Mixtral 8x22B Instruct
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
mistralai/mixtral-8x22b-instruct
- Contexto
- 66k tokens
- Máx. completion
- 52,428
- Tools
- Sí
- JSON
- Sí
- Lanzamiento
- 2024-04-17
Llámalo desde Geek Hub
El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.
curl https://api.geekhub.mx/v1/chat/completions \
-H "Authorization: Bearer $GEEKHUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mixtral-8x22b-instruct",
"messages": [{"role": "user", "content": "Hola"}]
}'Preguntas frecuentes
- ¿Qué es Mixtral 8x22B Instruct?
- 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 Mixtral 8x22B Instruct corre en el API de Geek Hub (compatible con OpenAI). Id: mistralai/mixtral-8x22b-instruct.
- ¿Mixtral 8x22B Instruct es gratis?
- No. El input cuesta $2.1801 / 1M tokens y el output $6.5404 / 1M tokens en Geek Hub (markup incluido).
- ¿Cuál es el contexto de Mixtral 8x22B Instruct?
- Mixtral 8x22B Instruct tiene una ventana de 66k tokens. Soporta hasta 52,428 tokens de completion.
- ¿Mixtral 8x22B Instruct soporta tool calling y structured outputs?
- Mixtral 8x22B Instruct acepta tools y tool_choice para function calling. También soporta structured outputs con un JSON schema en response_format.
- ¿Cuándo se lanzó Mixtral 8x22B Instruct?
- Mixtral 8x22B Instruct se lanzó el 17 de abril de 2024.
Más modelos de Mistral
- Codestral 2508Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc
- Codestral 2508 (batch)Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc
- Devstral 2 2512Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. De
- Ministral 3 14B 2512The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and
- Ministral 3 3B 2512The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
- Ministral 3 8B 2512A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.