Text model
mistral-medium pricing
Mistral charges $1.50 per million input tokens and $7.50 per million output tokens for mistral-medium, and $0.15 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $1.50/ 1M
- Output
- $7.50/ 1M
- Cached input
- $0.15/ 1M
- Context
- 262.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $1.50 | $7.50 | $0.15 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.00525 | 100,000 | $525.00 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00735 | 100,000 | $735.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.01 | 250,000 | $3,300.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with mistral-medium, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| mistral/glm-5-2 | $0.00386 | 26% |
| mistral/zai-glm-5 | $0.00386 | 26% |
| deepinfra/Qwen/Qwen3.8-Max | $0.00446 | 15% |
| azure-ai/FW-DeepSeek-V4-Pro | $0.00442 | 16% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Mistral pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.