Create chat completion
Generate a response from a conversation.
Authorizations
Modular Cloud API key. Obtain from the API keys page.
Body
Model identifier. See the supported models page.
"minimax/minimax-m3"
List of functions the model may call. To check whether a model supports function calling, open it in the console and review the Model specs.
Controls when and how the model calls a tool.
none: Disables tool calls.auto(default): Lets the model decide whether to call a tool.required: Forces the model to call at least one tool.- A function object: Forces the model to call the named function.
The following example requires the model to call the get_weather function:
none, auto, required Format that the model's response must follow. Omit it to return plain text. All text generation models support structured output.
See structured output for examples.
Controls whether the model generates chain-of-thought reasoning before responding. To check whether a model supports reasoning, open it in the console and review the Model specs.
We also support an equivalent thinking parameter. Use whichever format your client or model expects.
Controls how much reasoning the model performs. Shorthand for reasoning.effort. If both are set, reasoning.effort takes precedence.
To check whether a model supports reasoning, open it in the console and review the Model specs.
low, medium, high Response
Chat completion response.