// Reference

API Documentation_

UnchainedAPI is fully compatible with the OpenAI Chat Completions API.

// Base URL

https://llm.ai-vfx.com/api/v1

// Quick Start

01Create an account at /register
02Generate an API key from your dashboard
03Make API calls using any OpenAI-compatible SDK

// Code Examples

from openai import OpenAI

client = OpenAI(
    api_key="sk-unch-your-key-here",
    base_url="https://llm.ai-vfx.com/api/v1"
)

response = client.chat.completions.create(
    model="davidau-qwen3-30b-a3b-claude-4-5-opus-high-reasoning-2507-abliterated-uncensored-v2",
    messages=[
        {"role": "user", "content": "Hello, how are you?"}
    ],
    temperature=0.7,
    max_tokens=512,
)

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

// Connecting Agents & Clients

UnchainedAPI speaks the OpenAI protocol, so any tool with an "OpenAI-compatible" option works. Use the base URL and yoursk-unch- key from the dashboard.

Cline / Continue.dev / Roo Code (VS Code)

Provider: OpenAI Compatible
Base URL: https://llm.ai-vfx.com/api/v1
API Key: sk-unch-...
Model ID: copy slug from /models

Cursor

Settings → Models → OpenAI API Key → Override OpenAI Base URL

Base URL:  https://llm.ai-vfx.com/api/v1
API Key:   sk-unch-your-key-here
Model:     <slug from /models>

Open WebUI

Settings → Connections → OpenAI API

API Base URL:  https://llm.ai-vfx.com/api/v1
API Key:       sk-unch-your-key-here

LibreChat / BetterChatGPT / ChatBox / Jan / AnythingLLM

Pick the OpenAI or Custom OpenAI provider and plug in the same base URL and key. No extra configuration required.

Environment variables (openai SDK, LangChain, LlamaIndex)

export OPENAI_API_KEY=sk-unch-your-key-here
export OPENAI_BASE_URL=https://llm.ai-vfx.com/api/v1

// API Endpoints

GET/v1/models

List all available models. Returns OpenAI-compatible model list.

POST/v1/chat/completions

Create a chat completion. Supports streaming via SSE.

Headers

Authorization: Bearer sk-unch-your-key
Content-Type: application/json

Request Body

{
  "model": "model-slug",      // Required: model identifier
  "messages": [                // Required: conversation messages
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,         // Optional: 0.0-2.0 (default: 1.0)
  "max_tokens": 2048,         // Optional: max output tokens
  "top_p": 1.0,               // Optional: nucleus sampling
  "stream": false,             // Optional: enable SSE streaming
  "stop": null                 // Optional: stop sequences
}

POST/auth/register

Create a new account. Returns JWT access token.

POST/auth/login

GET/usage/me

Get your usage statistics and remaining credits.

// Error Codes

Code	Meaning
401	Invalid or missing API key
402	Insufficient credits -- top up your balance
404	Model not found or not active
429	Rate limit exceeded -- check Retry-After header
503	Model endpoint not available (cold start or error)