Model overview
Flat pricing is the distinguishing trait of ministral-3b-latest: 0.1 per million tokens read and 0.1 written, the same rate in both directions, which nothing outside the lightweight line applies. It is also the cheapest non-zero entry in the range, two-thirds of the 0.15 charged by the 8B step and half the 0.2 of the 14B one, and its cached input of 0.01 is the lowest figure in the catalogue that is not zero. Set against mistral-small-latest, which shares that 0.15 input band with the 8B step, output is the whole story: 0.6 there against 0.1 here, six times more, for multimodal and multilingual support the lightweight line does not declare.
Billing conditions: Standard API price. Mistral publishes a 90% discount for cached input; cache-write prices are not published separately.
- Context window
- 0 tokens
- Knowledge cutoff
- —
- Price last verified
- First observed
Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.