModelo independenteQwen · Estável2025-12-01Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated58.2Custo-benefício · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-Omni-Flash
qwen3-omni-flashModelo independenteQwen · Estável2025-12-01Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated58.2Custo-benefício · Estimated55.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-SiliconFlow DeepSeek-V3.2
qwen-siliconflow-deepseek-v3.2Modelo independenteDeepSeek · Estável2025-12-01Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated45.8Custo-benefício · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vanchin/DeepSeek-V3.2-think
qwen-vanchin-deepseek-v3.2-thinkModelo independenteDeepSeek · Estável2025-12-01Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated45.8Custo-benefício · Estimated47.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-TTS-Flash-Realtime
qwen3-tts-flash-realtimeModelo independenteQwen · Estável2025-11-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Z-Image-Turbo
Verificação pendente (UTC+8)
z-image-turboModelo independenteAlibaba Cloud · Estável2025-11-26Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho28.8Custo-benefício50.2
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentUso de saída · Imagem · por imagem27.398 pontos
FLUX.2 [flex]
Verificação pendente (UTC+8)
flux.2-flexModelo independenteBlack Forest Labs · Estável2025-11-25Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho46.8Custo-benefício32.8
Uso de entrada · Imagem · por megapixel100.000 pontosUso de saída · Imagem · por megapixel100.000 pontos
FLUX.2 Pro
Verificação pendente (UTC+8)
flux.2-proModelo independenteBlack Forest Labs · Estável2025-11-25Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho49.9Custo-benefício64.9
Megapixel inicial · por megapixel60.000 pontosMegapixel adicional · por megapixel30.000 pontos
claude-opus-4-5
claude-opus-4-5Modelo independenteAnthropic · Estável2025-11-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated67.9Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-opus-4-5-100
claude-opus-4-5-100Modelo independenteAnthropic · Estável2025-11-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated67.9Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Grok 4.1 Fast Non-Reasoning
Verificação pendente (UTC+8)
grok-4-1-fast-non-reasoningModelo independentexAI · Estável2025-11-19Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens400.000 pontosUso de acertos de cache · por milhão de Tokens100.000 pontosUso de saída · por milhão de Tokens1.000.000 pontos
Grok 4.1 Fast Reasoning
Verificação pendente (UTC+8)
grok-4-1-fast-reasoningModelo independentexAI · Estável2025-11-19Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.5Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens400.000 pontosUso de acertos de cache · por milhão de Tokens100.000 pontosUso de saída · por milhão de Tokens1.000.000 pontos
Gemini 3 Pro Preview-100
gemini-3-pro-previewModelo independenteGoogle · Estável2025-11-18Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated69.4Custo-benefício · Estimated63.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Veo 3.1 Fast Generate 001-100
veo-3.1-fast-generate-001Modelo independenteGoogle · Estável2025-11-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Veo 3.1 Generate 001-100
veo-3.1-generate-001Modelo independenteGoogle · Estável2025-11-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5.1
Verificação pendente (UTC+8)
gpt-5.1Modelo independenteOpenAI · Estável2025-11-13Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated63.8Custo-benefício · Estimated57.2
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
GPT-5.1 Codex
Verificação pendente (UTC+8)
gpt-5.1-codexModelo independenteOpenAI · Estável2025-11-13Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated63.6Custo-benefício · Estimated57.1
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
GPT-5.1 Codex Mini
Verificação pendente (UTC+8)
gpt-5.1-codex-miniModelo independenteOpenAI · Estável2025-11-13Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated43.1Custo-benefício · Estimated49.4
1/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens500.000 pontosUso de acertos de cache · por milhão de Tokens50.000 pontosUso de saída · por milhão de Tokens4.000.000 pontos
Lyria 002-100
lyria-002Modelo independenteGoogle · Estável2025-10-27Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2_reference2video
qwen-vidu-viduq2_reference2videoModelo independentevidu · Estável2025-10-21Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2_text2video
qwen-vidu-viduq2_text2videoModelo independentevidu · Estável2025-10-21Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vanchin/DeepSeek-OCR
qwen-vanchin-deepseek-ocrModelo independenteDeepSeek · Estável2025-10-20Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated81.8Custo-benefício · Estimated72.3
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-haiku-4-5
claude-haiku-4-5Modelo independenteAnthropic · Estável2025-10-15Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated60.4Custo-benefício · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
claude-haiku-4-5-100
claude-haiku-4-5-100Modelo independenteAnthropic · Estável2025-10-15Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated60.4Custo-benefício · Estimated57.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5 Pro
Verificação pendente (UTC+8)
gpt-5-proModelo independenteOpenAI · Estável2025-10-06Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.5Custo-benefício · Estimated41.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens20.000.000 pontosUso de saída · por milhão de Tokens240.000.000 pontos
GPT Audio Mini
Verificação pendente (UTC+8)
gpt-audio-miniModelo independenteOpenAI · Estável2025-10-06Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated52.6Custo-benefício · Estimated66.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens1.200.000 pontosUso de saída · por milhão de Tokens4.800.000 pontosUso de entrada · Áudio · por milhão de Tokens20.000.000 pontosUso de saída · Áudio · por milhão de Tokens40.000.000 pontos
GPT Image 1 Mini
Verificação pendente (UTC+8)
gpt-image-1-miniModelo independenteOpenAI · Estável2025-10-06Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho20.1Custo-benefício44.1
Uso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de entrada · Imagem · por milhão de Tokens5.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens500.000 pontosUso de saída · Imagem · por milhão de Tokens16.000.000 pontos
GPT Realtime Mini
Verificação pendente (UTC+8)
gpt-realtime-miniModelo independenteOpenAI · Estável2025-10-06Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated54.0Custo-benefício · Estimated67.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens1.200.000 pontosUso de acertos de cache · por milhão de Tokens120.000 pontosUso de saída · por milhão de Tokens4.800.000 pontosUso de entrada · Imagem · por milhão de Tokens1.600.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens160.000 pontosUso de entrada · Áudio · por milhão de Tokens20.000.000 pontosUso de acertos de cache · Áudio · por milhão de Tokens600.000 pontosUso de saída · Áudio · por milhão de Tokens40.000.000 pontos
Gemini 2.5 Flash TTS-100
