Chat Completions

POST/v1/chat/completions

Use an OpenAI Chat Completions-compatible shape for text, multimodal input, and tool calls.

This is the recommended text endpoint for a first integration. Available fields depend on the selected model and Provider route.

Core request fields

Field	Type	Required	Description
`model`	string	Yes	A model ID returned by /v1/models.
`messages`	array	Yes	Conversation messages; content can be a string or a multimodal content array.
`stream`	boolean	No	Returns an SSE stream when true.
`temperature`	number	No	Sampling control when supported by the model and route.
`max_tokens`	integer	No	Output token limit subject to model capability.
`tools`	array	No	OpenAI-style function tool definitions.
`response_format`	object	No	Structured output request when supported by the model and route.

Non-streaming examples

curl https://api.noxgate.net/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'

from openai import OpenAI

client = OpenAI(
    api_key="sk-your-api-key",
    base_url="https://api.noxgate.net/v1",
)

response = client.chat.completions.create(
    model="YOUR_MODEL_ID",
    messages=[{"role": "user", "content": "Hello"}],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-your-api-key",
  baseURL: "https://api.noxgate.net/v1",
});

const response = await client.chat.completions.create({
  model: "YOUR_MODEL_ID",
  messages: [{ role: "user", content: "Hello" }],
});

console.log(response.choices[0]?.message?.content);

Streaming

With stream=true, the response uses text/event-stream. Process each data event and treat data: [DONE] as normal completion. The gateway may send comment heartbeats while the connection is idle.

curl https://api.noxgate.net/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }' \
  -N

Successful response

{
  "id": "chatcmpl_example",
  "object": "chat.completion",
  "model": "YOUR_MODEL_ID",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Hello!"},
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 8,
    "completion_tokens": 3,
    "total_tokens": 11
  }
}

Usage notes

Start with a non-streaming text request to verify the key, Base URL, and model ID.
Multimodal input, tool calls, and structured output require support from the selected model.
Do not assume every Provider supports the same optional fields.