Chat Completions

code

POST /api/v1/chat/completions

The core endpoint. Send a conversation and receive a model response. Fully compatible with the OpenAI Chat Completions schema.

Request body

Field	Type	Required	Description
`model`	string	Yes	Model ID, e.g. `anthropic/claude-sonnet-4`
`messages`	array	Yes	Array of `{role, content}` objects
`stream`	boolean	No	Return SSE stream instead of JSON
`temperature`	number	No	0–2, default varies by model
`max_tokens`	number	No	Max tokens to generate, up to 64,000

You can browse all available models and their exact parameter support on the [Models](/models) page.

Example request

bash

curl https://modelgates.ai/api/v1/chat/completions \  -H "Authorization: Bearer sk-mg-YOUR_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "openai/gpt-4o",    "messages": [      {"role": "system", "content": "You are a helpful assistant."},      {"role": "user", "content": "Explain quantum computing in one sentence."}    ],    "temperature": 0.7,    "max_tokens": 256  }'

Example response

json

{  "id": "gen-xxxxxxxx",  "object": "chat.completion",  "created": 1715424000,  "model": "openai/gpt-4o",  "choices": [    {      "index": 0,      "message": {        "role": "assistant",        "content": "Quantum computing uses quantum bits to perform calculations..."      },      "finish_reason": "stop"    }  ],  "usage": {    "prompt_tokens": 24,    "completion_tokens": 18,    "total_tokens": 42  }}

Streaming

Set stream: true to receive Server-Sent Events (SSE). Each chunk contains a partial delta message.

Streaming is recommended for real-time UIs. The total cost is computed after the stream ends and debited from your balance.