Quickstart: Integrate the uncensored API

Prerequisites and base URL

Start by navigating to the Get API key page. Sign in with Google or create an account with just an email address. You receive a single active key immediately. No phone number is required. The base URL for all requests is https://api.llmserverless.com/v1. This endpoint works with standard OpenAI SDKs. Change the base URL in your client configuration to point here. Your API key authenticates every request. Keep it secure. It is the only credential you need to access the serverless LLM infrastructure.

Authentication and headers

Every request must include the Authorization header with the value Bearer YOUR_API_KEY. This header identifies your account and tracks usage against your prepaid balance. Without this header, the server returns a 401 error. The serverless LLM API relies on this standard format. Ensure your client library injects this header automatically. If you are using a raw HTTP client, add the header manually. Incorrect keys result in immediate rejection. Valid keys allow you to proceed to content generation.

Sending your first request

Use the /v1/chat/completions endpoint to generate text. The model identifier is uncensored. It answers without content refusals for lawful adult use. Send your prompt in the messages array. The system processes the input and returns a response. This is pure inference with zero restrictions. You can adjust parameters like temperature to control randomness. The context window supports up to 100,000 tokens. This allows for long conversations or large document processing. Start with a simple prompt to verify connectivity.

Streaming responses with SSE

Set stream: true in your request body. The server sends Server-Sent Events (SSE) containing partial responses. This reduces perceived latency significantly. You receive tokens as they are generated. The final chunk includes usage statistics. This is crucial for real-time applications. Buffering issues are common in custom implementations. Handle SSE parsing carefully. The serverless LLM API ensures consistent streaming. Use this for chat interfaces where immediate feedback matters. It improves the user experience dramatically.

Function calling and JSON mode

Enable function calling by providing a tools array in your request. The model can generate structured tool calls. Use response_format: {"type": "json_object"} to force JSON output. This is useful for data extraction tasks. The uncensored LLM API supports these features fully. You can define custom tools in your schema. The model adheres to the provided structure. This ensures reliable integration with your backend logic. Test with simple tool definitions first. Complex schemas may require higher temperature values for flexibility.

Rate limits and constraints

Each API key is limited to 300 requests per minute. You can have 8 concurrent requests at any time. The request body size must not exceed 8 MB. These limits prevent abuse and ensure fair usage. If you exceed the rate limit, you receive a 429 error. Increase your concurrency if needed by using multiple keys. The serverless LLM API handles high volumes efficiently. Monitor your usage to avoid unexpected throttling. These constraints are strict but predictable. Plan your architecture accordingly for smooth operation.

cURL

Copycurl https://api.llmserverless.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Generate a list of five fictional superhero names for my app."}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.llmserverless.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.llmserverless.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)