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": [
    {
      "role": "user",
      "content": "Hello!",
      "name": "<string>",
      "tool_call_id": "call_abc123",
      "tool_calls": [
        {
          "id": "call_abc123",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\":\"Paris\"}"
          }
        }
      ]
    }
  ],
  "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": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location.",
        "parameters": {}
      }
    }
  ],
  "response_format": {
    "type": "text"
  },
  "prompt_cache_key": "<string>",
  "web_search": {
    "provider": "auto",
    "max_results": 5,
    "allowed_domains": [
      "<string>"
    ],
    "blocked_domains": [
      "<string>"
    ],
    "answer": true,
    "model": "<string>"
  }
}
'

import requests

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

payload = {
    "model": "gpt-4o",
    "messages": [
        {
            "role": "user",
            "content": "Hello!",
            "name": "<string>",
            "tool_call_id": "call_abc123",
            "tool_calls": [
                {
                    "id": "call_abc123",
                    "type": "function",
                    "function": {
                        "name": "get_weather",
                        "arguments": "{\"location\":\"Paris\"}"
                    }
                }
            ]
        }
    ],
    "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": [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather for a location.",
                "parameters": {}
            }
        }
    ],
    "response_format": { "type": "text" },
    "prompt_cache_key": "<string>",
    "web_search": {
        "provider": "auto",
        "max_results": 5,
        "allowed_domains": ["<string>"],
        "blocked_domains": ["<string>"],
        "answer": True,
        "model": "<string>"
    }
}
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: [
      {
        role: 'user',
        content: 'Hello!',
        name: '<string>',
        tool_call_id: 'call_abc123',
        tool_calls: [
          {
            id: 'call_abc123',
            type: 'function',
            function: {name: 'get_weather', arguments: '{"location":"Paris"}'}
          }
        ]
      }
    ],
    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: [
      {
        type: 'function',
        function: {
          name: 'get_weather',
          description: 'Get the current weather for a location.',
          parameters: {}
        }
      }
    ],
    response_format: {type: 'text'},
    prompt_cache_key: '<string>',
    web_search: {
      provider: 'auto',
      max_results: 5,
      allowed_domains: ['<string>'],
      blocked_domains: ['<string>'],
      answer: true,
      model: '<string>'
    }
  })
};

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' => [
        [
                'role' => 'user',
                'content' => 'Hello!',
                'name' => '<string>',
                'tool_call_id' => 'call_abc123',
                'tool_calls' => [
                                [
                                                                'id' => 'call_abc123',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => 'get_weather',
                                                                                                                                'arguments' => '{"location":"Paris"}'
                                                                ]
                                ]
                ]
        ]
    ],
    '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' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => 'get_weather',
                                'description' => 'Get the current weather for a location.',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'response_format' => [
        'type' => 'text'
    ],
    'prompt_cache_key' => '<string>',
    'web_search' => [
        'provider' => 'auto',
        'max_results' => 5,
        'allowed_domains' => [
                '<string>'
        ],
        'blocked_domains' => [
                '<string>'
        ],
        'answer' => true,
        'model' => '<string>'
    ]
  ]),
  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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\":\"Paris\"}"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url": "https://example.com/article",
            "title": "Example Article Title",
            "start_index": 123,
            "end_index": 123
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 128,
    "total_tokens": 170
  },
  "credits_used": 0.115,
  "web_search_credits": 0.4,
  "infery_web_search": {
    "provider": "openai",
    "searches": 2,
    "citations": [
      {
        "url": "https://example.com/article",
        "title": "An example article"
      }
    ]
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

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": [
    {
      "role": "user",
      "content": "Hello!",
      "name": "<string>",
      "tool_call_id": "call_abc123",
      "tool_calls": [
        {
          "id": "call_abc123",
          "type": "function",
          "function": {
            "name": "get_weather",
            "arguments": "{\"location\":\"Paris\"}"
          }
        }
      ]
    }
  ],
  "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": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather for a location.",
        "parameters": {}
      }
    }
  ],
  "response_format": {
    "type": "text"
  },
  "prompt_cache_key": "<string>",
  "web_search": {
    "provider": "auto",
    "max_results": 5,
    "allowed_domains": [
      "<string>"
    ],
    "blocked_domains": [
      "<string>"
    ],
    "answer": true,
    "model": "<string>"
  }
}
'

