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, Chinese, Japanese, Korean, Arabic, and Hindi.
It supports function calling and is released under the Apache 2.0 license.
Modalities
In / Out Price
$0.019 / $0.03per 1M
Context
131K
Released
Jul 19, 2024
Knowledge Cutoff
Apr 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, Chinese, Japanese, Korean, Arabic, and Hindi. It supports function calling and is released under the Apache 2.0 license.
Mistral Nemo costs $0.019/M input tokens and $0.03/M output tokens.
Mistral Nemo has a 131,072 token context window. It supports up to 16,384 completion tokens.
The Mistral Nemo endpoint shown on this page does not accept tools, so function calling is unavailable there. It supports response_format for JSON output, without JSON-schema enforcement.
Mistral Nemo is served by 4 providers on OpenRouter: DeepInfra, Parasail, NovitaAI and io.net. Requests are routed to the best available provider, with automatic failover to the others, and you can pin or exclude providers with provider routing.
Mistral Nemo was released on July 19, 2024. Its knowledge cutoff is April 30, 2024.