Mistral AI · Released Apr 17, 2024Mixtral 8x22B Instruct
Mistral model for multilingual chat, reasoning, and tool-assisted workflows.
- Capability
- 122.0ECI · #155 of 165
- Input
- $2.00per 1M tokens
- Output
- $6.00per 1M tokens
- Context
- 66K52K max output
What it costs
- Input
- $2.00per million tokens
- Output
- $6.00per million tokens
- Blended (3:1)
- $3.00pricier than 76% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $7.00 |
| Team assistant25M input + 5M output tokens | $80.00 |
| Production app250M input + 50M output tokens | $800.00 |
Median of 5 paid API providers on models.dev.
Independent benchmarks
#155 of 165 scored models
The shaded band is Epoch AI’s confidence range (115.7–124.3); the tick marks the median scored model.
Scores from Epoch AI, run independently of Mistral AI.
The details
- Lab
- Mistral AI
- Released
- Apr 17, 2024
- Knowledge cutoff
- Jan 31, 2024
- Context window
- 65,536 tokens
- Max output
- 52,428 tokens
- Inputs
- Text, PDFs
- Output
- Text
- Reasoning
- No
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- Availability
- 5 API providerslisted on models.dev
More from Mistral AI
About Mixtral 8x22B Instruct
How much does Mixtral 8x22B Instruct cost?
Mixtral 8x22B Instruct costs $2.00 input / $6.00 output per million tokens (median across 5 API providers). At a 3:1 input-to-output mix that is $3.00 per million tokens, more expensive than 76% of the 445 priced models we track.
What is the context window of Mixtral 8x22B Instruct?
Mixtral 8x22B Instruct accepts up to 65,536 tokens per request and can write up to 52,428 tokens in one response.
How good is Mixtral 8x22B Instruct?
Epoch AI gives Mixtral 8x22B Instruct a Capabilities Index score of 122.0 (likely range 115.7–124.3), ranking it #155 of 165 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 34.1%.
Is Mixtral 8x22B Instruct open source?
Yes. Mistral AI publishes the weights, so it can be downloaded and self-hosted.
What inputs does Mixtral 8x22B Instruct support?
Mixtral 8x22B Instruct accepts text and PDFs and replies in text. It is not a dedicated reasoning model, supports tool calling.
When was Mixtral 8x22B Instruct released?
Mistral AI released Mixtral 8x22B Instruct on Apr 17, 2024. Its training data runs to Jan 31, 2024.
What are the best alternatives to Mixtral 8x22B Instruct?
The closest current models from other labs on capability, price and release date are Gemma 2 27B (Google, ECI 122.1, $0.65 / $0.65), GPT-4o (OpenAI, ECI 129.0, $2.50 / $10.00), Claude Haiku 3.5 (Anthropic, ECI 127.0, $0.80 / $4.00) and Llama-3.2-90B-Vision-Instruct (Meta, ECI 125.5).