gemini-2.5-flash-ttsModelo independenteGoogle · Estável2025-09-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated87.1Custo-benefício · Estimated76.0
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Gemini 2.5 Pro TTS-100
gemini-2.5-pro-ttsModelo independenteGoogle · Estável2025-09-30Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated82.6Custo-benefício · Estimated72.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sora 2
Verificação pendente (UTC+8)
sora-2Modelo independenteOpenAI · Prévia2025-09-30Última verificação do preçoVerificação pendente (UTC+8)
Desempenho66.0Custo-benefício50.4
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo · por segundo200.000 pontos
claude-sonnet-4-5
claude-sonnet-4-5Modelo independenteAnthropic · Estável2025-09-29Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated61.6Custo-benefício · Estimated58.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Pro_img2video
qwen-vidu-viduq2-pro_img2videoModelo independentevidu · Estável2025-09-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Pro_start-end2video
qwen-vidu-viduq2-pro_start-end2videoModelo independentevidu · Estável2025-09-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Turbo_img2video
qwen-vidu-viduq2-turbo_img2videoModelo independentevidu · Estável2025-09-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Turbo_start-end2video
qwen-vidu-viduq2-turbo_start-end2videoModelo independentevidu · Estável2025-09-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-5 Codex
Verificação pendente (UTC+8)
gpt-5-codexModelo independenteOpenAI · Estável2025-09-23Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.1Custo-benefício · Estimated53.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
qwen-SiliconFlow DeepSeek-V3.1-Terminus
qwen-siliconflow-deepseek-v3.1-terminusModelo independenteDeepSeek · Estável2025-09-22Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.9Custo-benefício · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vanchin/DeepSeek-V3.1-Terminus
qwen-vanchin-deepseek-v3.1-terminusModelo independenteDeepSeek · Estável2025-09-22Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.9Custo-benefício · Estimated46.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-TTS-Flash
Verificação pendente (UTC+8)
qwen3-tts-flashModelo independenteAlibaba Cloud · Estável2025-09 (apenas mês oficial)Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated74.4Custo-benefício · Estimated82.1
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres219.179 pontos
Chirp 3-100
chirp-3Modelo independenteGoogle · Estável2025-08-29Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT Realtime
Verificação pendente (UTC+8)
gpt-realtimeModelo independenteOpenAI · Estável2025-08-28Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.9Custo-benefício · Estimated41.9
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens8.000.000 pontosUso de acertos de cache · por milhão de Tokens800.000 pontosUso de saída · por milhão de Tokens32.000.000 pontosUso de entrada · Imagem · por milhão de Tokens10.000.000 pontosUso de acertos de cache · Imagem · por milhão de Tokens1.000.000 pontosUso de entrada · Áudio · por milhão de Tokens64.000.000 pontosUso de acertos de cache · Áudio · por milhão de Tokens800.000 pontosUso de saída · Áudio · por milhão de Tokens128.000.000 pontos
GPT-5
Verificação pendente (UTC+8)
gpt-5Modelo independenteOpenAI · Estável2025-08-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.7Custo-benefício · Estimated53.6
5/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
GPT-5 Mini
Verificação pendente (UTC+8)
gpt-5-miniModelo independenteOpenAI · Estável2025-08-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated43.1Custo-benefício · Estimated49.4
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens500.000 pontosUso de acertos de cache · por milhão de Tokens50.000 pontosUso de saída · por milhão de Tokens4.000.000 pontos
GPT-5 Nano
Verificação pendente (UTC+8)
gpt-5-nanoModelo independenteOpenAI · Estável2025-08-07Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated44.4Custo-benefício · Estimated57.0
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens100.000 pontosUso de acertos de cache · por milhão de Tokens10.000 pontosUso de saída · por milhão de Tokens800.000 pontos
GPT-OSS 120B-100
openai-gpt-oss-120b-maas-001Modelo independenteOpenAI · Estável2025-08-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated57.3Custo-benefício · Estimated55.1
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-Coder-Flash
Verificação pendente (UTC+8)
qwen3-coder-flashModelo independenteQwen · Estável2025-08-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated58.2Custo-benefício · Estimated64.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 32.000 TokenUso de entrada · por milhão de Tokens273.973 pontosUso de acertos de cache · por milhão de Tokens54.795 pontosUso de saída · por milhão de Tokens1.095.890 pontos
Input 32.001 – 128.000 TokenUso de entrada · por milhão de Tokens410.959 pontosUso de acertos de cache · por milhão de Tokens82.192 pontosUso de saída · por milhão de Tokens1.643.836 pontos
Input 128.001 – 256.000 TokenUso de entrada · por milhão de Tokens684.932 pontosUso de acertos de cache · por milhão de Tokens136.986 pontosUso de saída · por milhão de Tokens2.739.726 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens1.369.863 pontosUso de acertos de cache · por milhão de Tokens273.973 pontosUso de saída · por milhão de Tokens6.849.315 pontos
Qwen-Flash
Verificação pendente (UTC+8)
qwen-flashModelo independenteQwen · Estável2025-08-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.4Custo-benefício · Estimated70.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens41.096 pontosUso de acertos de cache · por milhão de Tokens8.219 pontosUso de saída · por milhão de Tokens410.959 pontos
Input 128.001 – 256.000 TokenUso de entrada · por milhão de Tokens164.384 pontosUso de acertos de cache · por milhão de Tokens32.877 pontosUso de saída · por milhão de Tokens1.643.836 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens65.753 pontosUso de saída · por milhão de Tokens3.287.671 pontos
doubao-glm-4-5-air
doubao-glm-4-5-air-20250728Snapshot / versão fixa · Acesso únicoZhipu AI · Estável2025-07-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GLM-4.5-Air
Verificação pendente (UTC+8)
glm-4.5-airModelo independenteZhipu · Estável2025-07-27Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.3Custo-benefício · Estimated64.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 31.999 Token · Output 0 – 199 TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens547.945 pontos
Input 0 – 31.999 Token · Output 200+ TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens1.643.836 pontos
Input 32.000+ TokenUso de entrada · por milhão de Tokens328.767 pontosUso de acertos de cache · por milhão de Tokens65.753 pontosUso de saída · por milhão de Tokens2.191.781 pontos
qwen-pixverse/pixverse-lipsync
qwen-pixverse-pixverse-lipsyncModelo independentepixverse · Estável2025-07-14Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Plus
Verificação pendente (UTC+8)
qwen-plusModelo independenteQwen · Estável2025-06-24Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated44.2Custo-benefício · Estimated55.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentInput 0 – 128.000 TokenUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens547.945 pontos
