curl --request POST \
  --url https://direct.evolink.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "MiniMax-M3.1-Flash",
  "input": "Explain recursion in one sentence.",
  "max_output_tokens": 131072
}
'

{
  "id": "0725233a85e23431681447327cbcd9d2",
  "object": "response",
  "created_at": 1792405562,
  "model": "MiniMax-M3.1-Flash",
  "status": "completed",
  "output": [
    {
      "id": "0725233a85e23431681447327cbcd9d2_rs",
      "type": "reasoning",
      "status": "completed",
      "summary": [],
      "content": [
        {
          "type": "reasoning_text",
          "text": "We need solve CRT. Need only n. Compute. n=3 mod7, 5 mod11,7 mod13. Product 1001. Let's solve.\n\nUse n=3+7a. mod11: 3+7a=5 =>7a=2 mod11. inverse7=8 (56=1), a=16=5 mod11. a=5+11b. n=38+77b. mod13: 38+77b = 12+12b mod13 (77=12,38=12) equals7 =>12b=-5=8 mod13. inverse12=12, b=96 mod13 =5? 91 remainder5. n=38+385=423. Check 423 mod7 3 (420), mod11 5 (418), mod13 7 (416). Smallest positive 423. Only n."
        }
      ],
      "encrypted_content": "Ahlub3JtYWwtcmVhc29uaW5nLTIwMjYxMDExjehfvIf2rUinmic9ZiAutly0DD3lHqWEni9ENDziUw0nX-F6VPZLM7x1NbRWbytJNcLH9XQIa-KLYgd-it6XmXzYLvck3xOPOG9wtDdxUnjdBhuuj9dkWrkx0kbK8MFT5UreZ7EcxoRZybrs3oELf2BK_WtDUFOm_FbZXKwNbg76pTCFDoRke0Er0GMWjmi5L8GE7hGnvvBQjHXrwQ88G0L2p6STay-n1FJ5prqz6Q4LEF-xu7FqGjDmh9haliI638ivcQ9XGo9_DLUrtKMh1K4UYN87j2H7vbjbJPJaw6oJ61ZF8Ngk1FSuHUvLB540QKwBJKnClMcvw-ih3CdKRdSTPRfIYlsYOkNCwEWrLwHarLTHG5HzeakMO_5usxOAvzXVDUKRIX7W62x9xKCnVl_Gp0E91dLtlU3U8j_ZZvYCj9pMvd_n_Ba82OUpFxvoXv2R2H1H8bfzztGg5E88fH6OMwoMS5OYa45nCoRFA11Bw7G8OEVqBiPzS48EY1JPjPTC5lBco0CUoeUAHPXeD7jmO-D3LhIL1-3erJ_mxP0ZeiCWUckYaFE2EliolooAHqkoVBmy5Q"
    },
    {
      "id": "0725233a85e23431681447327cbcd9d2_msg",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "423",
          "annotations": []
        }
      ]
    }
  ],
  "output_text": "423",
  "usage": {
    "input_tokens": 239,
    "output_tokens": 190,
    "total_tokens": 429,
    "input_tokens_details": {
      "cached_tokens": 174
    },
    "output_tokens_details": {
      "reasoning_tokens": 189
    }
  },
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {},
  "tools": null,
  "tool_choice": "auto",
  "temperature": 1,
  "top_p": 0.95,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "max_output_tokens": 2048,
  "max_tool_calls": null,
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "conversation": null,
  "store": false,
  "service_tier": null,
  "safety_identifier": null,
  "truncation": "disabled"
}

Responses API

MiniMax-M3.1-Flash - Responses API

Call MiniMax-M3.1-Flash using the OpenAI Responses protocol
Input: input accepts plain text or an array of input items (messages, function calls, and function results)
Multimodal input: combine input_text, input_image, and input_video blocks in message content
System instructions: use instructions, equivalent to an initial system message
Reasoning: always enabled; adjust depth with reasoning.effort. Reasoning is returned as reasoning output items
Streaming: semantic SSE events ending with response.completed, without a [DONE] marker
Tool calling: Function Calling
Context caching: matching prefixes are cached automatically; cached tokens are reported in usage.input_tokens_details.cached_tokens

Stateless requests: Responses are not stored and previous_response_id is not supported. For each turn, append every item from the previous output to input in its original order, preserving all fields, including content, summary, and encrypted_content in reasoning items. After executing a tool, append a function_call_output item with the same call_id as the function call.

