Create chat completion

Starting a new project? We recommend trying Responses to take advantage of the latest OpenAI platform features. Compare Chat Completions with Responses.

Creates a model response for the given chat conversation. Learn more in the text generation, vision, and audio guides.

Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, refer to the reasoning guide.

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

Authorization: Bearer ********************

curl --location --request POST 'https://api.openai.com/v1/chat/completions' \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data-raw '{ "model": "gpt-3.5-turbo", "messages": [{"role": "user", "content": "Hello!"}] }'

{ "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT", "object": "chat.completion", "created": 1741569952, "model": "gpt-4.1-2025-04-14", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "Hello! How can I assist you today?", "refusal": null, "annotations": [] }, "logprobs": null, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 19, "completion_tokens": 10, "total_tokens": 29, "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0 }, "completion_tokens_details": { "reasoning_tokens": 0, "audio_tokens": 0, "accepted_prediction_tokens": 0, "rejected_prediction_tokens": 0 } }, "service_tier": "default" }

Request

Responses