NOUMENOpen app
NOUMEN

Mistral · Open weights

Mixtral 8x22B

Added Dec 11, 2025Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

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.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Mixtral 8x22BMistralThis modelMistral Large 4MistralRemove
ProviderMistralMistral
Discovery tierOpen weightsOpen weights
AddedDec 11, 2025Oct 6, 2026
Limits
Context window65.54K524.29KBest
Max output52.43K—
Average output292 tokens—
Pricing, USD per 1M tokens
Input$2.00$0.68Best
Output$6.00$2.09Best
Cache read$0.20$0.07Best
Performance
Request success (24h)100.0%Best69.0%
Benchmark indexes
Intelligence Index5.7—
Capabilities
ReasoningNoYes
ToolsNoYes
VisionNoYes
Structured outputNoYes
Reasoning effort—none, high

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

  • Mixtral 8x22B
  • Mistral Large 4

Intelligence Index

  • Mixtral 8x22B5.7
  • Mistral Large 4—

Mixtral 8x22B: Better than 2% of 326 scored models

3.8Catalog models by score55.1

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • Mixtral 8x22B: 4.0%
    • Mistral Large 4: —

  • GPQA Diamond

    Graduate-level science questions

    • Mixtral 8x22B: 33.2%
    • Mistral Large 4: —

  • MMLU-Pro

    Multi-subject knowledge and reasoning

    • Mixtral 8x22B: 53.7%
    • Mistral Large 4: —

Coding

  • LiveCodeBench

    Recent competitive programming problems

    • Mixtral 8x22B: 14.8%
    • Mistral Large 4: —

Math

  • AIME

    Competition mathematics

    • Mixtral 8x22B: 0.0%
    • Mistral Large 4: —

  • MATH-500

    Competition math problems

    • Mixtral 8x22B: 54.5%
    • Mistral Large 4: —

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
40.6%
About $1.27 per 1M input tokens with caching
Request success (24h)
100.0%
Reliable

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.

Hourly request success · last 72 hoursLowest hour 100.0%
  • Healthy (98% or more)
  • Degraded (90–98%)
  • Down (under 90%)
  • No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart
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

Other Mistral models, starting with the same family.