Mistral Nemo
Mistral AI · Jul 19, 2024
A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese,…
Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...
mistralai/mistral-small-2603Mistral Small 4 is an API model from Mistral AI, released on Mar 16, 2026, with a context window of 262,144 tokens, pricing of $0.15 per million input tokens and $0.6 per million output tokens. It accepts image, text input and produces text output.
At listed prices, a request with 10,000 input tokens and 1,000 output tokens costs about $0.0021.
Specs are sourced from OpenRouter and were last checked on Sep 22, 2026. Always confirm current pricing and limits with the provider before production use.
Mistral Small 4 supports a context window of 262,144 tokens.
Mistral Small 4 is listed at $0.15 per million input tokens and $0.6 per million output tokens on OpenRouter.
Mistral Small 4 was published on Mar 16, 2026.
Mistral Small 4 accepts image, text input and produces text output.