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 input: 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 input
- 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
- Mixtral of Experts
Original Paper
Related GitHub
Related tools
Related rankings
Companies
Explore more models
- Mistral LargeMistralMistral’s flagship large model for enterprise reasoning, multilingual chat, and function calling via La Plateforme and cloud partners. Large 3 is the generally available line; Mistral Large 4 (`mistral-large-4`) entered public preview on 2026-10-06 as a natively multimodal MoE with 1.05T total / 52B active parameters, a 1.6B vision encoder, and a 1M-token context, with open weights promised by the end of October.
- PhiMicrosoftMicrosoft’s Phi family of small language models — high capability per parameter for on-device, edge, and cost-sensitive deployments.
- Sarvam 30BSarvamSarvam’s efficient open-weight reasoning MoE. About 2.4B active parameters, built for real-time conversational agents on the Samvaad platform and for local or GPU-constrained deployment.
- Muse GlimmerMetaMeta Superintelligence Labs’ Muse Glimmer — Apache-2.0 ~30B dense multimodal agent model for on-device and single-GPU local agents. Sibling to closed Muse Spark and Muse Wonder; distinct from Llama 4.
- DeepSeek V3DeepSeekDeepSeek’s MoE general model — strong open-weight performance on coding and knowledge tasks with competitive API pricing.
- Beam 1.0ReflectionReflection’s Beam 1.0 — Apache-2.0 text-only sparse MoE (501B total, 23B active, 1M context) for agentic coding and reasoning. Weights shipped 2026-10-16 with day-0 support in Hugging Face Transformers, vLLM, and SGLang. This is not the beam.cloud GPU tool.