Input 128.001 – 256.000 TokenUso de entrada · por milhão de Tokens657.534 pontosUso de acertos de cache · por milhão de Tokens131.507 pontosUso de saída · por milhão de Tokens5.479.452 pontos
Input 256.001+ TokenUso de entrada · por milhão de Tokens1.315.068 pontosUso de acertos de cache · por milhão de Tokens263.014 pontosUso de saída · por milhão de Tokens13.150.685 pontos
qwen-SiliconFlow DeepSeek-R1-0528
qwen-siliconflow-deepseek-r1-0528Modelo independenteDeepSeek · Estável2025-05-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated43.2Custo-benefício · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Mistral OCR 2505-100
mistralai-mistral-ocr-2505-001Modelo independenteMistral AI · Estável2025-05-22Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated81.8Custo-benefício · Estimated72.3
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
mistral-medium-2505
mistral-medium-2505Modelo independenteMistral AI · Estável2025-05-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated54.1Custo-benefício · Estimated52.9
Version comparison review4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Phi-4 Reasoning
Verificação pendente (UTC+8)
phi-4-reasoningModelo independenteMicrosoft · Estável2025-04-30Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens250.000 pontosUso de saída · por milhão de Tokens1.000.000 pontos
o3
Verificação pendente (UTC+8)
o3Modelo independenteOpenAI · Estável2025-04-16Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.8Custo-benefício · Estimated56.1
7/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens4.000.000 pontosUso de acertos de cache · por milhão de Tokens1.000.000 pontosUso de saída · por milhão de Tokens16.000.000 pontos
Veo 2.0 Generate 001-100
veo-2.0-generate-001Modelo independenteGoogle · Estável2025-04-09Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Llama 4 Maverick 17B 128E
Verificação pendente (UTC+8)
llama-4-maverick-17b-128e-instruct-fp8Modelo independenteMeta · Estável2025-04-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated60.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens500.000 pontosUso de saída · por milhão de Tokens2.000.000 pontos
Llama 4 Maverick 17B 128E-100
llama-4-maverick-17b-128e-instruct-maas-100Modelo independenteMeta · Estável2025-04-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Llama 4 Scout 17B 16E Instruct-100
meta-llama-4-scout-17b-16e-instruct-maas-001Modelo independenteMeta · Estável2025-04-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated53.1Custo-benefício · Estimated52.2
4/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-SiliconFlow DeepSeek-V3-0324
qwen-siliconflow-deepseek-v3-0324Modelo independenteDeepSeek · Estável2025-03-24Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated39.9Custo-benefício · Estimated42.9
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
GPT-4o Mini Transcribe
Verificação pendente (UTC+8)
gpt-4o-mini-transcribeModelo independenteOpenAI · Estável2025-03-20Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated94.0
Estimate basis
2026-10-08 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 · IndependentUso de entrada · Áudio · por milhão de Tokens6.000.000 pontosUso de entrada · por milhão de Tokens2.500.000 pontosUso de saída · por milhão de Tokens10.000.000 pontos
GPT-4o Mini TTS
Verificação pendente (UTC+8)
gpt-4o-mini-ttsModelo independenteOpenAI · Estável2025-03-20Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.8Custo-benefício · Estimated56.9
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens1.200.000 pontosUso de saída · Áudio · por milhão de Tokens24.000.000 pontos
GPT-4o Transcribe
Verificação pendente (UTC+8)
gpt-4o-transcribeModelo independenteOpenAI · Estável2025-03-20Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho91.4Custo-benefício64.0
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%qwen-asr-report · IndependentUso de entrada · Áudio · por milhão de Tokens12.000.000 pontosUso de entrada · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
mistral-small-2503
mistral-small-2503Modelo independenteMistral AI · Estável2025-03-17Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.0Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Mistral Small 3.1-100
Verificação pendente (UTC+8)
mistral-small-2503-100Modelo independenteGoogle · Prévia2025-03-17Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.0Custo-benefício · 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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens200.000 pontosUso de saída · por milhão de Tokens600.000 pontos
Text Embedding Large Exp 03 07-100
text-embedding-large-exp-03-07Modelo independenteGoogle · Estável2025-03-07Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-DeepSeek-R1-Distill-Qwen-1.5B
qwen-deepseek-r1-distill-qwen-1.5bModelo independenteDeepSeek · Estável2025-01-20Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated43.2Custo-benefício · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Codestral 2501
Verificação pendente (UTC+8)
codestral-2501Modelo independenteMistral AI · Estável2025-01-13Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated60.1
9/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens600.000 pontosUso de saída · por milhão de Tokens1.800.000 pontos
Ministral-3B
ministral-3bModelo independenteMistral AI · Estável2024-10-16Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated49.2Custo-benefício · Estimated49.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Long
Verificação pendente (UTC+8)
qwen-longModelo independenteQwen · Estável2024-05-20Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated52.5Custo-benefício · Estimated62.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens136.986 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens547.945 pontos
Text Embedding 3 Large
Verificação pendente (UTC+8)
text-embedding-3-largeModelo independenteOpenAI · Estável2024-01-25Última verificação do preçoVerificação pendente (UTC+8)
Desempenho64.6Custo-benefício45.2
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrada vetorial · por milhão de Tokens260.000 pontos
Text Embedding 3 Small
Verificação pendente (UTC+8)
text-embedding-3-smallModelo independenteOpenAI · Estável2024-01-25Última verificação do preçoVerificação pendente (UTC+8)
Desempenho62.3Custo-benefício71.3
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrada vetorial · por milhão de Tokens40.000 pontos
Cohere-embed-v3-english
cohere-embed-v3-englishModelo independenteCohere · Estável2023-11-02Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Cohere-embed-v3-multilingual
cohere-embed-v3-multilingualModelo independenteCohere · Estável2023-11-02Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Text Embedding Ada 002
Verificação pendente (UTC+8)
text-embedding-ada-002Modelo independenteOpenAI · Estável2022-12-15Última verificação do preçoVerificação pendente (UTC+8)
Desempenho61.0Custo-benefício46.6
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 15%openai-embedding · OfficialEntrada vetorial · por milhão de Tokens200.000 pontos
Qwen-Image-2.1-Turbo
