Create a model response

JavaScript

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."
  }'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.infercom.ai/v1/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'MiniMax-M2.7',
    'input' => '<string>',
    'instructions' => '<string>',
    'stream' => false,
    'max_output_tokens' => 123,
    'temperature' => 0.7,
    'top_p' => 1,
    'top_k' => 50,
    'tools' => [
        [
                'type' => 'function',
                'name' => '<string>',
                'description' => '<string>',
                'parameters' => [
                                
                ],
                'strict' => true
        ]
    ],
    'parallel_tool_calls' => true,
    'text' => [
        'format' => [
                'type' => 'text'
        ]
    ],
    'reasoning' => [
        'effort' => 'medium'
    ],
    'user' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.infercom.ai/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.infercom.ai/v1/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infercom.ai/v1/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "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
}

POST

responses

JavaScript

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."
  }'

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.infercom.ai/v1/responses",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'model' => 'MiniMax-M2.7',
    'input' => '<string>',
    'instructions' => '<string>',
    'stream' => false,
    'max_output_tokens' => 123,
    'temperature' => 0.7,
    'top_p' => 1,
    'top_k' => 50,
    'tools' => [
        [
                'type' => 'function',
                'name' => '<string>',
                'description' => '<string>',
                'parameters' => [
                                
                ],
                'strict' => true
        ]
    ],
    'parallel_tool_calls' => true,
    'text' => [
        'format' => [
                'type' => 'text'
        ]
    ],
    'reasoning' => [
        'effort' => 'medium'
    ],
    'user' => '<string>'
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.infercom.ai/v1/responses"

	payload := strings.NewReader("{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.infercom.ai/v1/responses")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infercom.ai/v1/responses")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"MiniMax-M2.7\",\n  \"input\": \"<string>\",\n  \"instructions\": \"<string>\",\n  \"stream\": false,\n  \"max_output_tokens\": 123,\n  \"temperature\": 0.7,\n  \"top_p\": 1,\n  \"top_k\": 50,\n  \"tools\": [\n    {\n      \"type\": \"function\",\n      \"name\": \"<string>\",\n      \"description\": \"<string>\",\n      \"parameters\": {},\n      \"strict\": true\n    }\n  ],\n  \"parallel_tool_calls\": true,\n  \"text\": {\n    \"format\": {\n      \"type\": \"text\"\n    }\n  },\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  },\n  \"user\": \"<string>\"\n}"

response = http.request(request)
puts response.read_body

{
  "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
}

Authorizations

Authorization

string

header

required

Infercom API Key

Body

application/json

Response creation parameters

Request body for creating a model response.

model

string

required

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

Example:

"MiniMax-M2.7"

input

required

Plain text input (equivalent to a user message).

instructions

string | null

System message prepended to input.

stream

boolean

default:false

If true, stream response as Server-Sent Events.

max_output_tokens

integer | null

Maximum tokens to generate.

temperature

number

default:0.7

Randomness control (0-2).

Required range: 0 <= x <= 2

top_p

number

default:1

Nucleus sampling cutoff (0-1).

Required range: 0 <= x <= 1

top_k

integer | null

Top-K sampling (1-100).

Required range: 1 <= x <= 100

tools

Response Tool · object[] | null

Function tools available to the model (max 128).

Maximum array length: 128

Show child attributes

tool_choice

Controls how the model uses tools.

Available options:

none,

auto,

required

parallel_tool_calls

boolean

default:true

Allow multiple tool calls in parallel.

text

Text · object

Response format configuration.

Show child attributes

reasoning

Reasoning · object | null

Reasoning configuration for supported models.

Show child attributes

user

string | null

User identifier (echoed in response).

Response

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

Response object from POST /responses.

string

required

Unique response identifier.

object

enum<string>

required

Object type, always "response".

Available options:

response

status

enum<string>

required

Response lifecycle status.

Available options:

completed,

failed,

in_progress,

incomplete

created_at

integer

required

Unix timestamp when created.

model

string

required

Model ID used.

output

(Response Message · object | Response Function Call · object | Response Output Reasoning · object)[]

required

Output items (messages, reasoning, function calls).

An output item in the response (message, reasoning, or function_call).

Response Message
Response Function Call
Response Output Reasoning

Show child attributes

completed_at

integer | null

Unix timestamp when completed.

usage

Response Usage · object

Token usage statistics for the response.

Show child attributes

error

object | null

Error details when status is "failed".

Show child attributes

instructions

string | null

Echoed system instructions.

temperature

number | null

top_p

number | null

tools

Response Tool · object[]

Show child attributes

tool_choice

Controls how the model uses tools.

Available options:

none,

auto,

required

parallel_tool_calls

boolean

text

object

Show child attributes

reasoning

object | null

Show child attributes

store

boolean

Always false (stateless API).

service_tier

string | null

Overview

Inference API

Using the API

Authorizations

Body

Response