Mistral

Use Mistral models with Kern agents.

Mistral is a platform for providing endpoints for Large Language models. See their library of models here.

We recommend experimenting to find the best-suited model for your use-case. Here are some general recommendations:

codestral model is good for code generation and editing.
mistral-large-latest model is good for most use-cases.
open-mistral-nemo is a free model that is good for most use-cases.
pixtral-12b-2409 is a vision model that is good for OCR, transcribing documents, and image comparison. It is not always capable at tool calling.

Mistral has tier-based rate limits. See the docs for more information.

Authentication

Set your MISTRAL_API_KEY environment variable. Get your key from here.

1export MISTRAL_API_KEY=***

1setx MISTRAL_API_KEY ***

Example

Use Mistral with your Agent:

1import os
2
3from kern.agent import Agent, RunOutput
4from kern.models.mistral import MistralChat
5
6mistral_api_key = os.getenv("MISTRAL_API_KEY")
7
8agent = Agent(
9    model=MistralChat(
10        id="mistral-large-latest",
11        api_key=mistral_api_key,
12    ),
13    markdown=True
14)
15
16# Print the response in the terminal
17agent.print_response("Share a 2 sentence horror story.")

Note View more examples here.

Params

Parameter	Type	Default	Description
`id`	`str`	`"mistral-large-latest"`	The id of the Mistral model to use
`name`	`str`	`"Mistral"`	The name of the model
`provider`	`str`	`"Mistral"`	The provider of the model
`api_key`	`Optional[str]`	`None`	The API key for Mistral (defaults to MISTRAL_API_KEY env var)
`base_url`	`str`	`"https://api.mistral.ai/v1"`	The base URL for the Mistral API
`timeout`	`Optional[int]`	`None`	Request timeout in seconds

MistralChat is a subclass of the Model class and has access to the same params.