Generate OpenAI chat completion from messages

curl --request POST \
  --url https://api.egp.scale.com/v4/beta/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "top_k": 123,
  "frequency_penalty": 0,
  "function_call": {},
  "functions": [
    {}
  ],
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 123,
  "max_tokens": 123,
  "metadata": {},
  "modalities": [
    "<string>"
  ],
  "n": 123,
  "parallel_tool_calls": true,
  "prediction": {},
  "presence_penalty": 0,
  "reasoning_effort": "<string>",
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "store": true,
  "stream": true,
  "stream_options": {},
  "temperature": 1,
  "tool_choice": "<string>",
  "tools": [
    {}
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "audio": {}
}
'

import requests

url = "https://api.egp.scale.com/v4/beta/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "top_k": 123,
    "frequency_penalty": 0,
    "function_call": {},
    "functions": [{}],
    "logit_bias": {},
    "logprobs": True,
    "max_completion_tokens": 123,
    "max_tokens": 123,
    "metadata": {},
    "modalities": ["<string>"],
    "n": 123,
    "parallel_tool_calls": True,
    "prediction": {},
    "presence_penalty": 0,
    "reasoning_effort": "<string>",
    "response_format": {},
    "seed": 123,
    "stop": "<string>",
    "store": True,
    "stream": True,
    "stream_options": {},
    "temperature": 1,
    "tool_choice": "<string>",
    "tools": [{}],
    "top_logprobs": 10,
    "top_p": 0.5,
    "audio": {}
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{}],
    top_k: 123,
    frequency_penalty: 0,
    function_call: {},
    functions: [{}],
    logit_bias: {},
    logprobs: true,
    max_completion_tokens: 123,
    max_tokens: 123,
    metadata: {},
    modalities: ['<string>'],
    n: 123,
    parallel_tool_calls: true,
    prediction: {},
    presence_penalty: 0,
    reasoning_effort: '<string>',
    response_format: {},
    seed: 123,
    stop: '<string>',
    store: true,
    stream: true,
    stream_options: {},
    temperature: 1,
    tool_choice: '<string>',
    tools: [{}],
    top_logprobs: 10,
    top_p: 0.5,
    audio: {}
  })
};

fetch('https://api.egp.scale.com/v4/beta/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.egp.scale.com/v4/beta/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'top_k' => 123,
    'frequency_penalty' => 0,
    'function_call' => [
        
    ],
    'functions' => [
        [
                
        ]
    ],
    'logit_bias' => [
        
    ],
    'logprobs' => true,
    'max_completion_tokens' => 123,
    'max_tokens' => 123,
    'metadata' => [
        
    ],
    'modalities' => [
        '<string>'
    ],
    'n' => 123,
    'parallel_tool_calls' => true,
    'prediction' => [
        
    ],
    'presence_penalty' => 0,
    'reasoning_effort' => '<string>',
    'response_format' => [
        
    ],
    'seed' => 123,
    'stop' => '<string>',
    'store' => true,
    'stream' => true,
    'stream_options' => [
        
    ],
    'temperature' => 1,
    'tool_choice' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'audio' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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.egp.scale.com/v4/beta/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}")

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

	req.Header.Add("x-api-key", "<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.egp.scale.com/v4/beta/chat/completions")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/beta/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}"

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

{
  "id": "<string>",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "refusal": "<string>",
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "end_index": 123,
              "start_index": 123,
              "title": "<string>",
              "url": "<string>"
            }
          }
        ],
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "function_call": {
          "arguments": "<string>",
          "name": "<string>"
        },
        "tool_calls": [
          {
            "id": "<string>",
            "function": {
              "arguments": "<string>",
              "name": "<string>"
            },
            "type": "function"
          }
        ]
      },
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ],
        "refusal": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ]
      }
    }
  ],
  "created": 123,
  "model": "<string>",
  "object": "chat.completion",
  "service_tier": "auto",
  "system_fingerprint": "<string>",
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "prompt_tokens_details": {
      "audio_tokens": 123,
      "cached_tokens": 123
    }
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Beta

Generate OpenAI chat completion from messages

Generates a chat completion from an OpenAI-style messages array.

