Mistral Small overview

Provider

The company that provides the model

Mistral

Context window

The number of tokens you can send in a prompt

32k tokens

Maximum output

The maximum number of tokens a model can generate in one request

4,096 tokens

Input token cost

The cost of prompt tokens sent to the model

$0.20 / 1M input tokens

Output token cost

The cost of output tokens generated by the model

$0.60 / 1M output tokens

Knowledge cut-off date

When the model's knowledge ends

Unknown

Release date

When the model was launched

February 26, 2024

Mistral Small functionality

Function (tool calling) support

Capability for the model to use external tools

Yes

Vision support

Ability to process and analyze visual inputs, like images

No

Multilingual

Support for multiple languages

Yes

Fine-tuning

Whether the model supports fine-tuning on custom datasets

Yes

Common questions about Mistral Small

How much does Mistral Small cost?

Mistral Small has a cost structure of $0.20 per million input tokens and $0.60 per million output tokens.

What is the API cost for Mistral Small?

The API cost for Mistral Small is $0.20 per million input tokens and $0.60 per million output tokens.

What is the price per token for Mistral Small?

For Mistral Small, the price is $0.0002 per 1,000 input tokens and $0.0006 per 1,000 output tokens.

What is the context window for Mistral Small?

Mistral Small supports a context window of up to 32,000 tokens.

What is the maximum output length for Mistral Small?

Mistral Small can generate up to 4,096 tokens in a single output.

When was Mistral Small released?

The latest version (v2) of Mistral Small was released on February 26, 2024.

Does Mistral Small support vision capabilities?

No, Mistral Small is a text-only model and does not support vision capabilities.

Can Mistral Small perform tool calling or functions?

Yes, Mistral Small supports tool calling and functions.

Is Mistral Small a multilingual model?

Yes, Mistral Small supports multiple languages, allowing it to handle input and output in several languages.

Does Mistral Small support fine-tuning?

Yes, Mistral Small supports fine-tuning.

Where can I find the official documentation for Mistral Small?

You can find the official documentation for Mistral Small on Mistral’s website: Mistral Small Documentation

Better LLM outputs are a click away

PromptHub is better way to test, manage, and deploy prompts for your AI products