Mistral Medium 3.5 API pricing
As of October 22, 2026, Mistral Medium 3.5 costs $1.50 per million input tokens and $7.50 per million output tokens on Mistral AI's own API.
Mistral Medium 3.5 benchmarks and specs · Every Mistral AI model's price
- Input, per million tokens$1.50
- Output, per million tokens$7.50
- Cached input, per millionNo cache price listed
- Context window262K tokens
- Max output210K tokens
- Output speed151 tok/s
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 | $0.0053 | $5.25 | Yes |
| Repository review | 50K input + 3K output tokens | $0.098 | $97.50 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.375 | $375.00 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $6.02 | $6020.00 |
Price history
We have read Mistral AI's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $1.50 input, $7.50 output
Cheaper models as good as Mistral Medium 3.5
Models within two points of Mistral Medium 3.5 or above it on the LLMBenchmark Index, with a lower output price. Cheapest first.
- gpt-oss-20b$0.15 Overall 38.5 against 37.3 · 98% cheaper output
- Qwen3.5-Flash$0.26 Overall 50.1 against 37.3 · 97% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 60.8 against 37.3 · 96% cheaper output
- Qwen3 30B A3B Instruct 2507$0.30 Overall 41.5 against 37.3 · 96% cheaper output
- MiMo-V2.5$0.336 Overall 50.7 against 37.3 · 96% cheaper output
Mistral Medium 3.5 pricing questions
- How much does Mistral Medium 3.5 cost per million tokens?
- $1.50 per million input tokens and $7.50 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Mistral Medium 3.5 support prompt caching?
- OpenRouter lists no cached input price for this model, so assume every input token is billed at the full rate.
- Is there a cheaper model as good as Mistral Medium 3.5?
- gpt-oss-20b scores 38.5 on the LLMBenchmark Index, within two points of Mistral Medium 3.5 or above it, and costs $0.15 per million output tokens.
- Has the price of Mistral Medium 3.5 changed?
- Not since we started recording it daily on October 21, 2026.