Responses

Create a model response

POST

/responses

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.infercom.ai/v1',
  apiKey: process.env['INFERCOM_API_KEY'],
});

const response = await client.responses.create({
  model: 'MiniMax-M2.7',
  input: 'Explain supervised vs unsupervised learning.',
});

console.log(response.output_text);

from openai import OpenAI

client = OpenAI(
    base_url="https://api.infercom.ai/v1",
    api_key="your-infercom-api-key",
)

response = client.responses.create(
    model="MiniMax-M2.7",
    input="Explain supervised vs unsupervised learning.",
)

print(response.output_text)

curl -X POST https://api.infercom.ai/v1/responses \
  -H "Authorization: Bearer $INFERCOM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MiniMax-M2.7",
    "input": "Explain supervised vs unsupervised learning."
  }'

Creates a model response for the given input. Designed for agentic workflows with structured output items (messages, reasoning, function calls). Only type: "function" tools are supported. Stateless API - supply full conversation history via input[] on each request.

Authorizations

api_key

Request Body^required

Response creation parameters

application/json

Response Request

Request body for creating a model response.

object

model

required

Model

The model ID to use (e.g., MiniMax-M2.7, gpt-oss-120b).

string

Example

MiniMax-M2.7

input

required

One of:

string
Array

Plain text input (equivalent to a user message).

string

instructions

Instructions

System message prepended to input.

string

nullable

stream

Stream

If true, stream response as Server-Sent Events.

boolean

max_output_tokens

Max Output Tokens

Maximum tokens to generate.

integer

nullable

temperature

Temperature

Randomness control (0-2). No default: omitting this parameter makes most models decode greedily, which behaves like temperature 0. Set it explicitly. See Recommended sampling parameters.

number

<= 2

Example

top_p

Top P

Nucleus sampling cutoff (0-1).

number

<= 1

top_k

Top K

Top-K sampling. Send 1 or greater. top_k has no effect unless temperature is 0.001 or above - below that, including when temperature is omitted, it is forced to 1 and decoding is greedy. When omitted, top_k is 1048576, which is effectively unrestricted. No upper bound is enforced. Note that this endpoint does not validate the lower bound: -1 and 0 return a 200 here but a 400 on /chat/completions and /messages, and they do not mean “unrestricted” on any endpoint.

integer

nullable >= 1

tools

Tools

Function tools available to the model (max 128).

Array<object>

nullable <= 128 items

Response Tool

A function tool definition for the Responses API.

object

type

required

Tool type. Only “function” is supported.

string

Allowed values: function

name

required

The name of the function.

string

description

A description of what the function does.

string

parameters

JSON Schema describing the function parameters.

object

strict

Whether to enforce strict schema validation.

boolean

nullable

tool_choice

One of:

string
object

string

Allowed values: none auto required

parallel_tool_calls

Parallel Tool Calls

Allow multiple tool calls in parallel.

boolean

default: true

text

Text

Response format configuration.

object

format

One of:

ResponseFormatText

Specifies that the model should produce output as plain text.

object

type

required

Type

string

Allowed value: text

Allowed values: text

key

additional properties

any

ResponseFormatJSONObject

Specifies that the model should produce output as a raw JSON object.

object

type

required

Type

string

Allowed value: json_object

Allowed values: json_object

key

additional properties

any

Example

{
  "type": "json_object"
}

ResponseFormatJSONSchema

Specifies that the model should produce output conforming to a given JSON schema.

object

json_schema

required

JSONSchema

A JSON Schema definition the model’s structured output. Follows standard JSON Schema syntax.

object

description

Description

Description the json schema

string

nullable

name

required

Name

Name of the object schema

string

schema

Schema

Actual json schema object

object

strict

Strict

Whether or not to do an strict validation of the schema

boolean

nullable

key

additional properties

any

type

required

Type

string

Allowed value: json_schema

Allowed values: json_schema

key

additional properties

any

Example

{
  "type": "json_schema",
  "json_schema": {
    "name": "User",
    "description": "JSON schema for a simple user object",
    "strict": false,
    "schema": {
      "type": "object",
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier for the user"
        },
        "name": {
          "type": "string",
          "description": "Full name of the user"
        }
      },
      "required": [
        "id",
        "name"
      ]
    }
  }
}

reasoning

Reasoning

Reasoning configuration for supported models.