Use this endpoint for standard messages-based chat inference; use /v5/completions instead when you have a raw text prompt rather than messages, /v5/responses for the OpenAI Responses API contract, and /v5/inference when the payload does not follow any OpenAI schema. The request accepts the OpenAI Chat Completions parameters plus a fixed set of vendor generation parameters such as top_k, guided_choice, and thinking; other extra fields are dropped, and fields that set the provider endpoint, credentials, or headers (for example api_base, api_key, extra_headers) are rejected with a 422. The model is selected from model given as vendor/name; most vendors are served through the litellm proxy gateway, while OpenAI may use a native gateway. When stream is set the response is delivered as server-sent events of chat.completion.chunk; otherwise a single chat.completion object is returned. Token usage is recorded for the account, and for streaming responses it is read from the final chunk.

POST

beta

chat

completions

Generate OpenAI chat completion from messages

curl --request POST \
  --url https://api.egp.scale.com/v4/beta/chat/completions \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "top_k": 123,
  "frequency_penalty": 0,
  "function_call": {},
  "functions": [
    {}
  ],
  "logit_bias": {},
  "logprobs": true,
  "max_completion_tokens": 123,
  "max_tokens": 123,
  "metadata": {},
  "modalities": [
    "<string>"
  ],
  "n": 123,
  "parallel_tool_calls": true,
  "prediction": {},
  "presence_penalty": 0,
  "reasoning_effort": "<string>",
  "response_format": {},
  "seed": 123,
  "stop": "<string>",
  "store": true,
  "stream": true,
  "stream_options": {},
  "temperature": 1,
  "tool_choice": "<string>",
  "tools": [
    {}
  ],
  "top_logprobs": 10,
  "top_p": 0.5,
  "audio": {}
}
'

import requests

url = "https://api.egp.scale.com/v4/beta/chat/completions"

payload = {
    "model": "<string>",
    "messages": [{}],
    "top_k": 123,
    "frequency_penalty": 0,
    "function_call": {},
    "functions": [{}],
    "logit_bias": {},
    "logprobs": True,
    "max_completion_tokens": 123,
    "max_tokens": 123,
    "metadata": {},
    "modalities": ["<string>"],
    "n": 123,
    "parallel_tool_calls": True,
    "prediction": {},
    "presence_penalty": 0,
    "reasoning_effort": "<string>",
    "response_format": {},
    "seed": 123,
    "stop": "<string>",
    "store": True,
    "stream": True,
    "stream_options": {},
    "temperature": 1,
    "tool_choice": "<string>",
    "tools": [{}],
    "top_logprobs": 10,
    "top_p": 0.5,
    "audio": {}
}
headers = {
    "x-api-key": "<api-key>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'x-api-key': '<api-key>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [{}],
    top_k: 123,
    frequency_penalty: 0,
    function_call: {},
    functions: [{}],
    logit_bias: {},
    logprobs: true,
    max_completion_tokens: 123,
    max_tokens: 123,
    metadata: {},
    modalities: ['<string>'],
    n: 123,
    parallel_tool_calls: true,
    prediction: {},
    presence_penalty: 0,
    reasoning_effort: '<string>',
    response_format: {},
    seed: 123,
    stop: '<string>',
    store: true,
    stream: true,
    stream_options: {},
    temperature: 1,
    tool_choice: '<string>',
    tools: [{}],
    top_logprobs: 10,
    top_p: 0.5,
    audio: {}
  })
};

fetch('https://api.egp.scale.com/v4/beta/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.egp.scale.com/v4/beta/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' => '<string>',
    'messages' => [
        [
                
