Create an OpenAI-compatible chat completion

POST

chat

completions

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>",
      "reasoning": "<string>",
      "reasoning_content": "<string>",
      "name": "<string>",
      "tool_call_id": "<string>",
      "tool_calls": [
        {}
      ],
      "function_call": {},
      "model_id": "<string>"
    }
  ],
  "flagged_categories": [],
  "stream": false,
  "max_tokens": 499995,
  "max_completion_tokens": 499995,
  "temperature": 1,
  "top_p": 0.5,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "logit_bias": {},
  "n": 64,
  "seed": 123,
  "stop": "<string>",
  "stream_options": {
    "include_usage": true
  },
  "thinking": true,
  "reasoning": {
    "enabled": true,
    "max_tokens": 499995,
    "exclude": true
  },
  "include_reasoning": true,
  "safety_identifier": "<string>",
  "user": "<string>",
  "structuredOutputs": true,
  "tools": [
    {}
  ],
  "parallel_tool_calls": true,
  "functions": [
    {}
  ],
  "response_format": {
    "type": "<string>"
  },
  "modalities": [
    "<string>"
  ],
  "audio": {},
  "prediction": {},
  "metadata": {},
  "store": true,
  "service_tier": "<string>",
  "prompt_cache_key": "<string>",
  "logprobs": true,
  "top_logprobs": 123,
  "prompt_logprobs": 123,
  "web_search_options": {},
  "cache_salt": "<string>"
}
'

import requests

url = "https://api.example.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [
        {
            "content": "<string>",
            "reasoning": "<string>",
            "reasoning_content": "<string>",
            "name": "<string>",
            "tool_call_id": "<string>",
            "tool_calls": [{}],
            "function_call": {},
            "model_id": "<string>"
        }
    ],
    "flagged_categories": [],
    "stream": False,
    "max_tokens": 499995,
    "max_completion_tokens": 499995,
    "temperature": 1,
    "top_p": 0.5,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "logit_bias": {},
    "n": 64,
    "seed": 123,
    "stop": "<string>",
    "stream_options": { "include_usage": True },
    "thinking": True,
    "reasoning": {
        "enabled": True,
        "max_tokens": 499995,
        "exclude": True
    },
    "include_reasoning": True,
    "safety_identifier": "<string>",
    "user": "<string>",
    "structuredOutputs": True,
    "tools": [{}],
    "parallel_tool_calls": True,
    "functions": [{}],
    "response_format": { "type": "<string>" },
    "modalities": ["<string>"],
    "audio": {},
    "prediction": {},
    "metadata": {},
    "store": True,
    "service_tier": "<string>",
    "prompt_cache_key": "<string>",
    "logprobs": True,
    "top_logprobs": 123,
    "prompt_logprobs": 123,
    "web_search_options": {},
    "cache_salt": "<string>"
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        reasoning: '<string>',
        reasoning_content: '<string>',
        name: '<string>',
        tool_call_id: '<string>',
        tool_calls: [{}],
        function_call: {},
        model_id: '<string>'
      }
    ],
    flagged_categories: [],
    stream: false,
    max_tokens: 499995,
    max_completion_tokens: 499995,
    temperature: 1,
    top_p: 0.5,
    frequency_penalty: 0,
    presence_penalty: 0,
    logit_bias: {},
    n: 64,
    seed: 123,
    stop: '<string>',
    stream_options: {include_usage: true},
    thinking: true,
    reasoning: {enabled: true, max_tokens: 499995, exclude: true},
    include_reasoning: true,
    safety_identifier: '<string>',
    user: '<string>',
    structuredOutputs: true,
    tools: [{}],
    parallel_tool_calls: true,
    functions: [{}],
    response_format: {type: '<string>'},
    modalities: ['<string>'],
    audio: {},
    prediction: {},
    metadata: {},
    store: true,
    service_tier: '<string>',
    prompt_cache_key: '<string>',
    logprobs: true,
    top_logprobs: 123,
    prompt_logprobs: 123,
    web_search_options: {},
    cache_salt: '<string>'
  })
};

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

{
  "id": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>",
        "refusal": "<string>",
        "reasoning": "<string>",
        "reasoning_content": "<string>",
        "name": "<string>",
        "tool_call_id": "<string>",
        "tool_calls": [
          {}
        ],
        "function_call": {},
        "annotations": [
          {
            "url_citation": {
              "url": "<string>",
              "title": "<string>",
              "start_index": 1,
              "end_index": 1
            },
            "type": "url_citation"
          }
        ]
      },
      "logprobs": null,
      "finish_reason": "<string>"
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {},
    "completion_tokens_details": {}
  },
  "system_fingerprint": "<string>",
  "service_tier": "<string>"
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

Headers

Authorization

string | null

Bearer API key.

x-api-key

string | null

API key alternative for Anthropic-compatible clients. Authorization takes precedence when both headers are present.

