Worked example
100K input + 2K output
$0.165
Estimated token cost for one request. At 10,000 identical requests per month, the token subtotal would be $1,650.
Open this scenario →Mistral pricing profile
Mistral Medium 3.5
Multimodal Mistral model optimized for agentic and coding workloads.
active
frontier
256,000 context
Verified 2026-08-02
Pricing modes
USD per one million tokens. Unsupported rate types are shown as unavailable rather than treated as zero.
| Mode | Input | Cached input | Cache write | Output | Long-context band |
|---|---|---|---|---|---|
| standard | $1.5 | — | — | $7.5 | — |
| batch | $0.75 | — | — | $3.75 | — |
Technical limits
Model constraints
Context window256,000 tokens
Maximum output64,000
Long-context thresholdNot applicable
Tokenizer profilemistral
What can change the invoice
- The current official schedule does not list a separate cached-input price.
- Taxes, cloud marketplaces, enterprise contracts, retries, latency and quality differences are not included in this example.
Verification record
Pricing was checked against first-party documentation on 2026-08-02. The active schedule is effective from 2026-04-28.
Related Mistral models
Compare models from the same provider before evaluating quality and latency.
Mistral Large 3
General-purpose open-weight multimodal model with competitive token pricing.
View pricing →Mistral Small 4
Efficient hybrid instruct, reasoning and coding model.
View pricing →Ministral 3 8B
Compact text-and-vision model for low-cost processing and edge-oriented workloads.
View pricing →