MiniMax

MiniMax exposes its text models through an OpenAI-compatible API, so you can drive them through Agno the same way you'd drive any OpenAI-compatible provider. The Agno MiniMax class defaults to MiniMax-M2.7 and points at the international endpoint https://api.minimax.io/v1.

1. Create and activate a virtual environment

See the repository Development setup.

2. Export your API key

shell

export MINIMAX_API_KEY=***

Create an API key from the MiniMax platform dashboard.

3. Install libraries

shell

uv pip install -U openai agno

4. Run the basic example

shell

python cookbook/90_models/minimax/basic.py

Available models

The OpenAI-compatible endpoint exposes the M2 family — see the models intro for the current catalog. As of writing:

Model id	Notes
`MiniMax-M2.7`	Flagship MoE (230B total / 10B active), 205k context
`MiniMax-M2.7-highspeed`	Same weights as M2.7, ~1.6–1.7× throughput
`MiniMax-M2.5`	Previous flagship
`MiniMax-M2.5-highspeed`	Higher-throughput variant of M2.5
`MiniMax-M2.1`, `MiniMax-M2.1-highspeed`, `MiniMax-M2`	Earlier releases

Pass any of these as MiniMax(id="..."):

python

from agno.agent import Agent
from agno.models.minimax import MiniMax

agent = Agent(model=MiniMax(id="MiniMax-M2.7-highspeed"))

Tool use

shell

python cookbook/90_models/minimax/tool_use.py

Structured output

MiniMax does not implement OpenAI-style native response_format / strict json_schema, so the Agno class sets supports_native_structured_outputs = False. Use use_json_mode=True on the agent for Pydantic-shaped output:

python

agent = Agent(
    model=MiniMax(id="MiniMax-M2.7"),
    output_schema=MovieScript,
    use_json_mode=True,
)

A full example lives in structured_output.py.

Custom base URL

If you need to hit a different host (private deployment, regional endpoint, etc.), pass base_url:

python

MiniMax(id="MiniMax-M2.7", base_url="https://your-host.example.com/v1")