Body

application/json

OpenAI-compatible chat completion request.

model

string

required

Public model ID.

Minimum string length: 1

messages

ChatCompletionMessage · object[]

required

OpenAI-compatible chat messages.

Minimum array length: 1

Show child attributes

flagged_categories

enum<string>[]

Abliteration safety categories to block for the latest user turn. Parent categories include their narrower child categories.

Available options:

harassment,

harassment/threatening,

hate,

hate/threatening,

illicit,

illicit/violent,

self-harm,

self-harm/intent,

self-harm/instructions,

sexual,

sexual/minors,

violence,

violence/graphic

stream

boolean

default:false

Whether to stream the response.

max_tokens

integer | null

Required range: 1 <= x <= 999990

max_completion_tokens

integer | null

Required range: 1 <= x <= 999990

temperature

number | null

Required range: 0 <= x <= 2

top_p

number | null

Required range: 0 <= x <= 1

frequency_penalty

number | null

Required range: -2 <= x <= 2

presence_penalty

number | null

Required range: -2 <= x <= 2

logit_bias

Logit Bias · object | null

Show child attributes

integer | null

Required range: 1 <= x <= 128

seed

integer | null

stop

stream_options

ChatCompletionStreamOptions · object | null

Show child attributes

thinking

boolean | null

Legacy compatibility toggle. The gateway translates this into backend-owned model-profile reasoning controls.

reasoning

ChatCompletionReasoningOptions · object | null

OpenRouter-style reasoning controls translated by the selected model profile.

Show child attributes

reasoning_effort

enum<string> | null

OpenAI/vLLM-compatible reasoning effort control.

Available options:

none,

minimal,

low,

medium,

high,

xhigh,

max,

ultracode

include_reasoning

boolean | null

Whether reasoning fields may be returned when the runtime emits them.

safety_identifier

string | null

Accepted for OpenAI compatibility, but not used for V1 abuse correlation and not forwarded to model runtimes.

Maximum string length: 64

user

string | null

Accepted for OpenAI compatibility but not forwarded to model runtimes.

Maximum string length: 512

structuredOutputs

boolean

Client structured-output capability declaration accepted for compatibility. It is ignored and never forwarded; use response_format to request an output format.

tools

Tools · object[] | null

tool_choice

Available options:

none,

auto,

required

parallel_tool_calls

boolean | null

functions

Functions · object[] | null

function_call

Available options:

none,

auto

response_format

ChatCompletionResponseFormatText · object

ChatCompletionResponseFormatText
ChatCompletionResponseFormatJsonObject
ChatCompletionResponseFormatJsonSchema

Show child attributes

modalities

string[] | null

verbosity

enum<string> | null

Available options:

low,

medium,

high

audio

Audio · object | null

prediction

Prediction · object | null

metadata

Metadata · object | null

store

boolean | null

service_tier

string | null

prompt_cache_key

string | null

Maximum string length: 512

prompt_cache_retention

enum<string> | null

Available options:

in_memory,

24h

logprobs

boolean | null

top_logprobs

integer | null

prompt_logprobs

integer | null

web_search_options

Web Search Options · object | null

cache_salt

string | null

Response

Successful Response

string

required

created

integer

required

model

string

required

choices

ChatCompletionChoice · object[]

required

Show child attributes

object

string

default:chat.completion

Allowed value: "chat.completion"

