Worked example
100K input + 2K output
$0.0162
Estimated standard-tier token cost for one request. At 10,000 identical requests per month, the token subtotal would be $162.00.
Open this scenario →Mistral pricing profile
Mistral Small 4
Efficient hybrid instruct, reasoning and coding model.
activeeconomy256,000 contextVerified 2026-08-02
Pricing modes
USD per one million tokens. A documented long-context band applies to the full request when its threshold is crossed.
| Mode | Input | Cached input | Cache write | Output | Long-context band |
|---|---|---|---|---|---|
| standard | $0.15 | — | — | $0.6 | — |
| batch | $0.075 | — | — | $0.3 | — |
Technical limits
Model constraints
Context window256,000 tokens
Maximum output64,000
Long-context thresholdNo separate band recorded
Tokenizer profilemistral
What can change the invoice
- No separate cached-input rate is recorded for the active pricing schedule.
- Taxes, cloud marketplaces, enterprise contracts, retries 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 2026-03-16.
Related Mistral models
Compare models from the same provider before evaluating quality and latency.
Mistral Medium 3.5
Multimodal Mistral model optimized for agentic and coding workloads.
View pricing →Mistral Large 3
General-purpose open-weight multimodal model with competitive token pricing.
View pricing →Ministral 3 8B
Compact text-and-vision model for low-cost processing and edge-oriented workloads.
View pricing →