AI Observatory / Model Radar Mistral / mistralai/mixtral-8x22b-instruct

Mistral: 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,...

65,536 Context
N/A Max output
$2.00 / 1M Prompt price
2024-04-17 Created
01 / Snapshot

Pricing, context, modalities, and parameters.

Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.

Provider Mistral Input modalities text
Output modalities text Prompt price $2.00 / 1M
Completion price $6.00 / 1M Request price N/A
Context length 65,536 Max completion tokens N/A
Supported parameters frequency_penalty, max_tokens, presence_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_p
Best for mistralai/mixtral-8x22b-instruct

Mistral: 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,...

Coding workflows High-volume usage tool-capable low-cost
03 / Colophon

Routes and exits.

Each model page stays simple: overview, compare, related models, then back to the public hub.