usage

ChatCompletionUsage · object | null

Show child attributes

system_fingerprint

string | null

service_tier

string | null

Last modified on August 11, 2026

Create an OpenAI-compatible chat completion

curl --request POST \
  --url https://api.example.com/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {
      "content": "<string>",
      "reasoning": "<string>",
      "reasoning_content": "<string>",
      "name": "<string>",
      "tool_call_id": "<string>",
      "tool_calls": [
        {}
      ],
      "function_call": {},
      "model_id": "<string>"
    }
  ],
  "flagged_categories": [],
  "stream": false,
  "max_tokens": 499995,
  "max_completion_tokens": 499995,
  "temperature": 1,
  "top_p": 0.5,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "logit_bias": {},
  "n": 64,
  "seed": 123,
  "stop": "<string>",
  "stream_options": {
    "include_usage": true
  },
  "thinking": true,
  "reasoning": {
    "enabled": true,
    "max_tokens": 499995,
    "exclude": true
  },
  "include_reasoning": true,
  "safety_identifier": "<string>",
  "user": "<string>",
  "structuredOutputs": true,
  "tools": [
    {}
  ],
  "parallel_tool_calls": true,
  "functions": [
    {}
  ],
  "response_format": {
    "type": "<string>"
  },
  "modalities": [
    "<string>"
  ],
  "audio": {},
  "prediction": {},
  "metadata": {},
  "store": true,
  "service_tier": "<string>",
  "prompt_cache_key": "<string>",
  "logprobs": true,
  "top_logprobs": 123,
  "prompt_logprobs": 123,
  "web_search_options": {},
  "cache_salt": "<string>"
}
'

import requests

url = "https://api.example.com/v1/chat/completions"

payload = {
    "model": "<string>",
    "messages": [
        {
            "content": "<string>",
            "reasoning": "<string>",
            "reasoning_content": "<string>",
            "name": "<string>",
            "tool_call_id": "<string>",
            "tool_calls": [{}],
            "function_call": {},
            "model_id": "<string>"
        }
    ],
    "flagged_categories": [],
    "stream": False,
    "max_tokens": 499995,
    "max_completion_tokens": 499995,
    "temperature": 1,
    "top_p": 0.5,
    "frequency_penalty": 0,
    "presence_penalty": 0,
    "logit_bias": {},
    "n": 64,
    "seed": 123,
    "stop": "<string>",
    "stream_options": { "include_usage": True },
    "thinking": True,
    "reasoning": {
        "enabled": True,
        "max_tokens": 499995,
        "exclude": True
    },
    "include_reasoning": True,
    "safety_identifier": "<string>",
    "user": "<string>",
    "structuredOutputs": True,
    "tools": [{}],
    "parallel_tool_calls": True,
    "functions": [{}],
    "response_format": { "type": "<string>" },
    "modalities": ["<string>"],
    "audio": {},
    "prediction": {},
    "metadata": {},
    "store": True,
    "service_tier": "<string>",
    "prompt_cache_key": "<string>",
    "logprobs": True,
    "top_logprobs": 123,
    "prompt_logprobs": 123,
    "web_search_options": {},
    "cache_salt": "<string>"
}
headers = {"Content-Type": "application/json"}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    messages: [
      {
        content: '<string>',
        reasoning: '<string>',
        reasoning_content: '<string>',
        name: '<string>',
        tool_call_id: '<string>',
        tool_calls: [{}],
        function_call: {},
        model_id: '<string>'
      }
    ],
    flagged_categories: [],
    stream: false,
    max_tokens: 499995,
    max_completion_tokens: 499995,
    temperature: 1,
    top_p: 0.5,
    frequency_penalty: 0,
    presence_penalty: 0,
    logit_bias: {},
    n: 64,
    seed: 123,
    stop: '<string>',
    stream_options: {include_usage: true},
    thinking: true,
    reasoning: {enabled: true, max_tokens: 499995, exclude: true},
    include_reasoning: true,
    safety_identifier: '<string>',
    user: '<string>',
    structuredOutputs: true,
    tools: [{}],
    parallel_tool_calls: true,
    functions: [{}],
    response_format: {type: '<string>'},
    modalities: ['<string>'],
    audio: {},
    prediction: {},
    metadata: {},
    store: true,
    service_tier: '<string>',
    prompt_cache_key: '<string>',
    logprobs: true,
    top_logprobs: 123,
    prompt_logprobs: 123,
    web_search_options: {},
    cache_salt: '<string>'
  })
};

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

{
  "id": "<string>",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "content": "<string>",
        "refusal": "<string>",
        "reasoning": "<string>",
        "reasoning_content": "<string>",
        "name": "<string>",
        "tool_call_id": "<string>",
        "tool_calls": [
          {}
        ],
        "function_call": {},
        "annotations": [
          {
            "url_citation": {
              "url": "<string>",
              "title": "<string>",
              "start_index": 1,
              "end_index": 1
            },
            "type": "url_citation"
          }
        ]
      },
      "logprobs": null,
      "finish_reason": "<string>"
    }
  ],
  "object": "chat.completion",
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {},
    "completion_tokens_details": {}
  },
  "system_fingerprint": "<string>",
  "service_tier": "<string>"
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}

{
  "error": {
    "code": "<string>",
    "message": "<string>",
    "request_id": "<string>",
    "param": "<string>",
    "doc_url": "<string>"
  }
}