qwen-image-2.1-turboModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-14Sem preço fixo; cobrança conforme o serviçoDesempenho—Custo-benefício—
Sem avaliaçãoPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Chirp 2-100
chirp-2-001Modelo independenteGoogle · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
语音生成CosyVoice-v3.5-flash大模型
cosyvoice-v3.5-flashModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated75.4Custo-benefício · Estimated67.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
语音生成CosyVoice-v3.5-plus大模型
cosyvoice-v3.5-plusModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated75.4Custo-benefício · Estimated67.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-GLM-5.3-Flash
Verificação pendente (UTC+8)
doubao-glm-5-3-flash-260828Snapshot / versão fixa · Acesso únicoZhipu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated63.3
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens63.014 pontosUso de saída · por milhão de Tokens767.123 pontos
qwen2-5-72b
doubao-qwen2-5-72b-20240919Snapshot / versão fixa · Acesso únicoQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen3-0-6b
doubao-qwen3-0-6b-20250429Snapshot / versão fixa · Acesso únicoQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen3-14b
doubao-qwen3-14b-20250429Snapshot / versão fixa · Acesso únicoQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen3-32b
doubao-qwen3-32b-20250429Snapshot / versão fixa · Acesso únicoQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen3-8b
doubao-qwen3-8b-20250429Snapshot / versão fixa · Acesso únicoQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-seed-translation
doubao-seed-translation-250915Snapshot / versão fixa · Acesso únicoDoubao · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
doubao-smart-router
doubao-smart-router-250928Snapshot / versão fixa · Acesso únicoDoubao · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated50.0Custo-benefício · Estimated50.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
FaceChain人物图像检测
facechain-facedetectModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Fun-ASR语音识别
fun-asrModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Fun-ASR实时语音识别
fun-asr-realtimeModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
音乐生成 Preview
fun-music-previewModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
音乐生成
fun-music-v1Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Grok 4.20 Non-Reasoning-100
Verificação pendente (UTC+8)
grok-4-20-non-reasoning-100Modelo independentexAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens2.500.000 pontosUso de acertos de cache · por milhão de Tokens400.000 pontosUso de saída · por milhão de Tokens5.000.000 pontos
Grok 4.20 Reasoning-100
grok-4-20-reasoning-100Modelo independentexAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Grok 4.3-100
grok-4.3-100Modelo independentexAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.8Custo-benefício—
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 estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-HappyHorse-1.0-Video-Edit
happyhorse-1.0-video-editModelo independenteHappyHorse · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated80.9Custo-benefício · Estimated71.6
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
图像擦除补全
image-erase-completionModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
人物实例分割
image-instance-segmentationModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Codestral 2-100
mistralai-codestral-2-001Modelo independenteMistral AI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Mistral Medium 3-100
mistralai-mistral-medium-3-001Modelo independenteMistral AI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Paraformer语音识别-8k-v2
paraformer-8k-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Paraformer实时语音识别-8k-v2
paraformer-realtime-8k-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Paraformer实时语音识别-v2
paraformer-realtime-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Paraformer语音识别-v2
paraformer-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-ASR-Flash-Filetrans
qwen3-asr-flash-filetransModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen3-ASR-Flash-Realtime
qwen3-asr-flash-realtimeModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.6Custo-benefício · Estimated51.8
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-ASR-Flash
qwen-audio-3.1-asr-flashModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-ASR-Flash-Filetrans
qwen-audio-3.1-asr-flash-filetransModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-ASR-Flash-Message
qwen-audio-3.1-asr-flash-messageModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-ASR-Flash-Streaming
qwen-audio-3.1-asr-flash-streamingModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated91.4Custo-benefício · Estimated79.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-TTS-Flash
qwen-audio-3.1-tts-flashModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.4Custo-benefício · Estimated67.1
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Audio-3.1-TTS-Next
qwen-audio-3.1-tts-nextModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated74.4Custo-benefício · Estimated67.1
Estimate basis
2026-10-08 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 · OfficialPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Doc-Turbo
Verificação pendente (UTC+8)
qwen-doc-turboModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated48.7Custo-benefício · Estimated49.1
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens164.384 pontosUso de acertos de cache · por milhão de Tokens32.877 pontosUso de saída · por milhão de Tokens273.973 pontos
Qwen-Flash-Character
Verificação pendente (UTC+8)
qwen-flash-characterModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated59.9Custo-benefício · Estimated70.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens68.493 pontosUso de acertos de cache · por milhão de Tokens13.699 pontosUso de saída · por milhão de Tokens410.959 pontos
qwen-Kling Video 3.0 Turbo
qwen-kling-kling-v3-turbo-video-generationModelo independentekling · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-speech-02-hd
qwen-minimax-speech-02-hdModelo independentemini-max · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated32.9Custo-benefício · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-speech-02-turbo
qwen-minimax-speech-02-turboModelo independentemini-max · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated34.1Custo-benefício · Estimated38.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-speech-2.8-hd
qwen-minimax-speech-2.8-hdModelo independentemini-max · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.1Custo-benefício · Estimated45.9
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-speech-2.8-turbo
qwen-minimax-speech-2.8-turboModelo independentemini-max · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated46.9Custo-benefício · Estimated47.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Flash
qwen-mt-flashModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated59.4Custo-benefício · Estimated56.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Image
qwen-mt-imageModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated34.1Custo-benefício · Estimated38.9
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Lite
