curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "MiniMax-M3.1-Flash",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself."
    }
  ],
  "max_completion_tokens": 131072
}
'

{
  "id": "072514edea627212c7e226a55bcf4e2e",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "0.05",
        "role": "assistant",
        "name": "MiniMax AI",
        "audio_content": "",
        "reasoning_content": "Let the ball cost x. Then 2x + 1 = 1.10, so x = 0.05."
      }
    }
  ],
  "created": 1792401901,
  "model": "MiniMax-M3.1-Flash",
  "object": "chat.completion",
  "usage": {
    "total_tokens": 281,
    "total_characters": 0,
    "prompt_tokens": 229,
    "completion_tokens": 52,
    "completion_tokens_details": {
      "reasoning_tokens": 49
    },
    "prompt_tokens_details": {
      "cached_tokens": 187
    }
  },
  "input_sensitive": false,
  "output_sensitive": false,
  "input_sensitive_type": 0,
  "output_sensitive_type": 0,
  "output_sensitive_int": 0,
  "base_resp": {
    "status_code": 0,
    "status_msg": ""
  }
}

Chat Completions API

MiniMax-M3.1-Flash - OpenAI-Compatible API

Call MiniMax-M3.1-Flash using the OpenAI Chat Completions protocol
Conversations: single-turn and multi-turn conversations
System prompts: set the assistant’s role and behavior with role=system
Multimodal input: combine text, images, and video in content
Reasoning: always enabled; adjust depth with reasoning_effort. Reasoning is returned in reasoning_content; content contains only the final answer
Streaming: SSE responses
Tool calling: Function Calling

Streaming responses: With stream=true, each SSE message uses the format data: {JSON}, followed by data: [DONE] at the end. choices[].delta returns incremental reasoning_content, then content / tool_calls. Set stream_options.include_usage=true to receive an additional chunk containing usage before the stream ends.

POST

chat

completions

curl --request POST \
  --url https://direct.evolink.ai/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "MiniMax-M3.1-Flash",
  "messages": [
    {
      "role": "user",
      "content": "Please introduce yourself."
    }
  ],
  "max_completion_tokens": 131072
}
'

{
  "id": "072514edea627212c7e226a55bcf4e2e",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "0.05",
        "role": "assistant",
        "name": "MiniMax AI",
        "audio_content": "",
        "reasoning_content": "Let the ball cost x. Then 2x + 1 = 1.10, so x = 0.05."
      }
    }
  ],
  "created": 1792401901,
  "model": "MiniMax-M3.1-Flash",
  "object": "chat.completion",
  "usage": {
    "total_tokens": 281,
    "total_characters": 0,
    "prompt_tokens": 229,
    "completion_tokens": 52,
    "completion_tokens_details": {
      "reasoning_tokens": 49
    },
    "prompt_tokens_details": {
      "cached_tokens": 187
    }
  },
  "input_sensitive": false,
  "output_sensitive": false,
  "input_sensitive_type": 0,
  "output_sensitive_type": 0,
  "output_sensitive_int": 0,
  "base_resp": {
    "status_code": 0,
    "status_msg": ""
  }
}

BaseURL: The default BaseURL is 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

Authorization

string

header

required

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

application/json

model

enum<string>

required

Chat model name

Available options:

MiniMax-M3.1-Flash

Example:

"MiniMax-M3.1-Flash"

messages

(System Message · object | User Message · object | Assistant Message · object | Tool Message · object)[]

required

List of conversation messages, supports multi-turn dialogue

Messages with different roles have different field structures; select the corresponding role to view

Minimum array length: 1

System Message
User Message
Assistant Message
Tool Message

Show child attributes

reasoning_effort

enum<string>

default:max

Reasoning depth. Defaults to max. Higher levels typically increase reasoning token usage and response time.

Available options:

low,

medium,

high,

xhigh,

max

Example:

"high"

thinking

object

Reasoning mode. MiniMax-M3.1-Flash always uses reasoning. Only adaptive is supported; this field may be omitted.

Show child attributes

reasoning_split

enum<boolean>

default:true

Return reasoning separately. Only true is supported. Reasoning is returned in reasoning_content; this field may be omitted.

Available options:

true

temperature

number

default:1

Sampling temperature controls output randomness.

Range: [0, 2]; default: 1
Lower values produce more deterministic output; higher values produce more varied output

Adjust either temperature or top_p, rather than both.

Required range: 0 <= x <= 2

Example:

1

top_p

number

default:0.95

Nucleus sampling threshold.

Samples from tokens whose cumulative probability reaches this threshold
For example, 0.95 samples from tokens accounting for 95% of the probability mass
Range: [0, 1]; default: 0.95

Adjust either temperature or top_p, rather than both.

Required range: 0 <= x <= 1

Example:

0.95

max_completion_tokens

integer

Maximum number of generated tokens, including reasoning and the final answer.

Recommended: 131,072 (128K); maximum: 524,288 (512K)
A small budget may be exhausted during reasoning, resulting in finish_reason=length and an empty content field

Required range: 1 <= x <= 524288

Example:

131072

stream

boolean

default:false

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)

Example:

false

stream_options

object

Streaming response options

Only effective when stream=true

Show child attributes

tools

object[]

Tool definition list for Function Calling

Each tool requires a name, description, and parameter schema

Show child attributes

tool_choice

enum<string>

default:auto

Tool selection strategy. Only auto is supported; the model decides whether to call a tool.

Available options:

auto

max_tokens

integer

deprecated

Legacy generation length limit parameter

Note: Deprecated, please use max_completion_tokens instead

Required range: x >= 1

enum<integer>

default:1

Number of responses to generate. Only 1 is supported.

Available options:

1

Response

Conversation generated successfully

string

Unique identifier for the chat completion

Example:

"0668a381bdc3c0ded310e27c9a46d16e7"

model

string

Model name actually used

Example:

"MiniMax-M3.1-Flash"

object

enum<string>

Response type

Available options:

chat.completion

Example:

"chat.completion"

created

integer

Creation timestamp (Unix seconds)

Example:

1777026807

choices

object[]

List of chat completion choices

Show child attributes

usage

object

Token usage statistics

Show child attributes

input_sensitive

boolean

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

input_sensitive_type

integer

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

output_sensitive

boolean

Whether the output content triggered a sensitive word filter

output_sensitive_type

integer

Type of sensitive word triggered by output

base_resp

object

Status code and error details

Show child attributes

output_sensitive_int

integer

Numeric identifier for the output content sensitivity category.

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

MiniMax-M3.1-Flash - OpenAI-Compatible API

Authorizations

Body

Response