ministral-8b-2512 API Pricing
ministral-8b-2512 on Mistral AI costs $0.15 per 1M input tokens and $0.15 per 1M output tokens (as of ).
| Input | $0.15 / 1M tokens |
|---|---|
| Output | $0.15 / 1M tokens |
| Cached input (read) | $0.01 |
| Cache write | — |
| Batch input / output | — |
| Above 200K tokens (input / output) | — |
| Context window | 262K tokens |
| Max output | 262K tokens |
| Supports | vision, tool calling |
| Deprecation date | None listed |
| API model id | ministral-8b-2512 |
| In our records since |
What it costs for common jobs
Estimated from the list price above (no caching or batch discount).
| Job | Estimated cost |
|---|---|
| 1,000 chat replies (2,000 tokens in, 500 out each) | $0.38 |
| Summarising 100 long documents (50,000 in, 1,000 out each) | $0.77 |
| 1 million classification calls (300 in, 5 out each) | $45.75 |
Try your own numbers in the LLM API cost calculator.
Price history
- Between and : cached input price changed from — to $0.01 per 1M tokens.
Similarly priced models
| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M | Context |
|---|---|---|---|---|---|
| ministral-3-8b-2512 | Mistral AI | $0.15 | $0.15 | $0.01 | 262K |
| ministral-8b-latest | Mistral AI | $0.15 | $0.15 | $0.01 | 262K |
| devstral-small-latest | Mistral AI | $0.10 | $0.30 | $0.01 | 256K |
| mistral-small | Mistral AI | $0.10 | $0.30 | $0.01 | 32K |
| voxtral-small-2507 | Mistral AI | $0.10 | $0.40 | $0.01 | 33K |
| voxtral-small-latest | Mistral AI | $0.10 | $0.40 | $0.01 | 33K |
| ministral-3-3b-2512 | Mistral AI | $0.10 | $0.10 | $0.01 | 131K |
| ministral-3b-2512 | Mistral AI | $0.10 | $0.10 | $0.01 | 131K |