token.app › Mistral AI › Mixtral 8x22B Instruct
Mixtral 8x22B Instruct pricing & benchmarks
Mixtral 8x22B Instruct is available from Mistral AI at $2.00 per million input tokens and $6.00 per million output tokens ($3.00 blended at 3:1). It accepts up to 65,536 tokens of context. 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,…
Pricing
Per million tokens · OpenRouter
Input$2.00
Output$6.00
Blended (3:1)$3.00
Specification
mistralai/mixtral-8x22b-instruct
Context window66K
Max output52K
ReleasedApr 2024
LicenceOpen weights
Modalitiesin:text, in:file, out:text
Benchmarks
Independently run — not vendor self-reports. Every score links its source.
| Benchmark | Score | Config | Run | Source |
|---|---|---|---|---|
| GPQA Diamond | 34.1% ±2.1 | — | 2025-01-27 | Independently run · Epoch AI |
Scores published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0.
Cheaper models that score at least as well on GPQA Diamond
Strictly lower blended price AND an equal-or-higher GPQA Diamond score. One benchmark is one dimension — a model that wins here may still be weaker at your specific task.
| Model | Provider | Blended $/1M | GPQA Diamond | |
|---|---|---|---|---|
| gpt-oss-20b | OpenAI | $0.036 (−99%) | 60.8% | Compare → |
| Qwen3.7 Flash | Alibaba | $0.055 (−98%) | 82.3% | Compare → |
| Phi 4 | Microsoft | $0.088 (−97%) | 56.1% | Compare → |
| Qwen3.5-Flash | Alibaba | $0.114 (−96%) | 82.3% | Compare → |
| GPT-5 Nano | OpenAI | $0.138 (−95%) | 69.4% | Compare → |
Where to run Mixtral 8x22B Instruct
3 options across 1 provider · 1.1× between cheapest and dearest. Blended at 3:1. ⚠ marks an option serving less context than the best available, or re-pricing above a prompt-length threshold. Bracketed labels are the provider's own service tier or region.
| Host | Blended $/1M | In / Out | Context | Uptime 24h |
|---|---|---|---|---|
| Mistral (zdr) | $3.00 | $2.00 / $6.00 | 66K | 100.0% |
| Mistral | $3.00 | $2.00 / $6.00 | 66K | 100.0% |
| Mistral (eu) | $3.30 | $2.20 / $6.60 | 66K | — |
Host prices and uptime from OpenRouter, synced 2026-10-22.
Compare Mixtral 8x22B Instruct
Mixtral 8x22B Instruct vs Gemini 3.7 Flash
Mixtral 8x22B Instruct vs Grok 4.6
Mixtral 8x22B Instruct vs DeepSeek V4 Flash 0731
Mixtral 8x22B Instruct vs Inkling Small
Mixtral 8x22B Instruct vs Qwen3.7 Flash
Mixtral 8x22B Instruct vs Claude Opus 5
Mixtral 8x22B Instruct vs Gemini 3.6 Flash
Mixtral 8x22B Instruct vs Gemini 3.5 Flash Lite
FAQ
How much does Mixtral 8x22B Instruct cost?
Mixtral 8x22B Instruct costs $2.00 per million input tokens and $6.00 per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to $3.00 per million tokens.
What is Mixtral 8x22B Instruct's context window?
Mixtral 8x22B Instruct accepts up to 65,536 tokens of context, and can generate up to 52,428 output tokens.
How good is Mixtral 8x22B Instruct on benchmarks?
Mixtral 8x22B Instruct scores 34.1% on GPQA Diamond, independently run and published by Epoch AI. 1 benchmark result are listed on this page, each with its run date and source.
Is there a cheaper model as good as Mixtral 8x22B Instruct?
Yes — 5 models in our catalogue cost less per token than Mixtral 8x22B Instruct and score at least as high on the same benchmark. The cheapest is gpt-oss-20b at $0.036 per million tokens blended.