object

effort

Reasoning depth level.

string

default: medium

Allowed values: low medium high

user

User

User identifier (echoed in response).

string

nullable

Responses

200

Successful response. Returns a ResponseResponse object (non-streaming), or a stream of Server-Sent Events (when stream: true).

application/json

Response Response

Response object from POST /responses.

object

required

Unique response identifier.

string

object

required

Object type, always “response”.

string

Allowed values: response

status

required

Response lifecycle status.

string

Allowed values: completed failed in_progress incomplete

created_at

required

Unix timestamp when created.

integer

completed_at

Unix timestamp when completed.

integer

nullable

model

required

Model ID used.

string

output

required

Output items (messages, reasoning, function calls).

Array

One of: discriminator: type

Response Message

object

type

required

string

Allowed values: message

required

Unique identifier for this message.

string

role

required

string

Allowed values: assistant

status

string

Allowed values: completed in_progress

content

required

Array

One of:

Response Output Text
Response Reasoning Text

Response Output Text

object

type

required

string

Allowed values: output_text

text

required

The text content.

string

annotations

Array<object>

nullable

object

logprobs

Array<object>

nullable

object

usage

Response Usage

Token usage statistics for the response.

object

input_tokens

required

Number of input tokens.

integer

output_tokens

required

Number of output tokens generated.

integer

total_tokens

required

Total tokens (input + output).

integer

input_tokens_details

object

cached_tokens

Tokens served from cache.

integer

output_tokens_details

object

reasoning_tokens

Tokens used for reasoning.

integer

time_to_first_token

Time to first token in seconds.

number

nullable

total_latency

Total generation time in seconds.

number

nullable

output_tokens_per_sec

Output throughput (tokens/second).

number

nullable

error

Error details when status is “failed”.

object

code

string

message

string

instructions

Echoed system instructions.

string

nullable

temperature

number

nullable

top_p

number

nullable

tools

Array<object>

Response Tool

A function tool definition for the Responses API.

object

type

required

Tool type. Only “function” is supported.

string

Allowed values: function

name

required

The name of the function.

string

description

A description of what the function does.

string

parameters

JSON Schema describing the function parameters.

object

strict

Whether to enforce strict schema validation.

boolean

nullable

tool_choice

One of:

string
object

string

Allowed values: none auto required

parallel_tool_calls

boolean

text

object

format

One of:

ResponseFormatText

Specifies that the model should produce output as plain text.

object

type

required

Type

string

Allowed value: text

Allowed values: text

key

additional properties

any

reasoning

object

effort

string

nullable

Allowed values: low medium high

summary

string

nullable

store

Always false (stateless API).

boolean

service_tier

string

nullable

Example

{
  "id": "resp_abc123",
  "object": "response",
  "status": "completed",
  "created_at": 1778845598,
  "completed_at": 1778845598,
  "model": "MiniMax-M2.7",
  "output": [
    {
      "type": "reasoning",
      "id": "rs_xyz",
      "status": "completed",
      "summary": [],
      "content": [
        {
          "type": "reasoning_text",
          "text": "The user asks a simple question..."
        }
      ]
    },
    {
      "type": "message",
      "id": "msg_xyz",
      "role": "assistant",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "text": "2 + 2 = 4."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 45,
    "output_tokens": 89,
    "total_tokens": 134,
    "output_tokens_details": {
      "reasoning_tokens": 77
    }
  },
  "parallel_tool_calls": true,
  "tools": [],
  "store": false
}

Headers

inference-id

string

Example

a0b08d8a-1893-45d6-a0f4-7ad6fdeb5443

Unique identifier for this inference request, useful for debugging and support.

x-ratelimit-limit-requests

integer

Example

Maximum requests allowed per minute.

x-ratelimit-limit-requests-day

integer

Example

Maximum requests allowed per day.

x-ratelimit-remaining-requests

integer

Example

Remaining requests in the current minute window.

x-ratelimit-remaining-requests-day

integer

Example

Remaining requests in the current day.

x-ratelimit-reset-requests

integer

Example

1776937132

Unix timestamp when the per-minute limit resets.

x-ratelimit-reset-requests-day

integer

Example

1777023472

Unix timestamp when the daily limit resets.