qwen-mt-liteModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.3Custo-benefício · Estimated54.4
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-MT-Plus
qwen-mt-plusModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated46.7Custo-benefício · Estimated47.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-PixVerse-V6-r2v
qwen-pixverse-pixverse-v6-r2vModelo independentepixverse · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Plus-Character
Verificação pendente (UTC+8)
qwen-plus-characterModelo independenteqwen-domain-model · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated46.9Custo-benefício · Estimated57.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens219.178 pontosUso de acertos de cache · por milhão de Tokens43.836 pontosUso de saída · por milhão de Tokens547.945 pontos
qwen-stepfun/step-5-preview
Verificação pendente (UTC+8)
qwen-stepfun-step-5-previewModelo independenteStepFun · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated30.7
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens1.917.808 pontosUso de acertos de cache · por milhão de Tokens95.890 pontosUso de saída · por milhão de Tokens5.479.452 pontos
qwen-unisound/unisound-u2
qwen-unisound-unisound-u2Modelo independenteunisound · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated32.9Custo-benefício · Estimated38.0
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vanchin/DeepSeek-R1
qwen-vanchin-deepseek-r1Modelo independenteDeepSeek · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated43.2Custo-benefício · Estimated45.2
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vanchin/DeepSeek-V3
qwen-vanchin-deepseek-v3Modelo independenteDeepSeek · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated42.6Custo-benefício · Estimated44.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-vanchin/deepseek-v4-pro
qwen-vanchin-deepseek-v4-proModelo independenteDeepSeek · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated71.1Custo-benefício · Estimated64.8
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vidu-image-lite_reference2image
qwen-vidu-vidu-image-lite_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated66.4Custo-benefício · Estimated61.5
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vidu-image-pro_reference2image
qwen-vidu-vidu-image-pro_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated66.4Custo-benefício · Estimated61.5
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Vidu-image_reference2image
qwen-vidu-vidu-image_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated73.8Custo-benefício · Estimated66.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-fast_reference2image
qwen-vidu-viduq2-fast_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated66.4Custo-benefício · Estimated61.5
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ2-Pro_reference2image
qwen-vidu-viduq2-pro_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated66.4Custo-benefício · Estimated61.5
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Ad_reference2video
qwen-vidu-viduq3-ad_reference2videoModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Drama_reference2video
qwen-vidu-viduq3-drama_reference2videoModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-fast_reference2image
qwen-vidu-viduq3-fast_reference2imageModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated85.0Custo-benefício · Estimated74.5
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ViduQ3-Pro-fast_img2video
qwen-vidu-viduq3-pro-fast_img2videoModelo independentevidu · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Qwen-Voice-Enrollment
qwen-voice-enrollmentEntrada de serviço independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-ZHIPU/GLM-5.3-FlashX
Verificação pendente (UTC+8)
qwen-zhipu-glm-5.3-flashxModelo independenteZhipu AI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated41.0Custo-benefício · Estimated37.8
Version comparison review0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens547.945 pontosUso de acertos de cache · por milhão de Tokens156.164 pontosUso de saída · por milhão de Tokens1.917.808 pontos
Sambert语音合成-Beth
sambert-beth-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Betty
sambert-betty-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Brian
sambert-brian-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Cally
sambert-cally-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Camila
sambert-camila-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Cindy
sambert-cindy-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Clara
sambert-clara-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Donna
sambert-donna-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Eva
sambert-eva-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Hanna
sambert-hanna-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Indah
sambert-indah-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Perla
sambert-perla-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-Waan
sambert-waan-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知厨
sambert-zhichu-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知达
sambert-zhida-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知德
sambert-zhide-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知飞
sambert-zhifei-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知柜
sambert-zhigui-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知浩
sambert-zhihao-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知佳
sambert-zhijia-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知婧
sambert-zhijing-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知伦
sambert-zhilun-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知猫
sambert-zhimao-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知妙（多情感）
sambert-zhimiao-emo-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知茗
sambert-zhiming-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知墨
sambert-zhimo-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知楠
sambert-zhinan-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知娜
sambert-zhina-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知倩
sambert-zhiqian-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知琪
sambert-zhiqi-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知茹
sambert-zhiru-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知硕
sambert-zhishuo-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知树
sambert-zhishu-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知莎
sambert-zhistella-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知婷
sambert-zhiting-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知薇
sambert-zhiwei-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知祥
sambert-zhixiang-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知笑
sambert-zhixiao-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知雅
sambert-zhiya-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知晔
sambert-zhiye-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知颖
sambert-zhiying-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知媛
sambert-zhiyuan-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
Sambert语音合成-知悦
sambert-zhiyue-v1Entrada de voz independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
鞋靴模特
