Mistral · Open weights
Mixtral 8x22B
Mixtral 8x22B is a powerful sparse Mixture of Experts (MoE) model with 141B total parameters and 39B active per token. Features a 64K context window, exceptional math performance, and cost-efficient inference. Supports English, French, German, Spanish, and Italian. Apache 2.0 licensed.
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $2.00
- Output
- $6.00
- Cache read
- $0.20
Reference prices as published by the model provider. API example
Specifications
- Context window
- 65.5K
- Max output
- 52.4K
- Average output (7 days)
- 292 tokens
- Longer than 30% of 468 models
Side by side
Mixtral 8x22B compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| Mixtral 8x22BMistralThis model | Mistral Code LatestMistralRemove | |
|---|---|---|
| Provider | Mistral | Mistral |
| Discovery tier | Open weights | Balanced |
| Added | Dec 11, 2025 | Jun 2, 2026 |
| Limits | ||
| Context window | 65.54K | 256KBest |
| Max output | 52.43KBest | 32.77K |
| Average output | 292 tokens | — |
| Pricing, USD per 1M tokens | ||
| Input | $2.00 | $0.30Best |
| Output | $6.00 | $0.90Best |
| Cache read | $0.20 | — |
| Performance | ||
| Request success (24h) | 100.0% | — |
| Benchmark indexes | ||
| Intelligence Index | 5.7 | — |
| Capabilities | ||
| Tools | No | Yes |
| Structured output | No | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- Mixtral 8x22B
- Mistral Code Latest
Intelligence Index
- Mixtral 8x22B5.7
- Mistral Code Latest—
Mixtral 8x22B: Better than 2% of 326 scored models
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- Mixtral 8x22B: 4.0%
- Mistral Code Latest: —
GPQA Diamond
Graduate-level science questions
- Mixtral 8x22B: 33.2%
- Mistral Code Latest: —
MMLU-Pro
Multi-subject knowledge and reasoning
- Mixtral 8x22B: 53.7%
- Mistral Code Latest: —
Coding
LiveCodeBench
Recent competitive programming problems
- Mixtral 8x22B: 14.8%
- Mistral Code Latest: —
Math
AIME
Competition mathematics
- Mixtral 8x22B: 0.0%
- Mistral Code Latest: —
MATH-500
Competition math problems
- Mixtral 8x22B: 54.5%
- Mistral Code Latest: —
Scores from Artificial Analysis, updated Oct 26, 2026.
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Prompt cache hits
- 33.0%
- About $1.41 per 1M input tokens with caching
- Request success (24h)
- 100.0%
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mixtral-8x22b-instruct-v0.1",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="mistralai/mixtral-8x22b-instruct-v0.1",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)Mistral
Related models
Other Mistral models, starting with the same family.