Integrate the uncensored LLM API

Base URL and Authentication

The base URL for all requests is https://api.llmtokenpricing.com/v1. You authenticate using your API key in the Authorization header. Obtain your key instantly via Google or email during signup. Use the key as Bearer YOUR_API_KEY in every request.

• Base URL: https://api.llmtokenpricing.com/v1
• Header: Authorization: Bearer YOUR_API_KEY

Sending Your First Request

Send a simple text completion request to POST /v1/chat/completions. The model ID is uncensored. Set max_tokens to control output length. The API returns generated text directly. Use this endpoint for basic text generation tasks.

Copycurl https://api.llmtokenpricing.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the current price per token for the largest model."}]
  }'

Python SDK Integration

Use the official OpenAI Python SDK for seamless integration. Set the base URL to our API endpoint. Pass your API key as the api_key. Initialize the client and call chat.completions.create(). This approach simplifies request handling and response parsing.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmtokenpricing.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 SDK Usage

The Node.js SDK works identically with our API. Configure the base URL and API key in the client options. Call the chat completions endpoint with your desired parameters. Handle the response object to extract generated text. This method supports modern async/await patterns.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmtokenpricing.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 Responses via SSE

Enable streaming by setting stream: true in your request. The API returns data as Server-Sent Events. Process each chunk as it arrives for real-time output. Token usage details appear in the final chunk. Streaming reduces perceived latency for long responses.

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)

Understanding Rate Limits and Costs

Rate limits are 300 requests per minute per key. Concurrency is capped at 8 simultaneous requests. The context window is 100,000 tokens total. Input costs $0.15 per million tokens. Output costs $0.50 per million tokens. Errors and refusals do not consume credits. Payment is prepaid via crypto with no monthly fees. Handle 401 errors for invalid keys and 429 for rate limits.