shoemodel-v1Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
语音识别热词
speech-biasingEntrada de serviço independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
通用文本向量-async-v1
text-embedding-async-v1Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
通用文本向量-async-v2
text-embedding-async-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
意图分类模型
tongyi-intent-detect-v3Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
伶鹊-对话分析-flash
Verificação pendente (UTC+8)
tongyi-xiaomi-analysis-flashModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens54.795 pontosUso de acertos de cache · por milhão de Tokens10.959 pontosUso de saída · por milhão de Tokens109.589 pontos
伶鹊-对话分析-pro
Verificação pendente (UTC+8)
tongyi-xiaomi-analysis-proModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens273.973 pontosUso de acertos de cache · por milhão de Tokens54.795 pontosUso de saída · por milhão de Tokens739.726 pontos
Translate LLM-100
translate-llmModelo independenteGoogle · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
声动人像VideoRetalk
videoretalkModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
视频风格重绘
video-style-transformModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.0Custo-benefício · Estimated50.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
虚拟模特V2
virtualmodel-v2Modelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated44.5Custo-benefício · Estimated46.1
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
大模型声音复刻及声音设计
voice-enrollmentEntrada de serviço independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated56.6Custo-benefício · Estimated54.6
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-Animate-Mix
wan2.2-animate-mixModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-Animate-Move
wan2.2-animate-moveModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-KF2V-Flash
wan2.2-kf2v-flashModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-通义万相2.2-数字人-S2V
wan2.2-s2vModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-S2V-Detect
wan2.2-s2v-detectModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-T2I-Flash
wan2.2-t2i-flashModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.2-T2I-Plus
wan2.2-t2i-plusModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.5-I2I-Preview
wan2.5-i2i-previewModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated52.7Custo-benefício · Estimated51.9
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.5-T2I-Preview
wan2.5-t2i-previewModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated51.5Custo-benefício · Estimated51.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.6-R2V-Flash
wan2.6-r2v-flashModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated55.3Custo-benefício · Estimated53.7
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.0-T2I-Turbo
wanx2.0-t2i-turboModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.1-ImageEdit
wanx2.1-imageeditModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.1-KF2V-Plus
wanx2.1-kf2v-plusModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.1-T2I-Plus
wanx2.1-t2i-plusModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.1-T2I-Turbo
wanx2.1-t2i-turboModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-Wan2.1-VACE-Plus
wanx2.1-vace-plusModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-创意海报生成
wanx-poster-generation-v1Modelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-万相-涂鸦作画
wanx-sketch-to-image-liteModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated34.8Custo-benefício · Estimated39.4
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-人像风格重绘
wanx-style-repaint-v1Modelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-wanx-t2i
wanx-v1Modelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-虚拟模特
wanx-virtualmodelModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated36.9Custo-benefício · Estimated40.8
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
qwen-万相-图像局部重绘
wanx-x-paintingModelo independenteWan · EstávelAdicionado ao catálogo (lançamento pendente): 2026-10-05Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated37.0Custo-benefício · Estimated40.9
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
语音生成cosyvoice-v2大模型
Verificação pendente (UTC+8)
cosyvoice-v2Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated75.4Custo-benefício · Estimated52.8
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres547.946 pontos
语音生成CosyVoice-v3-flash大模型
Verificação pendente (UTC+8)
cosyvoice-v3-flashModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated75.4Custo-benefício · Estimated75.5
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres273.973 pontos
语音生成CosyVoice-v3-plus大模型
Verificação pendente (UTC+8)
cosyvoice-v3-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated75.4Custo-benefício · Estimated52.8
Estimate basis
2026-10-08 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 · OfficialÁudio · por 10.000 caracteres547.946 pontos
GUI-Plus
Verificação pendente (UTC+8)
gui-plusModelo independenteQwen · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated56.6Custo-benefício · Estimated61.7
0/41 fixed-panel observations; remaining cells are marked estimatesEstimate basis
2026-10-08 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 · IndependentUso de entrada · por milhão de Tokens410.959 pontosUso de acertos de cache · por milhão de Tokens0 pontosUso de saída · por milhão de Tokens1.232.877 pontos
通用多模态向量
Verificação pendente (UTC+8)
multimodal-embedding-v1Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated48.1
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens191.781 pontosUso de entrada · Imagem · por milhão de Tokens246.576 pontosEntrada de vídeo · por milhão de Tokens246.576 pontos
Qwen2.5-VL-Embedding
Verificação pendente (UTC+8)
qwen2.5-vl-embeddingModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated48.1
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens191.781 pontosUso de entrada · Imagem · por milhão de Tokens493.151 pontos
Qwen3-ASR-Flash
Verificação pendente (UTC+8)
qwen3-asr-flashModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated94.0
Estimate basis
2026-10-08 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 · IndependentTranscrição · por segundo61 pontos
千问3-Rerank
Verificação pendente (UTC+8)
qwen3-rerankModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated72.5Custo-benefício · Estimated80.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens136.987 pontos
Qwen3-VL-Embedding
Verificação pendente (UTC+8)
qwen3-vl-embeddingModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated48.1
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens191.781 pontosUso de entrada · Imagem · por milhão de Tokens493.151 pontos
Qwen3-VL-Rerank
Verificação pendente (UTC+8)
qwen3-vl-rerankModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated72.5Custo-benefício · Estimated80.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens136.987 pontosEntrada de vídeo · por milhão de Tokens493.154 pontos
Preço estimado de responsabilidade para entrada de vídeo, confirmado pelo cliente. O fornecedor não publicou preço oficial de vídeo nem conversão de quadros para Token. Usado apenas no catálogo e na reserva de testes; não é registrado como custo do fornecedor nem altera cobranças históricas.
