Integration Guide

1. Quick Start

Use the same request shape as OpenAI. Change only your base URL and model id.

curl https://api.tokenoutput.cc/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "DeepSeek-V3.2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

2. Authentication

All requests require your API key in the Authorization header.

3. SDK Usage

from openai import OpenAI

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

resp = client.chat.completions.create(
    model="GLM-5",
    messages=[{"role": "user", "content": "Hello"}]
)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'sk-your-api-key',
  baseURL: 'https://api.tokenoutput.cc/v1',
});

const resp = await client.chat.completions.create({
  model: 'QWEN3.6-PLUS',
  messages: [{ role: 'user', content: 'Hello' }],
});

4. Streaming

Set stream: true to receive SSE chunks.

curl -N https://api.tokenoutput.cc/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QWEN3.6-PLUS",
    "stream": true,
    "messages": [{"role": "user", "content": "请用中文写一句问候"}]
  }'

5. Public Model ID List

These are the model IDs you can pass in the model field.

6. Billing

• Pay-as-you-go: usage is billed by token consumption.
• Starter: 1,200 requests / month, then overage switches to pay-as-you-go.
• Pro: 3,000 requests / month, then overage switches to pay-as-you-go.