Skip to main content
POST
/
v1
/
responses
curl --request POST \
  --url https://api.minimax.io/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "model": "MiniMax-M3",
  "input": "Hello!"
}
'
{
  "id": "abc123",
  "object": "response",
  "created_at": 1764000000,
  "model": "MiniMax-M3",
  "status": "completed",
  "output": [
    {
      "id": "abc123_msg",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Hello! I'm MiniMax. How can I help you today?",
          "annotations": []
        }
      ]
    }
  ],
  "output_text": "Hello! I'm MiniMax. How can I help you today?",
  "usage": {
    "input_tokens": 8,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 14,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 22
  },
  "parallel_tool_calls": true,
  "store": false,
  "truncation": "disabled"
}

​
Reasoning Control

For MiniMax-M3, the reasoning field controls whether the response can include reasoning output.
  • If reasoning is omitted, reasoning is on by default and the response includes an output item with type: "reasoning".
  • Set reasoning: {"effort": "none"} to disable reasoning output for MiniMax-M3.
  • Values minimal, low, medium, and high are accepted for compatibility and keep reasoning enabled, but they do not tune MiniMax-M3’s reasoning depth.
  • For M2.x models, reasoning cannot be disabled; reasoning: {"effort": "none"} is accepted but reasoning remains on.
{
  "model": "MiniMax-M3",
  "input": "Which is larger, 9.11 or 9.9?"
}

{
  "model": "MiniMax-M3",
  "input": "Which is larger, 9.11 or 9.9?",
  "reasoning": {
    "effort": "none"
  }
}

Authorizations

​
Authorization
string
header
required

HTTP: Bearer Auth

  • Security Scheme Type: http
  • HTTP Authorization Scheme: Bearer API_key, used to authenticate your account. View it in Account Management > API Keys

Headers

​
Content-Type
enum<string>
default:application/json
required

Media type of the request body. Must be set to application/json

Available options:
application/json

Body

application/json
​
model
string
required

Model name to invoke, e.g. MiniMax-M3

Example:

"MiniMax-M3"

​
input
required

Conversation content. Supports either a simple text or a full conversation history array

​
instructions
string

System instructions

​
max_output_tokens
integer

Maximum output token count

​
temperature
number<float>
default:1

Sampling temperature, range (0, 1]

Required range: 0 <= x <= 1
​
top_p
number<float>
default:0.95

Nucleus sampling, range (0, 1]

Required range: 0 <= x <= 1
​
stream
boolean
default:false

Set to true to enable SSE streaming response

​
tools
object[]

Tool list

​
tool_choice
enum<string>

Tool selection strategy: none means no tool will be called; auto lets the model decide whether to call tools

Available options:
none,
auto
​
metadata
object

Request metadata. Both keys and values are strings

​
prompt_cache_key
string

Prompt cache routing identifier

​
text
object

Output format control

​
reasoning
object

Reasoning control. For MiniMax-M3, reasoning is on by default and responses include a reasoning output item. Set effort to none to disable MiniMax-M3 reasoning output. The minimal, low, medium, and high values are accepted for compatibility and keep reasoning enabled; they do not tune MiniMax-M3's reasoning depth. For M2.x models, reasoning cannot be disabled.

Response

200 - application/json

Successful response

​
id
string
required

Response ID

Example:

"abc123"

​
object
enum<string>
required

Object type, always response

Available options:
response
​
created_at
integer
required

Response creation time (Unix seconds)

​
model
string
required

Actual model that processed the request

​
status
enum<string>
required

Response status

Available options:
completed,
incomplete,
failed
​
output
(Message · object | Reasoning · object | Function Call · object)[]
required

Model output list

Assistant reply

​
output_text
string | null

Convenience field. Concatenation of all text outputs

​
usage
object
​
error
object

Error info, only returned when status=failed

​
incomplete_details
object

Reason for incompletion, only returned when status=incomplete

​
parallel_tool_calls
boolean

Whether parallel tool calls are supported

​
store
boolean

Whether the response is persisted

​
truncation
enum<string>

Context truncation strategy

Available options:
disabled