Streaming events: response.created, response.in_progress, response.output_item.added, response.content_part.added, response.reasoning_text.delta / response.reasoning_text.done, response.output_text.delta / response.output_text.done, response.content_part.done, and response.output_item.done, ending with response.completed. Each event includes a sequence_number for ordering.

POST

responses

curl --request POST \
  --url https://direct.evolink.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "MiniMax-M3.1-Flash",
  "input": "Explain recursion in one sentence.",
  "max_output_tokens": 131072
}
'

{
  "id": "0725233a85e23431681447327cbcd9d2",
  "object": "response",
  "created_at": 1792405562,
  "model": "MiniMax-M3.1-Flash",
  "status": "completed",
  "output": [
    {
      "id": "0725233a85e23431681447327cbcd9d2_rs",
      "type": "reasoning",
      "status": "completed",
      "summary": [],
      "content": [
        {
          "type": "reasoning_text",
          "text": "We need solve CRT. Need only n. Compute. n=3 mod7, 5 mod11,7 mod13. Product 1001. Let's solve.\n\nUse n=3+7a. mod11: 3+7a=5 =>7a=2 mod11. inverse7=8 (56=1), a=16=5 mod11. a=5+11b. n=38+77b. mod13: 38+77b = 12+12b mod13 (77=12,38=12) equals7 =>12b=-5=8 mod13. inverse12=12, b=96 mod13 =5? 91 remainder5. n=38+385=423. Check 423 mod7 3 (420), mod11 5 (418), mod13 7 (416). Smallest positive 423. Only n."
        }
      ],
      "encrypted_content": "Ahlub3JtYWwtcmVhc29uaW5nLTIwMjYxMDExjehfvIf2rUinmic9ZiAutly0DD3lHqWEni9ENDziUw0nX-F6VPZLM7x1NbRWbytJNcLH9XQIa-KLYgd-it6XmXzYLvck3xOPOG9wtDdxUnjdBhuuj9dkWrkx0kbK8MFT5UreZ7EcxoRZybrs3oELf2BK_WtDUFOm_FbZXKwNbg76pTCFDoRke0Er0GMWjmi5L8GE7hGnvvBQjHXrwQ88G0L2p6STay-n1FJ5prqz6Q4LEF-xu7FqGjDmh9haliI638ivcQ9XGo9_DLUrtKMh1K4UYN87j2H7vbjbJPJaw6oJ61ZF8Ngk1FSuHUvLB540QKwBJKnClMcvw-ih3CdKRdSTPRfIYlsYOkNCwEWrLwHarLTHG5HzeakMO_5usxOAvzXVDUKRIX7W62x9xKCnVl_Gp0E91dLtlU3U8j_ZZvYCj9pMvd_n_Ba82OUpFxvoXv2R2H1H8bfzztGg5E88fH6OMwoMS5OYa45nCoRFA11Bw7G8OEVqBiPzS48EY1JPjPTC5lBco0CUoeUAHPXeD7jmO-D3LhIL1-3erJ_mxP0ZeiCWUckYaFE2EliolooAHqkoVBmy5Q"
    },
    {
      "id": "0725233a85e23431681447327cbcd9d2_msg",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "423",
          "annotations": []
        }
      ]
    }
  ],
  "output_text": "423",
  "usage": {
    "input_tokens": 239,
    "output_tokens": 190,
    "total_tokens": 429,
    "input_tokens_details": {
      "cached_tokens": 174
    },
    "output_tokens_details": {
      "reasoning_tokens": 189
    }
  },
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {},
  "tools": null,
  "tool_choice": "auto",
  "temperature": 1,
  "top_p": 0.95,
  "text": {
    "format": {
      "type": "text"
    }
  },
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "max_output_tokens": 2048,
  "max_tool_calls": null,
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "conversation": null,
  "store": false,
  "service_tier": null,
  "safety_identifier": null,
  "truncation": "disabled"
}

