Mistral Small vs Ministral 14B
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Mistral Smallmistral/mistral-small | Ministral 14Bmistral/ministral-14b |
|---|---|---|
| Maker | mistral | mistral |
| Kind | Chat | Chat |
| Input per 1M tokens | $0.1575 Lower | $0.21 |
| Cached input per 1M tokens | $0.01575 | $0.021 |
| Cache write per 1M tokens | Same as input | Same as input |
| Output per 1M tokens | $0.63 | $0.21 Lower |
| Context window | 262,144 tokens | 262,144 tokens |
| Max output | 4,000 tokens | 256,000 tokens Larger |
| Capabilities | Tool use, vision | Tool use, vision, file input |
| Takes | Text, image | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Yes, on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2024-09-17 | 2025-12-02 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Mistral Small | Ministral 14B |
|---|---|---|
| 1,000 tokens in, 200 out | $0.000284 | $0.000252 |
| 10,000 tokens in, 1,000 out | $0.002205 | $0.00231 |
| 100,000 tokens in, 4,000 out | $0.01827 | $0.02184 |