---
id: "mistralai/mistral-nemo"
also: ["mistralai/mistral-nemo", "mistralai/Mistral-Nemo-Instruct-2407", "requesty/mistral/mistral-nemo", "vercel/mistral/mistral-nemo"]
card_usd_per_m: "0.15 in, 0.15 out, at mistral/eu"
cheapest_list_usd_per_m: "0.0166 in, 0.0216 out, at io-net/fp16 on openrouter"
cheapest_effective_usd_per_m: "0.0122 in, 0.0206 out, at io-net/fp16 on openrouter"
context: 131072
max_output: 16384
input: ["text"]
output: ["text"]
released: "2024-07-19"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 11
gateways: "openrouter (6), vercel (4), requesty (1)"
no_training: 10
trains: 0
retains_prompts: 1
---
# Mistral: 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.