Mistral AI

Mixtral 8x22B Instruct

mistralai/mixtral-8x22b-instruct

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

Mixtral 8x22B Instruct

open weights tools

Mistral AI mistralai/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,...

Input $/1M: $2.00
Output $/1M: $6.00
Context: 66K
Max output: 52K
Released: Apr 17, 2024
Modalities: textfile

Cached input reads $0.20 per 1M · weights on Hugging Face as mistralai/Mixtral-8x22B-Instruct-v0.1

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs Mixtral 8x22B Instruct
targets:
  - id: mixtral-8x22b-instruct
    kind: llm
    name: Mixtral 8x22B Instruct
    metadata:
      model: mistralai/mixtral-8x22b-instruct          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 65536
    cost:
      usd_per_1k_tokens: 0.004000

Price among Mistral AI models

Input list price per million tokens; Mixtral 8x22B Instruct is the most expensive of 13 listed.

More from Mistral AI

Other models by the same vendor in the catalogue.