import requests

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

payload = {
    "model": "gpt-4o",
    "messages": [
        {
            "role": "user",
            "content": "Hello!",
            "name": "<string>",
            "tool_call_id": "call_abc123",
            "tool_calls": [
                {
                    "id": "call_abc123",
                    "type": "function",
                    "function": {
                        "name": "get_weather",
                        "arguments": "{\"location\":\"Paris\"}"
                    }
                }
            ]
        }
    ],
    "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": [
        {
            "type": "function",
            "function": {
                "name": "get_weather",
                "description": "Get the current weather for a location.",
                "parameters": {}
            }
        }
    ],
    "response_format": { "type": "text" },
    "prompt_cache_key": "<string>",
    "web_search": {
        "provider": "auto",
        "max_results": 5,
        "allowed_domains": ["<string>"],
        "blocked_domains": ["<string>"],
        "answer": True,
        "model": "<string>"
    }
}
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: [
      {
        role: 'user',
        content: 'Hello!',
        name: '<string>',
        tool_call_id: 'call_abc123',
        tool_calls: [
          {
            id: 'call_abc123',
            type: 'function',
            function: {name: 'get_weather', arguments: '{"location":"Paris"}'}
          }
        ]
      }
    ],
    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: [
      {
        type: 'function',
        function: {
          name: 'get_weather',
          description: 'Get the current weather for a location.',
          parameters: {}
        }
      }
    ],
    response_format: {type: 'text'},
    prompt_cache_key: '<string>',
    web_search: {
      provider: 'auto',
      max_results: 5,
      allowed_domains: ['<string>'],
      blocked_domains: ['<string>'],
      answer: true,
      model: '<string>'
    }
  })
};

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' => [
        [
                'role' => 'user',
                'content' => 'Hello!',
                'name' => '<string>',
                'tool_call_id' => 'call_abc123',
                'tool_calls' => [
                                [
                                                                'id' => 'call_abc123',
                                                                'type' => 'function',
                                                                'function' => [
                                                                                                                                'name' => 'get_weather',
                                                                                                                                'arguments' => '{"location":"Paris"}'
                                                                ]
                                ]
                ]
        ]
    ],
    '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' => [
        [
                'type' => 'function',
                'function' => [
                                'name' => 'get_weather',
                                'description' => 'Get the current weather for a location.',
                                'parameters' => [
                                                                
                                ]
                ]
        ]
    ],
    'response_format' => [
        'type' => 'text'
    ],
    'prompt_cache_key' => '<string>',
    'web_search' => [
        'provider' => 'auto',
        'max_results' => 5,
        'allowed_domains' => [
                '<string>'
        ],
        'blocked_domains' => [
                '<string>'
        ],
        'answer' => true,
        'model' => '<string>'
    ]
  ]),
  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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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      \"role\": \"user\",\n      \"content\": \"Hello!\",\n      \"name\": \"<string>\",\n      \"tool_call_id\": \"call_abc123\",\n      \"tool_calls\": [\n        {\n          \"id\": \"call_abc123\",\n          \"type\": \"function\",\n          \"function\": {\n            \"name\": \"get_weather\",\n            \"arguments\": \"{\\\"location\\\":\\\"Paris\\\"}\"\n          }\n        }\n      ]\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      \"type\": \"function\",\n      \"function\": {\n        \"name\": \"get_weather\",\n        \"description\": \"Get the current weather for a location.\",\n        \"parameters\": {}\n      }\n    }\n  ],\n  \"response_format\": {\n    \"type\": \"text\"\n  },\n  \"prompt_cache_key\": \"<string>\",\n  \"web_search\": {\n    \"provider\": \"auto\",\n    \"max_results\": 5,\n    \"allowed_domains\": [\n      \"<string>\"\n    ],\n    \"blocked_domains\": [\n      \"<string>\"\n    ],\n    \"answer\": true,\n    \"model\": \"<string>\"\n  }\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": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\":\"Paris\"}"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url": "https://example.com/article",
            "title": "Example Article Title",
            "start_index": 123,
            "end_index": 123
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 42,
    "completion_tokens": 128,
    "total_tokens": 170
  },
  "credits_used": 0.115,
  "web_search_credits": 0.4,
  "infery_web_search": {
    "provider": "openai",
    "searches": 2,
    "citations": [
      {
        "url": "https://example.com/article",
        "title": "An example article"
      }
    ]
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

{
  "error": {
    "message": "Model not found",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": "model",
    "job_id": "job_1hR9xTPZqK4mVLc2nJ7fY5wB"
  }
}

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.

