OpenAI chat completion

Creates a chat completion using a conversational message format. This endpoint supports multi-turn conversations with system, user, and assistant messages.

How To Use

Simply specify the model name in your request payload. All other parameters remain the same across different models.

Supported Models

GPT-3.5 series: gpt-3.5-turbo, gpt-3.5-turbo-0125, gpt-3.5-turbo-0613, gpt-3.5-turbo-1106, gpt-3.5-turbo-16k, gpt-3.5-turbo-16k-0613

GPT-4 series: gpt-4-32k, gpt-4-32k-0613, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-vision-preview

GPT-4.1 series: gpt-4.1, gpt-4.1-2025-04-14, gpt-4.1-mini, gpt-4.1-mini-2025-04-14, gpt-4.1-nano, gpt-4.1-nano-2025-04-14

GPT-4o series: gpt-4o, gpt-4o-2024-05-13, gpt-4o-2024-08-06, gpt-4o-2024-11-20, gpt-4o-mini, gpt-4o-mini-2024-07-18

GPT-5 series: gpt-5, gpt-5-2025-08-07, gpt-5-chat-latest, gpt-5-mini, gpt-5-nano

O1 series: o1, o1-2024-12-17, o1-mini, o1-mini-2024-09-12, o1-preview, o1-preview-2024-09-12

O3 series: o3, o3-2025-04-16, o3-mini, o3-mini-2025-01-31, o3-pro

O4 series: o4-mini, o4-mini-2025-04-16

Request

Authorization

Bearer Token

Provide your bearer token in the

Authorization

header when making requests to protected resources.

Example:

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

Body Params application/jsonRequired

Examples

GPT-4oO3 ReasoningGPT-5

{
    "model": "gpt-4o",
    "max_tokens": 1024,
    "messages": [
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Hello!"
        }
    ]
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

Responses

🟢200OK

application/json

Successful response

Body

Example

{
    "choices": [
        {
            "content_filter_results": {
                "hate": {
                    "filtered": false,
                    "severity": "safe"
                },
                "protected_material_code": {
                    "filtered": false,
                    "detected": false
                },
                "protected_material_text": {
                    "filtered": false,
                    "detected": false
                },
                "self_harm": {
                    "filtered": false,
                    "severity": "safe"
                },
                "sexual": {
                    "filtered": false,
                    "severity": "safe"
                },
                "violence": {
                    "filtered": false,
                    "severity": "safe"
                }
            },
            "finish_reason": "stop",
            "index": 0,
            "logprobs": null,
            "message": {
                "annotations": [],
                "content": "Hello! I'm ChatGPT, a large language model created by OpenAI based on the GPT-4 architecture. I'm designed to understand and generate natural language so I can help answer questions, assist with tasks, and have open-ended conversations.",
                "refusal": null,
                "role": "assistant"
            }
        }
    ],
    "created": 1769503909,
    "id": "chatcmpl-D2Z5Zt1vNXljenyUCj2M42Xe2LjL6",
    "model": "o3-2025-04-16",
    "object": "chat.completion",
    "prompt_filter_results": [
        {
            "prompt_index": 0,
            "content_filter_results": {
                "hate": {
                    "filtered": false,
                    "severity": "safe"
                },
                "jailbreak": {
                    "filtered": false,
                    "detected": false
                },
                "self_harm": {
                    "filtered": false,
                    "severity": "safe"
                },
                "sexual": {
                    "filtered": false,
                    "severity": "safe"
                },
                "violence": {
                    "filtered": false,
                    "severity": "safe"
                }
            }
        }
    ],
    "system_fingerprint": null,
    "usage": {
        "completion_tokens": 133,
        "completion_tokens_details": {
            "accepted_prediction_tokens": 0,
            "audio_tokens": 0,
            "reasoning_tokens": 64,
            "rejected_prediction_tokens": 0
        },
        "prompt_tokens": 13,
        "prompt_tokens_details": {
            "audio_tokens": 0,
            "cached_tokens": 0
        },
        "total_tokens": 146
    }
}

🟠400Bad Request

🟠401Unauthorized

🟠429Too Many Requests

🔴500Internal Server Error

How To Use#

Supported Models#

Request

Request Code Samples

Responses

How To Use

Supported Models