        ]
    ],
    'top_k' => 123,
    'frequency_penalty' => 0,
    'function_call' => [
        
    ],
    'functions' => [
        [
                
        ]
    ],
    'logit_bias' => [
        
    ],
    'logprobs' => true,
    'max_completion_tokens' => 123,
    'max_tokens' => 123,
    'metadata' => [
        
    ],
    'modalities' => [
        '<string>'
    ],
    'n' => 123,
    'parallel_tool_calls' => true,
    'prediction' => [
        
    ],
    'presence_penalty' => 0,
    'reasoning_effort' => '<string>',
    'response_format' => [
        
    ],
    'seed' => 123,
    'stop' => '<string>',
    'store' => true,
    'stream' => true,
    'stream_options' => [
        
    ],
    'temperature' => 1,
    'tool_choice' => '<string>',
    'tools' => [
        [
                
        ]
    ],
    'top_logprobs' => 10,
    'top_p' => 0.5,
    'audio' => [
        
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-api-key: <api-key>"
  ],
]);

$response = curl_exec($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.egp.scale.com/v4/beta/chat/completions"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}")

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

	req.Header.Add("x-api-key", "<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.egp.scale.com/v4/beta/chat/completions")
  .header("x-api-key", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.egp.scale.com/v4/beta/chat/completions")

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

request = Net::HTTP::Post.new(url)
request["x-api-key"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"messages\": [\n    {}\n  ],\n  \"top_k\": 123,\n  \"frequency_penalty\": 0,\n  \"function_call\": {},\n  \"functions\": [\n    {}\n  ],\n  \"logit_bias\": {},\n  \"logprobs\": true,\n  \"max_completion_tokens\": 123,\n  \"max_tokens\": 123,\n  \"metadata\": {},\n  \"modalities\": [\n    \"<string>\"\n  ],\n  \"n\": 123,\n  \"parallel_tool_calls\": true,\n  \"prediction\": {},\n  \"presence_penalty\": 0,\n  \"reasoning_effort\": \"<string>\",\n  \"response_format\": {},\n  \"seed\": 123,\n  \"stop\": \"<string>\",\n  \"store\": true,\n  \"stream\": true,\n  \"stream_options\": {},\n  \"temperature\": 1,\n  \"tool_choice\": \"<string>\",\n  \"tools\": [\n    {}\n  ],\n  \"top_logprobs\": 10,\n  \"top_p\": 0.5,\n  \"audio\": {}\n}"

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

{
  "id": "<string>",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "refusal": "<string>",
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "end_index": 123,
              "start_index": 123,
              "title": "<string>",
              "url": "<string>"
            }
          }
        ],
        "audio": {
          "id": "<string>",
          "data": "<string>",
          "expires_at": 123,
          "transcript": "<string>"
        },
        "function_call": {
          "arguments": "<string>",
          "name": "<string>"
        },
        "tool_calls": [
          {
            "id": "<string>",
            "function": {
              "arguments": "<string>",
              "name": "<string>"
            },
            "type": "function"
          }
        ]
      },
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ],
        "refusal": [
          {
            "token": "<string>",
            "logprob": 123,
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ],
            "bytes": [
              123
            ]
          }
        ]
      }
    }
  ],
  "created": 123,
  "model": "<string>",
  "object": "chat.completion",
  "service_tier": "auto",
  "system_fingerprint": "<string>",
  "usage": {
    "completion_tokens": 123,
    "prompt_tokens": 123,
    "total_tokens": 123,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 123,
      "audio_tokens": 123,
      "reasoning_tokens": 123,
      "rejected_prediction_tokens": 123
    },
    "prompt_tokens_details": {
      "audio_tokens": 123,
      "cached_tokens": 123
    }
  }
}

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}

Authorizations

x-api-key

string

header

required

Headers

x-api-key

string | null

x-openai-api-key

string | null

x-selected-account-id

string | null

Body

application/json

model

string

required

model specified as model_vendor/model, for example openai/gpt-4o

messages

Messages · object[]

required

openai standard message format

top_k

integer | null

Only sample from the top K options for each subsequent token

frequency_penalty

number | null

Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far.

