curl --request POST \
--url https://direct.evolink.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "MiniMax-M3",
"messages": [
{
"role": "user",
"content": "Please introduce yourself"
}
]
}
'{
"id": "066b36619b147e326d17053cccdef70f",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "<think>\nThe user is asking about the capital of France, which is a common knowledge question. The answer is Paris.\n</think>\nThe capital of France is **Paris**.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1777026807,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 60,
"total_characters": 0,
"prompt_tokens": 7,
"completion_tokens": 53,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}MiniMax-M3 - OpenAI-Compatible API
- Use the OpenAI Chat Completions protocol to call the MiniMax-M3 model
- Multi-turn conversation: Supports single-turn or multi-turn contextual dialogue
- System prompts: Customize AI role and behavior via
role=systemmessages - Multimodal input:
contentsupports mixed text + image / video - Thinking mode: Controlled via
thinking.type; thinking content is returned viareasoning_content - Streaming output: Supports SSE streaming responses
- Tool calling: Supports Function Calling
curl --request POST \
--url https://direct.evolink.ai/v1/chat/completions \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '
{
"model": "MiniMax-M3",
"messages": [
{
"role": "user",
"content": "Please introduce yourself"
}
]
}
'{
"id": "066b36619b147e326d17053cccdef70f",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "<think>\nThe user is asking about the capital of France, which is a common knowledge question. The answer is Paris.\n</think>\nThe capital of France is **Paris**.",
"role": "assistant",
"name": "MiniMax AI",
"audio_content": ""
}
}
],
"created": 1777026807,
"model": "MiniMax-M3",
"object": "chat.completion",
"usage": {
"total_tokens": 60,
"total_characters": 0,
"prompt_tokens": 7,
"completion_tokens": 53,
"prompt_tokens_details": {
"cached_tokens": 0
}
},
"input_sensitive": false,
"output_sensitive": false,
"input_sensitive_type": 0,
"output_sensitive_type": 0,
"base_resp": {
"status_code": 0,
"status_msg": ""
}
}https://direct.evolink.ai, which has better support for text models and long-lived connections. https://api.evolink.ai is the primary endpoint for multimodal services and serves as a fallback address for text models.Authorizations
##All APIs require Bearer Token authentication##
Get API Key:
Visit API Key Management Page to get your API Key
Add to request header:
Authorization: Bearer YOUR_API_KEY
Body
Chat model name
MiniMax-M3 "MiniMax-M3"
List of conversation messages, supports multi-turn dialogue
Messages with different roles have different field structures; select the corresponding role to view
1- System Message
- User Message
- Assistant Message
- Tool Message
Show child attributes
Show child attributes
Controls deep thinking
Notes:
- Defaults to
adaptive: The model adaptively decides whether to engage in deep thinking based on problem difficulty - By default, thinking content is inlined in the response
content(wrapped in<think>...</think>tags); to separate it into a dedicated field, usereasoning_split
Show child attributes
Show child attributes
Whether to split thinking content into a separate field
false(default): Thinking content is inlined incontent, wrapped in<think>...</think>tagstrue: Thinking content is split intochoices[].message.reasoning_contentandreasoning_details
Sampling temperature, controls output randomness
Notes:
- Lower values (e.g. 0.2): More deterministic, focused output
- Higher values (e.g. 1.5): More random, creative output
- Range:
[0, 2], default 1
0 <= x <= 21
Nucleus Sampling parameter
Notes:
- Controls sampling from tokens with cumulative probability
- e.g. 0.95 means selecting from tokens reaching 95% cumulative probability
- Range:
[0, 1], MiniMax-M3 default 0.95
Recommendation: Do not adjust temperature and top_p simultaneously
0 <= x <= 10.95
Upper limit for generated content length (in tokens)
Notes:
- MiniMax-M3 recommended 131,072 (128K), maximum 524,288 (512K)
- Tokens generated by thinking also count toward this limit
- If generation is interrupted due to
length, try increasing this value
1 <= x <= 524288131072
Whether to return the response in streaming mode
true: Streaming response, returns content in real-time chunks via SSE (Server-Sent Events)false: Wait for complete response before returning (default)
false
Streaming response options
Only effective when stream=true
Show child attributes
Show child attributes
Tool definition list for Function Calling
Each tool requires a name, description, and parameter schema
Show child attributes
Show child attributes
Legacy generation length limit parameter
Note: Deprecated, please use max_completion_tokens instead
x >= 1Response
Chat completion successful
Unique identifier for the chat completion
"0668a381bdc3c0ded310e27c9a46d16e7"
Model name actually used
"MiniMax-M3"
Response type
chat.completion "chat.completion"
Creation timestamp (Unix seconds)
1777026807
List of chat completion choices
Show child attributes
Show child attributes
Token usage statistics
Show child attributes
Show child attributes
Whether the input content triggered a sensitive word filter. If the input severely violates policies, the API will return a content violation error with empty response content
Type of sensitive word triggered by input (returned when input_sensitive is true): 1 severe violation; 2 pornography; 3 advertising; 4 prohibited content; 5 abusive language; 6 violence/terrorism; 7 other
Whether the output content triggered a sensitive word filter
Type of sensitive word triggered by output
Status code and error details
Show child attributes
Show child attributes