Mistral

Use Mistral models with Agno agents.

Mistral provides API endpoints for its 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.
• ministral-14b-2512 supports vision tasks such as OCR, document transcription, and image comparison.

Mistral has tier-based rate limits. See the tier docs.

Installation

uv pip install -U "mistralai>=2.0.0" agno

Agno v3.0 requires mistralai>=2.0.0; the v1 compatibility layer was removed, and the agno[mistral] extra pins the floor. With a 1.x SDK installed, the import fails with the generic `mistralai` not installed message — upgrade the package rather than reinstalling it.

Authentication

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

Mac

export MISTRAL_API_KEY=***

Example

Use MistralChat with your Agent:

agent.py

import os

from agno.agent import Agent
from agno.models.mistral import MistralChat

mistral_api_key = os.getenv("MISTRAL_API_KEY")

agent = Agent(
    model=MistralChat(
        id="mistral-large-latest",
        api_key=mistral_api_key,
    ),
    markdown=True
)

# Print the response in the terminal
agent.print_response("Share a 2 sentence horror story.")

View more examples here.

Params

Parameter	Type	Default	Description
id	str	"mistral-large-latest"	The id of the Mistral model to use
name	str	"MistralChat"	The name of the model
provider	str	"Mistral"	The provider of the model
temperature	Optional[float]	None	Controls randomness in the model’s output
max_tokens	Optional[int]	None	Maximum number of tokens to generate
top_p	Optional[float]	None	Controls diversity via nucleus sampling
random_seed	Optional[int]	None	Random seed for reproducibility
safe_mode	bool	False	Enable safe mode content filtering
safe_prompt	bool	False	Prepend a safety prompt to all requests
request_params	Optional[Dict[str, Any]]	None	Additional parameters for the request
api_key	Optional[str]	None	The API key for Mistral (defaults to MISTRAL_API_KEY env var)
endpoint	Optional[str]	None	Custom endpoint for the Mistral API
max_retries	Optional[int]	None	Maximum number of retries for API requests
timeout	Optional[int]	None	Request timeout in seconds
client_params	Optional[Dict[str, Any]]	None	Additional parameters for client configuration
mistral_client	Optional[Mistral]	None	A pre-configured Mistral client instance to use

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