Mixtral 8x22B Instruct API pricing
As of October 21, 2026, Mistral Mixtral 8x22B Instruct costs $2.00 per million input tokens and $6.00 per million output tokens through OpenRouter, with cached input at $0.20 per million.
Mixtral 8x22B Instruct benchmarks and specs · Every Mistral AI model's price
- Input, per million tokens$2.00
- Output, per million tokens$6.00
- Cached input, per million$0.20
- Context window66K tokens
- Max output52K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0050 | $5.00 | Yes |
| Repository review | 50K input + 3K output tokens | $0.118 | $118.00 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.460 | $460.00 | No, it would need splitting |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We read this price every day and have since October 15, 2026. It has not changed yet; any change will be listed here with its date.
- October 15, 2026 First recorded: $2.00 input, $6.00 output
Cheaper models as good as Mixtral 8x22B Instruct
Models within two points of Mixtral 8x22B Instruct or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Gemma 3 4B$0.05 Overall 4.8 against 5.7 · 99% cheaper output
- Ling 3.0 Flash$0.063 Overall 20.1 against 5.7 · 99% cheaper output
- Llama 3.1 8B Instruct$0.08 Overall 6.9 against 5.7 · 99% cheaper output
- Mistral Small 3$0.08 Overall 6.7 against 5.7 · 99% cheaper output
- gpt-oss-20b$0.09 Overall 10.0 against 5.7 · 99% cheaper output
Mixtral 8x22B Instruct pricing questions
- How much does Mixtral 8x22B Instruct cost per million tokens?
- $2.00 per million input tokens and $6.00 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does Mixtral 8x22B Instruct support prompt caching?
- Yes. OpenRouter lists cached input at $0.20 per million tokens, against $2.00 for uncached input.
- Is there a cheaper model as good as Mixtral 8x22B Instruct?
- Gemma 3 4B scores 4.8 on the Artificial Analysis Intelligence Index, within two points of Mixtral 8x22B Instruct or above it, and costs $0.05 per million output tokens.
- Has the price of Mixtral 8x22B Instruct changed?
- Not since we started recording it daily on October 15, 2026.