Mistral: Mistral Nemo

Created Jul 19, 2024131,072 context

$0.02/M input tokens$0.04/M output tokens

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.

Created Jul 19, 2024131,072 context

$0.02/M input tokens$0.04/M output tokens

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.

Recent activity on Mistral Nemo

Prompt

3.3B

Completion

208M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Prompt

3.3B

Completion

208M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.