Mistral
Mixtral 8x22B Instruct
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.
At a glance
- Input / 1M
- $2
- Output / 1M
- $6
- Context
- 66K
- Max output
- 52K
- Intelligence
- 5.7
- Released
- Apr 2024
Pricing
Mixtral 8x22B Instruct API pricing
Per-token rates, plus what common tasks actually cost.
| Input tokensPer 1M tokens | $2 |
|---|---|
| Output tokensPer 1M tokens | $6 |
| Cached input (read)Per 1M tokens | $0.20 |
| Cache writePer 1M tokens | Not available |
Chat message
2K in, 500 out
$7
per 1,000 requests
Coding task
30K in, 4K out
$84
per 1,000 requests
Long document summary
150K in, 2K out
$312
per 1,000 requests
Benchmarks
Mixtral 8x22B Instruct benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
5.7
Coding index
Not available
Agentic index
Not available
Specs
Context window and capabilities
What it can read, what it can write, and which API features it supports.
- Context window
- 66K tokens
- Max output
- 52K tokens
- Input types
- File, Text
- Output types
- Text
- Reasoning effort
- Not available
- Release date
- April 17, 2024
- Knowledge cutoff
- January 31, 2024
- Tool calling
- Structured outputs
- JSON mode
- Reasoning
- Temperature
- Stop sequences
- Deterministic seed
- Verbosity control
Compare
Mixtral 8x22B Instruct vs other models
See how Mixtral 8x22B Instruct stacks up head to head on price, benchmarks, and features.
VSMixtral 8x22B Instruct vs Mistral Medium 3.1
Mistral vs Mistral
See comparisonVSMixtral 8x22B Instruct vs Mistral Medium 3
Mistral vs Mistral
See comparisonVSMixtral 8x22B Instruct vs Devstral 2 2512
Mistral vs Mistral
See comparisonVS
Mixtral 8x22B Instruct vs GPT-4o (2024-11-20)
Mistral vs OpenAI
See comparisonVSMixtral 8x22B Instruct vs GPT-4o (2024-08-06)
Mistral vs OpenAI
See comparisonVS
Mixtral 8x22B Instruct vs Sonar Pro
Mistral vs Perplexity
See comparisonAlternatives
Mixtral 8x22B Instruct alternatives
Similar models worth considering, and where each one has the edge.
Mistral
Mistral Medium 3.1
Mistral
Mistral Medium 3
Mistral
Devstral 2 2512
Want to learn about other models? Browse all models
FAQ
Frequently asked questions
How much does Mixtral 8x22B Instruct cost?
Mixtral 8x22B Instruct costs $2 per 1M input tokens and $6 per 1M output tokens through the API. A typical chat message costs about $7 per 1,000 messages.
What is the context window of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct accepts up to 66K tokens of input and can write up to 52K tokens in a single response.
What is the best alternative to Mixtral 8x22B Instruct?
Mistral Medium 3.1 from Mistral is a strong alternative. It offers: 3x cheaper output, higher intelligence score, larger 131k context.
Can I use Mixtral 8x22B Instruct alongside other models?
Yes. Shortcut Chat sends one prompt to Mixtral 8x22B Instruct and any other models you pick at the same time, so you can compare answers side by side.
Try Mixtral 8x22B Instruct next to every other model.
Use Mixtral 8x22B Instruct alongside all the other models. Use one at a time, or multiple together. Get the best answer from every AI.