Total attachment size per request

All file_id references in one request must total 64 MB or less, decoded. This is a limit on the sum, and it is separate from your plan’s per-file max_file_size_bytes. Both apply. Every file can be individually within your plan’s per-file cap and the request can still be refused for their total — that is the intended behaviour, because the server resolves all of them at once.

{
  "error": {
    "message": "Attachments total at least 78643200 bytes, above the 67108864-byte limit for one request. This is a limit on the SUM of all attached files, not on any single one — reference fewer files, or smaller ones.",
    "type": "invalid_request_error",
    "code": "attachments_too_large",
    "param": "messages[].content[].file_id"
  }
}

attachments_too_large always means the total, never one file. A single file that is too big for your plan is refused at upload time by /v1/files instead. Split the work across turns, or reference smaller files.

The cap is on decoded bytes, so it is the sum of the file sizes you see in /v1/files — not the size of the JSON request, which only carries the ids. Inline data blocks are not counted against it; they are bounded by the request body limit and by each model’s own per-file limits.

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-model-used
x-fallback-from

Cost isn’t a header here: chat completions return credits_used in the JSON response body, or in the final SSE chunk when streaming. x-credits-used exists only on binary-body endpoints that have no JSON body to carry it, like text-to-speech.

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 definitions available to the model. The gateway translates ONLY entries shaped {type:"function", function:{name, description?, parameters?}} into each provider's native tool-calling form; any other entry is forwarded upstream byte-identical — provider-native tools (web search, grounding, …) already arrive in their own shape.

Option 1
Option 2

Show child attributes

tool_choice

Controls whether/which tool the model must call: "none", "auto", "required", or {type:"function", function:{name}} to force one specific function tool.

Available options:

none,

auto,

required

response_format

object

Output format constraint: {type:"text"}, {type:"json_object"}, or {type:"json_schema", json_schema:{...}}.

Option 1
Option 2
Option 3

Show child attributes

prompt_cache_key

string

Optional cache-routing key for providers that cache prompt prefixes per-server (xAI, OpenAI). Send the same value across turns of one conversation to improve cache hit rate. Mirrors OpenAI’s own parameter of the same name.

web_search

object

Ground the completion in web search, without having to write a provider-native tool entry by hand. Sending this object is the opt-in; there is no boolean form and its absence means no search.

It is a SHORTHAND over tools, and the two reach the same place: the gateway resolves a backend from web_search.provider (or the model family) and, for the natively-grounded providers, injects the matching entry into tools before forwarding — then removes web_search itself, so the upstream provider never sees this key. Sending the provider-native tool entry in tools yourself is the equivalent long form and needs no web_search; send one or the other rather than both.

BILLED. The brave backend runs as a separate search charge reported as web_search_credits on the response, on top of the completion's own tokens; the natively-grounded backends bill through the upstream provider's own search pricing.

Show child attributes

Response

stream=false (default) returns application/json — a single chat-completion object, shown below. stream=true returns text/event-stream: a sequence of data: <json>\n\n lines terminated by a literal data: [DONE]. OpenAPI 3.0 has no way to describe a framed event stream, so the text/event-stream schema below describes the JSON payload of a SINGLE data: line (a chat.completion.chunk) — never the whole body. The final chunk before [DONE] carries usage and credits_used alongside an EMPTY choices array; every other chunk carries a non-empty choices with an incremental delta.

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

number

Credits deducted from the workspace balance for this request

Example:

0.115

web_search_credits

number

Credits charged for the grounded web search this request performed, separate from credits_used, which covers the model call. Present only when a web-search provider actually ran.

Example:

0.4

infery_web_search

object

What the grounded search actually did. Present only when a web-search provider ran. The same object rides the final SSE chunk when streaming.

Show child attributes

Overview

Embeddings

Images

Audio

Video

Music

Files

Models

Capabilities

Workflows

Chat completions

Minimal example

Streaming

Multimodal content

Using a Files API reference

Total attachment size per request

Tool calls

JSON mode

Vision and PDFs

Parameters

Response headers

Authorizations

Headers

Body

Response

​Minimal example

​Streaming

​Multimodal content

​Using a Files API reference

​Total attachment size per request

​Tool calls

​JSON mode

​Vision and PDFs

​Parameters

​Response headers

Authorizations

Headers

Body

Response

Minimal example

Streaming

Multimodal content

Using a Files API reference

Total attachment size per request

Tool calls

JSON mode

Vision and PDFs

Parameters

Response headers