Qwen-Image-2.0-Pro
Verificação pendente (UTC+8)
qwen-image-2.0-proModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated66.4Custo-benefício · Estimated46.5
Estimate basis
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem136.987 pontos
Qwen-Image-3.0-Pro
Verificação pendente (UTC+8)
qwen-image-3.0-proModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho85.0Custo-benefício59.5
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentImagem Uso de entrada 1K · por imagem5.480 pontosImagem Uso de entrada 2K · por imagem5.480 pontosImagem Uso de saída 1K · por imagem68.494 pontosImagem Uso de saída 2K · por imagem136.987 pontos
QwenVL-OCR
Verificação pendente (UTC+8)
qwen-vl-ocrModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated81.8Custo-benefício · Estimated72.3
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens82.192 pontosUso de saída · por milhão de Tokens136.987 pontos
通用文本向量-v1
Verificação pendente (UTC+8)
text-embedding-v1Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho58.3Custo-benefício45.3
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrada vetorial · por milhão de Tokens191.781 pontos
通用文本向量-v2
Verificação pendente (UTC+8)
text-embedding-v2Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho60.1Custo-benefício46.6
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrada vetorial · por milhão de Tokens191.781 pontos
通用文本向量-v3
Verificação pendente (UTC+8)
text-embedding-v3Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho63.4Custo-benefício53.9
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrada vetorial · por milhão de Tokens136.987 pontos
通用文本向量-v4
Verificação pendente (UTC+8)
text-embedding-v4Modelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho71.6Custo-benefício59.6
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%aliyun-embedding · OfficialEntrada vetorial · por milhão de Tokens136.987 pontos
视觉向量-flash
Verificação pendente (UTC+8)
tongyi-embedding-vision-flashModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated70.9
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens41.096 pontos
视觉向量-plus
Verificação pendente (UTC+8)
tongyi-embedding-vision-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated62.3Custo-benefício · Estimated53.1
Estimate basis
2026-10-08 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 · OfficialEntrada vetorial · por milhão de Tokens136.987 pontos
Wan2.2-I2V-Flash
Verificação pendente (UTC+8)
wan2.2-i2v-flashModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated38.2
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo27.398 pontosGeração de vídeo 720P · por segundo54.795 pontosGeração de vídeo 1080P · por segundo131.507 pontos
Wan2.2-I2V-Plus
Verificação pendente (UTC+8)
wan2.2-i2v-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo38.357 pontosGeração de vídeo 1080P · por segundo191.781 pontos
Wan2.2-T2V-Plus
Verificação pendente (UTC+8)
wan2.2-t2v-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated23.2
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo38.357 pontosGeração de vídeo 1080P · por segundo191.781 pontos
Wan2.5-I2V-Preview
Verificação pendente (UTC+8)
wan2.5-i2v-previewModelo independenteAlibaba Cloud · PréviaAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho55.3Custo-benefício46.8
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo 480P · por segundo82.192 pontosGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
Wan2.5-T2V-Preview
Verificação pendente (UTC+8)
wan2.5-t2v-previewModelo independenteAlibaba Cloud · PréviaAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho48.9Custo-benefício42.3
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 45%arena · IndependentGeração de vídeo 480P · por segundo82.192 pontosGeração de vídeo 720P · por segundo164.384 pontosGeração de vídeo 1080P · por segundo273.973 pontos
wan2.6-I2V-flash
Verificação pendente (UTC+8)
wan2.6-i2v-flashModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated54.9Custo-benefício · Estimated60.3
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo82.192 pontosGeração de vídeo 1080P · por segundo136.987 pontos
Wan2.1-I2V-Plus
Verificação pendente (UTC+8)
wanx2.1-i2v-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated13.2
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo191.781 pontos
Wan2.1-I2V-Turbo
Verificação pendente (UTC+8)
wanx2.1-i2v-turboModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated34.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo65.754 pontosGeração de vídeo 720P · por segundo65.754 pontos
Wan2.1-T2V-Plus
Verificação pendente (UTC+8)
wanx2.1-t2v-plusModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated13.2
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 720P · por segundo191.781 pontos
Wan2.1-T2V-Turbo
Verificação pendente (UTC+8)
wanx2.1-t2v-turboModelo independenteAlibaba Cloud · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-10Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated11.7Custo-benefício · Estimated34.6
Estimate basis
2026-10-08 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 · IndependentGeração de vídeo 480P · por segundo65.754 pontosGeração de vídeo 720P · por segundo65.754 pontos