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

Model ID.

Available options:

MiniMax-M3.1-Flash

Example:

"MiniMax-M3.1-Flash"

input

required

Model input.

String: treated as a single user message
Array: input items of type message, function_call, function_call_output, or reasoning

Multimodal input: combine input_text, input_image, and input_video blocks in message content.

Conversation history: requests are stateless. Include the complete history in the array for each turn.

Example:

"Explain recursion in one sentence."

instructions

string

System-level instructions, equivalent to a system message inserted at the very front; used to set the role, tone and output constraints.

Example:

"You are a technical documentation assistant. Keep your answers concise."

stream

boolean

default:false

Whether to stream the response.

false (default): return the complete response at once
true: send semantic SSE events ending with response.completed, without a [DONE] marker

Example:

false

max_output_tokens

integer

Maximum output 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 status: "incomplete" without a message output item

Required range: 1 <= x <= 524288

Example:

131072

reasoning

object

Reasoning configuration. MiniMax-M3.1-Flash always uses reasoning, returned as reasoning output items. Reasoning tokens count toward the output budget and are billed at the output rate.

Show child attributes

temperature

enum<number>

default:1

Sampling temperature. Fixed at 1.

Available options:

1

Example:

1

top_p

number

default:0.95

Nucleus sampling threshold. Defaults to 0.95.

Required range: 0 <= x <= 1

Example:

0.95

tools

Tool definition · object[]

Tools available to the model. Only function tools are supported. Execute the function on the client and return its result as a function_call_output input item.

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

Example:

"auto"

text

object

Text output format configuration. format.type only supports text.

Show child attributes

metadata

object

Request metadata. Keys and values must be strings.

Show child attributes

Response

Generated successfully

Responses API response object. In addition to the fields below, the response includes the request configuration, such as tools, tool_choice, temperature, top_p, text, reasoning, and max_output_tokens.

string

Unique identifier for this response

Example:

"072514d63605b7a0c83f1672230c398c"

object

string

Object type, always response

Example:

"response"

created_at

integer

Creation time as a Unix timestamp (seconds)

Example:

1792401878

status

enum<string>

Response status.

completed: generation completed
incomplete: generation was truncated; see incomplete_details
failed: generation failed; see error

Available options:

completed,

incomplete,

failed

Example:

"completed"

model

string

ID of the model that actually generated this response

Example:

"MiniMax-M3.1-Flash"

output

object[]

Output items in generation order:

reasoning: reasoning content, with an ID such as <id>_rs, content (reasoning_text blocks), summary (an empty array), and encrypted_content
message: final answer, with an ID such as <id>_msg and content (output_text blocks)
function_call: a function call, with an ID such as <id>_fc_<index>, call_id, name, and arguments. Execute it on the client and return a function_call_output item

output_text

string | null

Convenience field containing all output_text blocks concatenated. null when there is no text output.

error

object | null

Failure reason; null on success

incomplete_details

object | null

Truncation details, or null if generation was not truncated. reason is max_output_tokens (output limit reached) or content_filter (content safety).

usage

object

Token usage statistics, including caching and reasoning details.

Show child attributes

Image Series

Video Series

Audio Series

Text Series

Account Management

Task Management

File Management

MiniMax-M3.1-Flash - Responses API

Authorizations

Body

Response