400

Bad Request - Missing or invalid parameters

application/json

GeneralError

Other kind of errors

object

error

required

object

code

code

Error code

string

nullable

message

message

Error message

string

param

param

Error params

string

nullable

type

type

Error type

string

request_id

request_id

Unique identifier for the request. Quote it in any support report. Absent on the two responses that use the flat error shape.

string

Examples

Required field missing

{
  "error": {
    "message": "Missing required field: 'input'.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "missing_required_field"
  }
}

Model not supported for Responses API

{
  "error": {
    "message": "Unsupported model DeepSeek-V3.1 on Response API",
    "type": "invalid_request_error",
    "code": "unsupported_model"
  }
}

Built-in tools not supported

{
  "error": {
    "message": "built-in/server-side tools are not supported; only \"function\" type tools are accepted",
    "type": "invalid_request_error",
    "code": "unsupported_tool_type"
  }
}

401

Unauthorized - Invalid or missing API key

application/json

GeneralError

Other kind of errors

object

error

required

object

code

code

Error code

string

nullable

message

message

Error message

string

param

param

Error params

string

nullable

type

type

Error type

string

request_id

request_id

Unique identifier for the request. Quote it in any support report. Absent on the two responses that use the flat error shape.

string

Example^generated

{
  "error": {
    "code": "example",
    "message": "example",
    "param": "example",
    "type": "example"
  },
  "request_id": "example"
}

404

Not found - Model does not exist

application/json

GeneralError

Other kind of errors

object

error

required

object

code

code

Error code

string

nullable

message

message

Error message

string

param

param

Error params

string

nullable

type

type

Error type

string

request_id

request_id

Unique identifier for the request. Quote it in any support report. Absent on the two responses that use the flat error shape.

string

Example^generated

{
  "error": {
    "code": "example",
    "message": "example",
    "param": "example",
    "type": "example"
  },
  "request_id": "example"
}

410

Gone - the model has been deprecated and removed. Returns the envelope, but with type and code both set to internal_error rather than model_deprecated. The condition is permanent despite that type - change the model ID rather than retrying.

application/json

GeneralError

Other kind of errors

object

error

required

object

code

code

Error code

string

nullable

message

message

Error message

string

param

param

Error params

string

nullable

type

type

Error type

string

request_id

request_id

Unique identifier for the request. Quote it in any support report. Absent on the two responses that use the flat error shape.

string

Example

{
  "error": {
    "code": "internal_error",
    "message": "The requested model (MiniMax-M2.5) is not available on SambaNova Cloud.",
    "param": null,
    "type": "internal_error"
  },
  "request_id": "d95bc20b79214a2fb7bbd8fe1712754c"
}

429

Too Many Requests - Rate limit exceeded

application/json

GeneralError

Other kind of errors

object

error

required

object

code

code

Error code

string

nullable

message

message

Error message

string

param

param

Error params

string

nullable

type

type

Error type

string

request_id

request_id

Unique identifier for the request. Quote it in any support report. Absent on the two responses that use the flat error shape.

string

Example^generated

{
  "error": {
    "code": "example",
    "message": "example",
    "param": "example",
    "type": "example"
  },
  "request_id": "example"
}

500

Internal Server Error

text/plain

string

Create a model response

Authorizations

Request Bodyrequired

Example

Example

Example

Example

Responses

200

Example

Headers

Example

Example

Example

Example

Example

Example

Example

400

Examples

401

Examplegenerated

404

Examplegenerated

410

Example

429

Examplegenerated

500

Request Body^required

Example^generated

Example^generated

Example^generated