doubao-hitem3d-2-0-251223
Verificação pendente (UTC+8)
doubao-hitem3d-2-0-251223Snapshot / versão fixa · Acesso únicoHitem3D · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated82.2Custo-benefício · Estimated57.5
Estimate basis
2026-10-08 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 · OfficialUso de saída · 3D · por milhão de Tokens21.917.809 pontos
doubao-hyper3d-gen2-260112
Verificação pendente (UTC+8)
doubao-hyper3d-gen2-260112Snapshot / versão fixa · Acesso únicoHyper3D · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated82.2Custo-benefício · Estimated87.5
Estimate basis
2026-10-08 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 · OfficialUso de saída · 3D · por milhão de Tokens16.438.357 pontos
doubao-seedance-2-0-260128
Verificação pendente (UTC+8)
doubao-seedance-2-0-260128Snapshot / versão fixa · Acesso únicoByteDance · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.5Custo-benefício · Estimated68.5
Estimate basis
2026-10-08 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 · IndependentUso de saída · Geração de vídeo · por milhão de Tokens12.602.740 pontos
doubao-seedance-2-0-fast-260128
Verificação pendente (UTC+8)
doubao-seedance-2-0-fast-260128Snapshot / versão fixa · Acesso únicoByteDance · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.5Custo-benefício · Estimated70.8
Estimate basis
2026-10-08 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 · IndependentUso de saída · Geração de vídeo · por milhão de Tokens7.602.740 pontos
doubao-seedance-2-0-mini-260615
Verificação pendente (UTC+8)
doubao-seedance-2-0-mini-260615Snapshot / versão fixa · Acesso únicoByteDance · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Última verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.5Custo-benefício · Estimated75.9
Estimate basis
2026-10-08 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 · IndependentUso de saída · Geração de vídeo · por milhão de Tokens2.520.548 pontos
doubao-seedream-5-0-260128
Verificação pendente (UTC+8)
doubao-seedream-5-0-260128Snapshot / versão fixa · Acesso únicoByteDance · EstávelAdicionado ao catálogo (lançamento pendente): 2026-09-09Disponível · criação e ediçãoÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated54.4Custo-benefício · Estimated53.4
Estimate basis
2026-10-08 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 · IndependentUso de saída · Imagem · por imagem60.274 pontos
GPT-4o Transcribe Diarize
Verificação pendente (UTC+8)
gpt-4o-transcribe-diarizeModelo independenteOpenAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-08-28Disponível · ferramentas de áudioÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated91.4Custo-benefício · Estimated64.0
Estimate basis
2026-10-08 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 · IndependentUso de entrada · Áudio · por milhão de Tokens12.000.000 pontosUso de entrada · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontos
GPT Audio
Verificação pendente (UTC+8)
gpt-audioModelo independenteOpenAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-08-28Capacidades completasÚltima verificação do preçoVerificação pendente (UTC+8)
Desempenho · Estimated52.6Custo-benefício · Estimated36.8
Estimate basis
2026-10-08 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 · OfficialUso de entrada · por milhão de Tokens5.000.000 pontosUso de saída · por milhão de Tokens20.000.000 pontosUso de entrada · Áudio · por milhão de Tokens80.000.000 pontosUso de saída · Áudio · por milhão de Tokens160.000.000 pontos
Mistral Document AI 2512
Verificação pendente (UTC+8)
mistral-document-ai-2512Modelo independenteMistral AI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-08-28Última verificação do preçoVerificação pendente (UTC+8)
Desempenho96.1Custo-benefício76.1
Provisório
2026-10-08 16:22 (UTC+8) · Confidence 18%mistral-ocr · OfficialProcessamento de documentos · por 1.000 páginas6.000.000 pontos
Model Router
model-routerServiço de encaminhamento independenteOpenAI · EstávelAdicionado ao catálogo (lançamento pendente): 2026-08-28Sem preço fixo; cobrança conforme o serviçoDesempenho · Estimated50.0Custo-benefício · Estimated50.0
Estimate basis
2026-10-08 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 · IndependentPreço dinâmico: acréscimo de entrada do roteador e pontos do modelo realmente selecionado.
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.
LIMITE ATUAL
Limite atual
Adicionados 32 modelos fora do Google: 27 de texto, Mistral Document AI, três de embeddings e Sora 2. Atualize para o conector 1.0.86.0 e ative cada plugin e permissão da chave API. API de texto: 34 modelos; menu Codex: 32 com ferramentas. Phi e Llama atendem somente perguntas pela API. Documentos: 30 MB e 30 páginas. Busca com citações em textos locais selecionados e índices reutilizáveis. Vídeo: 4/8/12 segundos, 720p, imagens de referência e remix de vídeos concluídos. Baixe os vídeos logo. Uso concluído é cobrado; leitura do cache é gratuita. Google e model-router continuam excluídos. Identidades, protocolos, dados, agentes e controle permanecem no ambiente local, de borda ou privado autorizado pelo cliente. O site público apenas apresenta o serviço; não controla equipamentos pela nuvem.