Chat Completions

POST /v1/chat/completions

Generate a model response for a conversation. Compatible with the OpenAI Chat Completions API.

Headers

Request body

Required fields

Generation parameters

Output control

Tool calling

Reasoning

Streaming

Advanced

Messages

Each message must be an object with role (required) and content. Plain strings are not accepted.

Message fields

{"role": "user", "content": "What is 2+2?"}

Roles

Text messages

[
  {"role": "system", "content": "You are a helpful assistant."},
  {"role": "user", "content": "Hello!"}
]

Multi-turn conversations

[
  {"role": "user", "content": "What is the capital of France?"},
  {"role": "assistant", "content": "The capital of France is Paris."},
  {"role": "user", "content": "What about Germany?"}
]

Multimodal content parts

To send anything other than plain text, set content to an array of content parts. Each part declares a type and a type-specific payload. The following part types are accepted:

Any other type value is rejected with a 422 error.

Image

Image URLs can be an HTTPS URL or a base64 data URI.

[
  {
    "role": "user",
    "content": [
      {"type": "text", "text": "What is in this image?"},
      {"type": "image_url", "image_url": {"url": "https://example.com/photo.jpg"}}
    ]
  }
]

https://example.com/image.png
data:image/jpeg;base64,/9j/4AAQ...

Audio

input_audio.data must be a raw base64 string (no data-URI prefix). input_audio.format is one of wav, mp3, aiff, aac, ogg, flac, m4a, pcm16, pcm24.

[
  {
    "role": "user",
    "content": [
      {"type": "text", "text": "Transcribe and summarize this audio."},
      {"type": "input_audio", "input_audio": {"data": "<base64-mp3>", "format": "mp3"}}
    ]
  }
]

Video

video_url.url can be an HTTPS URL or a base64 data URI with a video MIME type (video/mp4, video/mpeg, video/mov, video/webm).

[
  {
    "role": "user",
    "content": [
      {"type": "text", "text": "Describe what is happening in this video."},
      {"type": "video_url", "video_url": {"url": "data:video/mp4;base64,<base64>"}}
    ]
  }
]

Document (PDF)

file.file_data can be an HTTPS URL or a base64 data URI with application/pdf. Either file_data or file_id is required.

[
  {
    "role": "user",
    "content": [
      {"type": "text", "text": "Summarize this document."},
      {
        "type": "file",
        "file": {
          "filename": "report.pdf",
          "file_data": "data:application/pdf;base64,<base64>"
        }
      }
    ]
  }
]

Model requirements

The model you target must declare support for each non-text modality you send. If a request contains audio parts but the chosen model’s input_modality.audio is false, the request is rejected with a 400:

{"error": {"message": "Model 'openai/gpt-4.1-nano' does not support audio input"}}

See the Providers capability matrix for per-provider support, and the Models endpoint for per-model modality flags. PDFs (file) are routed through OpenRouter’s universal PDF parser and do not require a dedicated modality flag on the model.

Tool calls (multi-turn)

When the model calls a tool, continue the conversation by including the assistant’s tool call and your tool’s response:

[
  {"role": "user", "content": "What's the weather in Paris?"},
  {
    "role": "assistant",
    "content": null,
    "tool_calls": [
      {
        "id": "call_1",
        "type": "function",
        "function": {"name": "get_weather", "arguments": "{\"city\": \"Paris\"}"}
      }
    ]
  },
  {"role": "tool", "tool_call_id": "call_1", "content": "{\"temp\": 18, \"unit\": \"C\"}"}
]

Tool format

Define tools using the standard function calling format. This format is the same regardless of which provider handles the request — the provider layer converts it automatically.

{
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get weather for a city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string", "description": "The city name"}
          },
          "required": ["city"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}

Examples

curl -X POST https://api.quantized.us/v1/chat/completions \
  -H "Authorization: Bearer sk-quantized-YOUR-KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1-mini",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ],
    "max_tokens": 128,
    "temperature": 0.7
  }'

import httpx

response = httpx.post(
    "https://api.quantized.us/v1/chat/completions",
    headers={"Authorization": "Bearer sk-quantized-YOUR-KEY"},
    json={
        "model": "openai/gpt-4.1-mini",
        "messages": [
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": "What is the capital of France?"},
        ],
        "max_tokens": 128,
        "temperature": 0.7,
    },
)
data = response.json()
print(data["choices"][0]["message"]["content"])

from openai import OpenAI

client = OpenAI(
    api_key="sk-quantized-YOUR-KEY",
    base_url="https://api.quantized.us/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4.1-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"},
    ],
    max_tokens=128,
    temperature=0.7,
)
print(response.choices[0].message.content)

Response

{
  "id": "gen-abc123",
  "object": "chat.completion",
  "model": "openai/gpt-4.1-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris.",
        "refusal": null
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33,
    "credits_used": 2400,
    "credits_remaining": 997600,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "cache_write_tokens": 0,
      "audio_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 0,
      "audio_tokens": 0
    }
  },
  "created": 1719000000
}

Response fields

Streaming

Set "stream": true to receive Server-Sent Events. See the Streaming guide for details and code examples.

Errors