Chat completions

Create chat completion

curl --request POST \
  --url https://api.infery.ai/v1/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 1,
  "max_tokens": 123,
  "top_p": 0.5,
  "top_k": 123,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "seed": 123,
  "stream": false,
  "stop": "<string>",
  "tools": [
    {}
  ],
  "tool_choice": "<unknown>",
  "response_format": {}
}
'

import requests

url = "https://api.infery.ai/v1/chat/completions"

payload = {
    "model": "gpt-4o",
    "messages": [{ "content": "<string>" }],
    "temperature": 1,
    "max_tokens": 123,
    "top_p": 0.5,
    "top_k": 123,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "seed": 123,
    "stream": False,
    "stop": "<string>",
    "tools": [{}],
    "tool_choice": "<unknown>",
    "response_format": {}
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{content: '<string>'}],
    temperature: 1,
    max_tokens: 123,
    top_p: 0.5,
    top_k: 123,
    presence_penalty: 0,
    frequency_penalty: 0,
    seed: 123,
    stream: false,
    stop: '<string>',
    tools: [{}],
    tool_choice: '<unknown>',
    response_format: {}
  })
};

fetch('https://api.infery.ai/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.infery.ai/v1/chat/completions",
  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' => 'gpt-4o',
    'messages' => [
        [
                'content' => '<string>'
        ]
    ],
    'temperature' => 1,
    'max_tokens' => 123,
    'top_p' => 0.5,
    'top_k' => 123,
    'presence_penalty' => 0,
    'frequency_penalty' => 0,
    'seed' => 123,
    'stream' => false,
    'stop' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => '<unknown>',
    'response_format' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	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.infery.ai/v1/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}"

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

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1713204900,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 128,
    "total_tokens": 170
  },
  "credits_used": 2
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

POST

chat

completions

Create chat completion

curl --request POST \
  --url https://api.infery.ai/v1/chat/completions \
  --header 'Authorization: <api-key>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "gpt-4o",
  "messages": [
    {
      "content": "<string>"
    }
  ],
  "temperature": 1,
  "max_tokens": 123,
  "top_p": 0.5,
  "top_k": 123,
  "presence_penalty": 0,
  "frequency_penalty": 0,
  "seed": 123,
  "stream": false,
  "stop": "<string>",
  "tools": [
    {}
  ],
  "tool_choice": "<unknown>",
  "response_format": {}
}
'

import requests

url = "https://api.infery.ai/v1/chat/completions"

payload = {
    "model": "gpt-4o",
    "messages": [{ "content": "<string>" }],
    "temperature": 1,
    "max_tokens": 123,
    "top_p": 0.5,
    "top_k": 123,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "seed": 123,
    "stream": False,
    "stop": "<string>",
    "tools": [{}],
    "tool_choice": "<unknown>",
    "response_format": {}
}
headers = {
    "Authorization": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'gpt-4o',
    messages: [{content: '<string>'}],
    temperature: 1,
    max_tokens: 123,
    top_p: 0.5,
    top_k: 123,
    presence_penalty: 0,
    frequency_penalty: 0,
    seed: 123,
    stream: false,
    stop: '<string>',
    tools: [{}],
    tool_choice: '<unknown>',
    response_format: {}
  })
};

fetch('https://api.infery.ai/v1/chat/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.infery.ai/v1/chat/completions",
  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' => 'gpt-4o',
    'messages' => [
        [
                'content' => '<string>'
        ]
    ],
    'temperature' => 1,
    'max_tokens' => 123,
    'top_p' => 0.5,
    'top_k' => 123,
    'presence_penalty' => 0,
    'frequency_penalty' => 0,
    'seed' => 123,
    'stream' => false,
    'stop' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'tool_choice' => '<unknown>',
    'response_format' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <api-key>",
    "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.infery.ai/v1/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}")

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

	req.Header.Add("Authorization", "<api-key>")
	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.infery.ai/v1/chat/completions")
  .header("Authorization", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.infery.ai/v1/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"gpt-4o\",\n  \"messages\": [\n    {\n      \"content\": \"<string>\"\n    }\n  ],\n  \"temperature\": 1,\n  \"max_tokens\": 123,\n  \"top_p\": 0.5,\n  \"top_k\": 123,\n  \"presence_penalty\": 0,\n  \"frequency_penalty\": 0,\n  \"seed\": 123,\n  \"stream\": false,\n  \"stop\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"tool_choice\": \"<unknown>\",\n  \"response_format\": {}\n}"

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

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1713204900,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?",
        "tool_calls": [
          {}
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 128,
    "total_tokens": 170
  },
  "credits_used": 2
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model"
  }
}

Drop-in OpenAI-compatible chat endpoint. Supports streaming, tool calls, JSON mode, vision, PDF, audio input and Files API file_id references.

