Create chat completion - Sionic Opengateway

Creates a model response for the given chat conversation. Compatible with the OpenAI API.
With stream: true the response is a server-sent event stream of chat.completion.chunk
objects that ends with data: [DONE]. Supported parameters differ by model.

Request

Header Params

Body Params application/jsonRequired

Examples

Basic requestStreaming with usageModel fallbacks

{
    "model": "openai/gpt-4o-mini",
    "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

A chat completion object (stream false/omitted) or an SSE stream of chat completion
chunks (stream: true). Each SSE data: line carries one ChatCompletionChunk JSON
object; the stream ends with data: [DONE].

Headers

Body

Example

{
    "id": "string",
    "object": "chat.completion",
    "created": 0,
    "model": "openai/gpt-5-mini",
    "system_fingerprint": "string",
    "service_tier": "string",
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "string",
                "tool_calls": [
                    {
                        "id": "string",
                        "type": "function",
                        "function": {
                            "name": "string",
                            "arguments": "string"
                        }
                    }
                ],
                "reasoning_content": "string",
                "reasoning_details": [
                    null
                ],
                "function_call": {}
            },
            "finish_reason": "stop",
            "logprobs": {
                "content": [
                    {
                        "top_logprobs": [
                            {
                                "token": "string",
                                "logprob": 0,
                                "bytes": [
                                    0
                                ]
                            }
                        ],
                        "token": "string",
                        "logprob": 0,
                        "bytes": [
                            0
                        ]
                    }
                ],
                "refusal": null
            }
        }
    ],
    "usage": {
        "prompt_tokens": 0,
        "completion_tokens": 0,
        "total_tokens": 0,
        "prompt_tokens_details": {
            "cached_tokens": 0
        },
        "completion_tokens_details": {
            "reasoning_tokens": 0
        }
    },
    "debug": {
        "normalizations": [
            {
                "param": "string",
                "action": "add",
                "before": null,
                "after": null
            }
        ],
        "deprecations": [
            {
                "param": "string",
                "message": "string"
            }
        ],
        "routing": [
            {
                "provider": "string",
                "region": "string",
                "status": "failed",
                "target": "string"
            }
        ]
    }
}

🟠400Bad Request

🟠401Unauthorized

🟠402

🟠429

🔴500Server Error

🔴503Service Unavailable

🔴529