POST / API reference

Chat Completions

Create a model response from a conversation using an OpenAI-compatible request format.

POST/v1/chat/completions

https://api.aonis.space/v1/chat/completions

Request examples

shell · cURL

curl https://api.aonis.space/v1/chat/completions \
  -H "Authorization: Bearer $AONIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

javascript / example.mjs

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AONIS_API_KEY,
  baseURL: "https://api.aonis.space/v1",
});

const response = await client.chat.completions.create({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "Hello!" }],
});

console.log(response);

python / example.py

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AONIS_API_KEY",
    base_url="https://api.aonis.space/v1",
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "Hello!"}],
)

print(response)

Streaming

Supported

Set stream: true to receive the response incrementally instead of waiting for the complete response.

json · Streaming request

{
  "model": "claude-sonnet-5",
  "messages": [{ "role": "user", "content": "Hello!" }],
  "stream": true
}

Notes

Tool Calling is supported through this endpoint. See the dedicated guide for the validated request format.

For configurable reasoning effort, use the Responses API or the OpenCode reasoning variants.