OpenAI-Compatible API Documentation

Base URL and Authentication

Start every request by pointing your SDK to https://api.openclawuncensored.com/v1 and passing your key in the Authorization header. This base URL works with the official OpenAI SDKs and any compatible client without requiring custom middleware. You get one active key per account, which appears immediately after you sign in with Google or an email address.

Chat Completions Endpoint

Use the POST /v1/chat/completions endpoint to send messages and receive raw text responses. This is a text-in, text-out API that serves a single uncensored model tuned to answer without content refusals for lawful adult use. You can configure the response with parameters like temperature, top_p, and stop sequences. The model does not act as a generic wrapper for GPT or Claude; it is a distinct open-weight model running on our servers. Use this endpoint for agents that need to execute tasks or pipe data through your workflow without hitting standard safety filters.

Models List Endpoint

Query the available models by sending a GET /v1/models request to the base URL. The response lists the model ID you must use for completions: uncensored. This ID is required for all chat requests and ensures you are interacting with the correct uncensored large language model. The endpoint confirms the model's capabilities, such as its 100,000-token context window. There are no other models available for routing, and no fine-tuning or embedding endpoints exist for this service.

Streaming and Function Calling

Enable streaming by setting stream: true in your request body to receive Server-Sent Events (SSE) as tokens are generated. This is critical for agents that need to display progress or pipe output to other tools in real time. You can also use function calling with the tools parameter to let the model output structured arguments for your workflow. JSON mode is available via response_format: {"type": "json_object"} for reliable parsing. The final chunk of the stream contains the total token usage for billing purposes.

Token Limits and Rates

The model supports a context window of 100,000 tokens for both the prompt and the completion combined. You can request up to 16,000 tokens per output, or 2,048 if you do not specify max_tokens. Requests are limited to 300 per minute per key, with a maximum of 8 concurrent requests. The request body size cannot exceed 8 MB. If you exceed these limits, you will receive a 429 status code. Errors and refusals do not consume your prepaid credit.

Errors and Billing

Handle errors by checking the HTTP status code and the error message in the response body. A 401 error indicates an invalid or expired API key. A 402 error means your prepaid credit is exhausted; you can top up using crypto (USDT on TRC20 or USDC on Base) starting from $20. You receive bonus credit for larger deposits: +5% from $50, +10% from $100, and +15% from $200. Mistakes like double charges are fixed via the Support page, and credit never expires. There are no hidden fees or per-request costs beyond the token usage.

cURL

Copycurl https://api.openclawuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "what is the current temperature outside"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openclawuncensored.com/v1", api_key="YOUR_KEY")

resp = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Summarise this thread without softening it."}],
)
print(resp.choices[0].message.content)

Node.js

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openclawuncensored.com/v1", apiKey: process.env.API_KEY });

const resp = await client.chat.completions.create({
  model: "uncensored",
  messages: [{ role: "user", content: "Draft a villain monologue for my game." }],
});
console.log(resp.choices[0].message.content);

Streaming

Copystream = client.chat.completions.create(
    model="uncensored",
    messages=[{"role": "user", "content": "Tell the story in second person."}],
    stream=True,
)
for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)