Minimal example

curl https://api.infery.ai/v1/chat/completions \
  -H "Authorization: Bearer $INFERY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "Summarise Node.js streams in 2 sentences"}
    ]
  }'

from openai import OpenAI
client = OpenAI(api_key=API_KEY, base_url="https://api.infery.ai/v1")
resp = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hi"}],
)

import OpenAI from 'openai';
const client = new OpenAI({ apiKey: process.env.INFERY_API_KEY, baseURL: 'https://api.infery.ai/v1' });
const resp = await client.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hi' }],
});

Streaming

Add "stream": true. Response is Server-Sent Events (text/event-stream). Each chunk is data: {...}\n\n; the stream ends with data: [DONE]\n\n. The final chunk before [DONE] carries usage info and Infery-specific credits_used:

data: {"choices":[{"delta":{"content":"..."}}]}
data: {"choices":[],"usage":{"prompt_tokens":42,"completion_tokens":128}}
data: {"choices":[],"usage":{...},"credits_used":2}
data: [DONE]

OpenAI SDKs ignore chunks with empty choices, so credits_used is a non-breaking extension.

Multimodal content

Pass arrays in content:

{
  "model": "gpt-4o",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "What's in this image?"},
      {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
    ]
  }]
}

Supported block types:

text
image_url — HTTP URL or base64 data: URI
input_audio — inline base64 audio with format (wav/mp3/pcm16/webm)
file — inline data + mime_type or file_id reference (Files API)

Using a Files API reference

{
  "content": [
    {"type": "text", "text": "Review this PDF"},
    {"type": "file", "file_id": "file_abc123..."}
  ]
}

The gateway resolves file_id to bytes on the server, injects them into the provider call, and returns a clear 400 if the id doesn’t exist or is out of your workspace.

Tool calls

Works exactly like OpenAI’s spec — tools, tool_choice, function schema and tool role messages. Every chat-capable model on Infery that supports tools honours the same format.

JSON mode

{"response_format": {"type": "json_object"}}

Or with a schema (Structured Outputs):

{
  "response_format": {
    "type": "json_schema",
    "json_schema": { "schema": { ... }, "strict": true }
  }
}

Vision and PDFs

Models with supportsVision: true accept images directly. For PDFs, models with supportsPdf: true read them natively. Others get an automatic PDF-to-image conversion on the gateway (plus text extraction) — you pay a small extra fee per page (see billing), no code changes required.

Parameters

Full OpenAI parameter set: temperature, top_p, presence_penalty, frequency_penalty, max_tokens, stop, seed, stream, tools, tool_choice, response_format. Plus model-specific:

top_k — Gemini and some OSS models

Response headers

x-request-id
x-credits-used
x-model-used (when fallback fires)
x-fallback-from, x-fallback-depth

Authorizations

Authorization

string

header

required

API key in format: Bearer inf_***

Headers

x-request-id

string

Optional request ID for tracking

Body

application/json

model

string

required

Model ID

Example:

"gpt-4o"

messages

object[]

required

Show child attributes

temperature

number

Required range: 0 <= x <= 2

max_tokens

integer

top_p

number

Required range: 0 <= x <= 1

top_k

integer

Top-K sampling (Google Gemini)

presence_penalty

number

Presence penalty (OpenAI, Google Gemini)

Required range: -2 <= x <= 2

frequency_penalty

number

Frequency penalty (OpenAI, Google Gemini)

Required range: -2 <= x <= 2

seed

integer

Seed for deterministic output (OpenAI, Google Gemini)

stream

boolean

default:false

stop

tools

object[]

tool_choice

any

response_format

object

Response

Chat completion result. When stream=true, returns SSE (text/event-stream) where each data chunk is a chat.completion.chunk; the final chunk before [DONE] carries usage and credits_used.

string

Example:

"chatcmpl-abc123"

object

string

Example:

"chat.completion"

created

integer

Example:

1713204900

model

string

Example:

"gpt-4o"

choices

object[]

Show child attributes

usage

object

Show child attributes

credits_used

integer

Credits deducted from the workspace balance for this request

Example:

2

Rate limits Embeddings

Overview

Embeddings

Images

Audio

Video

Music

Files

Models

Chat completions

Minimal example

Streaming

Multimodal content

Using a Files API reference

Tool calls

JSON mode

Vision and PDFs

Parameters

Response headers

Authorizations

Headers

Body

Response

​Minimal example

​Streaming

​Multimodal content

​Using a Files API reference

​Tool calls

​JSON mode

​Vision and PDFs

​Parameters

​Response headers

Authorizations

Headers

Body

Response

Minimal example

Streaming

Multimodal content

Using a Files API reference

Tool calls

JSON mode

Vision and PDFs

Parameters

Response headers