OpenAI-compatible API

One API.
Every model.

Access 34 state-of-the-art AI models through a single, unified endpoint. Claude, GPT, Gemini, Grok and more.

Get Started → View Docs
quickstart.py 
from openai import OpenAI

client = OpenAI(
    base_url="https://sy-nc.lol/api",
    api_key="your-key-here",
)

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

print(response.choices[0].message.content)
34 AI Models
1 Endpoint
100% OpenAI-compatible
✓ Streaming

Models

All models use the sync/ prefix.

Claude Anthropic Claude
  • sync/claude-opus-5.5
  • sync/claude-opus-5
  • sync/claude-opus-4.8
  • sync/claude-opus-4.7
  • sync/claude-opus-4.6
  • sync/claude-sonnet-5
  • sync/claude-fable-5.1
  • sync/claude-fable-5
  • sync/claude-mythos-preview
GPT OpenAI GPT
  • sync/gpt-5.6-sol
  • sync/gpt-5.6-terra
  • sync/gpt-5.6-luna
  • sync/gpt-5.5-pro
  • sync/gpt-5.5
Gemini Google Gemini
  • sync/gemini-3.7-flash
  • sync/gemini-3.6-flash
  • sync/gemini-3.1-pro
DeepSeek DeepSeek
  • sync/deepseek-v4-pro-max
  • sync/deepseek-v4-pro-0813
  • sync/deepseek-v4-flash-0731
Grok xAI Grok
  • sync/grok-4.6
  • sync/grok-4.5
Qwen Alibaba Qwen
  • sync/qwen3.8-max
  • sync/qwen3.8-27b
  • sync/qwen3.7-max
Kimi Moonshot Kimi
  • sync/kimi-k3
  • sync/kimi-k2.6
Others Others
  • sync/glm-5.3
  • sync/glm-5.2
  • sync/seed-2.1-pro
  • sync/seed-2.1-turbo
  • sync/muse-spark-1.1
  • sync/gemma-2-2b

Documentation

Drop-in replacement for the OpenAI API.

Base URL

https://sy-nc.lol/api

Authentication

Authorization: Bearer <your-key>

List Models

GET /api/models 
curl https://sy-nc.lol/api/models \
  -H "Authorization: Bearer your-key"

Chat Completion

POST /api/chat/completions 
curl https://sy-nc.lol/api/chat/completions \
  -H "Authorization: Bearer your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sync/claude-opus-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://sy-nc.lol/api",
    api_key="your-key",
)

res = client.chat.completions.create(
    model="sync/gpt-5.5",
    messages=[{"role": "user", "content": "Hello!"}],
    stream=True,
)

for chunk in res:
    print(chunk.choices[0].delta.content, end="")

JavaScript SDK

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://sy-nc.lol/api",
  apiKey: "your-key",
});

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

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

Setup Guides

How to use sy-nc in your favorite app or IDE.

1

Download Claude Desktop

Install the desktop app at claude.com/download. This only works in the desktop app, not the browser.

2

Enable Developer Mode

Open the menu (☰) → Help → Troubleshooting → Enable Developer Mode. A new Developer option will appear in the menu.

3

Open Third-Party Inference Settings

Menu (☰) → Developer → Configure Third-Party Inference.

4

Fill in the credentials

Under Connection, select Gateway, then fill in:

Credential type Static API key
Gateway base URL https://sy-nc.lol/api
Gateway API key your-key-here
Authentication scheme bearer
5

Test and save

Click Test connection → Save changes → Apply changes. Then go back to the chat, select your model and send a message.

1

Open Settings

Go to Settings → Models → API Keys.

2

Enable OpenAI provider

Toggle on OpenAI (both options). Then fill in:

API Key your-key-here
Override OpenAI Base URL https://sy-nc.lol/api
3

Add a model

In the models list, add a custom model with the name exactly as shown, for example:

sync/claude-opus-5
4

Save and test

Save settings, select the model in the chat and send a test message.

Created by

...
...