Mistral Nemoon Krater.ai

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,

Released July 19, 2024

Specifications

Mistral Nemo at a glance

Context

131.1K tokens

Max output

16.4K tokens

Input

Text

Output

Text

Input price

$0.02 / 1M

Output price

$0.03 / 1M

Knowledge cutoff

2024-04-30

Tool callingStructured outputs

Capabilities

What it is good at

Catalog capabilities

  • Generates text responses
  • Supports tool calling
  • Supports structured outputs
  • Instruction format: mistral

Good for

Long documentsUse with toolsStructured responses

FAQ

Questions about Mistral Nemo

Clear answers based on the model catalog and Krater access.

Mistral Nemo supports a context window of 131,072 tokens.

Use Mistral Nemo in your API

Connect with Krater's unified API.

API access

Ready to use Mistral Nemo?

Access leading models in one focused workspace.