Loading...
Loading...
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding, and reasoning - large context length (64k) - fluency in English, French, Italian, German, and Spanish See benchmarks on the launch announcement [here](https://mistral.ai/news/mixtral-8x22b/). #moe
Preço/1M
$3.00
559th mais barato
868% acima da mediana
Top 84%
Janela de Contexto
66K
271st maior
Top 80%
Entrada
$2.00
por 1M tokens
Saída
$6.00
por 1M tokens
Combinado
$3.00
por 1M tokens
Mais barato que 16% dos modelos. Preço mediano é $0.31/1M tokens.
Diário
$3.00
Mensal
$90.00
Janela de Contexto
66K
tokens
Maior que 20% dos modelos
Comparação de Janela de Contexto