Required range: -2 <= x <= 2

function_call

Function Call · object | null

Deprecated in favor of tool_choice. Controls which function is called by the model.

functions

Functions · object[] | null

Deprecated in favor of tools. A list of functions the model may generate JSON inputs for.

logit_bias

Logit Bias · object | null

Modify the likelihood of specified tokens appearing in the completion. Maps tokens to bias values from -100 to 100.

Show child attributes

logprobs

boolean | null

Whether to return log probabilities of the output tokens or not.

max_completion_tokens

integer | null

An upper bound for the number of tokens that can be generated, including visible output tokens and reasoning tokens.

max_tokens

integer | null

Deprecated in favor of max_completion_tokens. The maximum number of tokens to generate.

metadata

Metadata · object | null

Developer-defined tags and values used for filtering completions in the dashboard.

Show child attributes

modalities

string[] | null

Output types that you would like the model to generate for this request.

integer | null

How many chat completion choices to generate for each input message.

parallel_tool_calls

boolean | null

Whether to enable parallel function calling during tool use.

prediction

Prediction · object | null

Static predicted output content, such as the content of a text file being regenerated.

presence_penalty

number | null

Number between -2.0 and 2.0. Positive values penalize tokens based on whether they appear in the text so far.

Required range: -2 <= x <= 2

reasoning_effort

string | null

For o1 models only. Constrains effort on reasoning. Values: low, medium, high.

response_format

Response Format · object | null

An object specifying the format that the model must output.

seed

integer | null

If specified, system will attempt to sample deterministically for repeated requests with same seed.

stop

Up to 4 sequences where the API will stop generating further tokens.

store

boolean | null

Whether to store the output for use in model distillation or evals products.

stream

boolean | null

If true, partial message deltas will be sent as server-sent events.

stream_options

Stream Options · object | null

Options for streaming response. Only set this when stream is true.

temperature

number | null

What sampling temperature to use. Higher values make output more random, lower more focused.

Required range: 0 <= x <= 2

tool_choice

Controls which tool is called by the model. Values: none, auto, required, or specific tool.

tools

Tools · object[] | null

A list of tools the model may call. Currently, only functions are supported. Max 128 functions.

top_logprobs

integer | null

Number of most likely tokens to return at each position, with associated log probability.

Required range: 0 <= x <= 20

top_p

number | null

Alternative to temperature. Only tokens comprising top_p probability mass are considered.

Required range: 0 <= x <= 1

audio

Audio · object | null

Parameters for audio output. Required when audio output is requested with modalities: ['audio'].

Response

Successful Response

Response Post-V4-Beta-/V5/Chat/Completions
Response Post-V4-Beta-/V5/Chat/Completions

string

required

choices

Choice · object[]

required

Show child attributes

created

integer

required

model

string

required

object

string

default:chat.completion

Allowed value: "chat.completion"

service_tier

enum<string> | null

Available options:

auto,

default,

flex,

scale,

priority

system_fingerprint

string | null

usage

CompletionUsage · object | null

Usage statistics for the completion request.

Show child attributes

Knowledge Bases

Chunks

Agents

Completions

Chat Completions

Models

Users

Accounts

Organizations

Question Sets

Evaluations

Evaluation Configs

Evaluation Datasets

Studio Projects

Application Specs

Questions

Knowledge Base Data Sources

Model Templates V3 (Beta)

Model server

API Reference

Fine Tuning Jobs V3 (Beta)

Training Datasets V3 (Beta)

package deployments

Beta

Applications

ChatThreads

Interactions

MonitoringDashboard

Chat Themes

Sessions

account groups

Generate OpenAI chat completion from messages

Authorizations

Headers

Body

Response