Quickstart: Integrate the llm api router

Configuration: Base URL and API Key

Set your client to use the official base URL and your unique key. Point your OpenAI-compatible SDKs to HTTPS://api.llmapirouter.com/v1 and assign the key retrieved from your dashboard. This single change directs all requests to our uncensored model without modifying your application logic.

Basic Text Completion

Send a standard chat completion request to generate text responses. The endpoint accepts a list of messages and returns the model's output in JSON format.

Use this structure to start your first generation:

Copycurl https://api.llmapirouter.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all npm packages"}]
  }'

Streaming Responses (SSE)

Enable streaming by setting the stream parameter to true. This returns Server-Sent Events, allowing you to display tokens as they generate rather than waiting for the full response.

Implement the stream flag in your SDK client:

Copyfrom openai import OpenAI

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

Function Calling (Tools)

Define tools in your request to enable the model to call external functions. Pass a list of tool definitions and specify tool_choice to control when the model uses them.

Configure tools using the Node SDK:

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llmapirouter.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);

JSON Mode Response Format

Force the model to output valid JSON by setting response_format to {type: "json_object"}. This ensures structured data output for reliable parsing in your application.

Enable JSON mode in your streaming client:

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)

Rate Limits and Constraints

Each API key supports 300 requests per minute and 8 concurrent requests. The request body must stay under 8 MB, and you can specify up to 100,000 tokens for the combined prompt and completion. Errors return standard HTTP codes: 401 for invalid keys, 402 if credit is exhausted, and 429 when you exceed the rate limit.