DataAIHub
DataAIHubNews · Research · Tools · Learning
MistralOpen SourceCodingSmall Models

Mixtral

Mistral’s sparse Mixture-of-Experts open models (e.g. Mixtral 8x7B / 8x22B) — efficient high-quality text generation for self-hosting.

Tool calling · Coding

Last reviewed: 16 August 2026

Overview

Mistral’s sparse Mixture-of-Experts open models (e.g. Mixtral 8x7B / 8x22B) — efficient high-quality text generation for self-hosting.

Capabilities

  • Vision: No
  • Audio: No
  • Tool calling: Yes
  • Thinking: No
  • MCP: No
  • Coding: Yes
  • Structured output: Yes

Technical specifications

Provider
Mistral
License
Apache-2.0
Context window
64K
Parameters
8x7B / 8x22B MoE
Architecture
Mixture-of-Experts
Release
2023–2024
Modalities
Text
Vision
No
Audio
No
Tool calling
Yes
Thinking
No
MCP
No
Open weights
Yes
API
Yes
Pricing (input)
Self-host (infra cost)
Pricing (output)
Self-host (infra cost)

Supported modalities

Text

Context window

64K (64,000 tokens)

Pricing

Input: Self-host (infra cost)
Output: Self-host (infra cost)

Not listed on Mistral serverless API pricing as of 2026-08-16. Third-party inference hosts may still serve Mixtral weights.

Availability

API: Yes
Chat UI: No
Open weights: Yes

Apache-2.0 weights for self-host. Mistral’s own serverless pricing page no longer lists Mixtral 8x7B / 8x22B as of 2026-08-16; prefer self-host or third-party hosts over assuming La Plateforme.

Use cases

  • Self-hosted chat and RAG
  • Cost-efficient batch inference
  • On-prem coding assistants
  • MoE serving experiments

Strengths

  • Apache-2.0 friendly licensing
  • Strong quality per activated parameter
  • Excellent community serving support

Limitations

  • Surpassed by newer dense/MoE open models on many benches
  • Text-only for classic Mixtral releases

Related guides

Related benchmarks

Related research

Related GitHub

Related tools

Related rankings

Companies

Explore more models

All models →