Mistral Nemo

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.

ChatMistral131k tokens$0.0207 / $0.0327 · 1M

mistralai/mistral-nemo

Context
131k tokens
Completion cap
16,384
Tools
Yes
JSON
Yes
Released
2024-07-19

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-nemo",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Mistral Nemo?
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 runs on the Geek Hub API (OpenAI-compatible). Model id: mistralai/mistral-nemo.
Is Mistral Nemo free?
No. Input is $0.0207 per 1M tokens and output is $0.0327 per 1M tokens on Geek Hub (markup included).
What is the context length of Mistral Nemo?
Mistral Nemo has a 131k tokens context window. It supports up to 16,384 completion tokens.
Does Mistral Nemo support tool calling and structured outputs?
Mistral Nemo accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was Mistral Nemo released?
Mistral Nemo was released on 2024-07-19.

More models from Mistral