Anonymous llm API Quickstart

Base URL and Authentication

Your API key authenticates every request to the https://api.llmanonymous.com/v1 base URL. Generate a key via the dashboard using Google or email, then pass it in the Authorization header. This works with any OpenAI-compatible client by updating the base URL and key configuration.

Copycurl https://api.llmanonymous.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the root cause of 503 errors in this log?"}]
  }'

Keep your key secure. The dashboard shows your single active key, and generating a new one replaces the old immediately.

Chat Completions Endpoint

Send text prompts to the uncensored model via POST /v1/chat/completions. Use the model ID uncensored for responses without content refusals on lawful adult topics. The API accepts standard message arrays with role and content fields.

Copyfrom openai import OpenAI

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

Errors and refusals are free, so you only pay for actual token usage. The model handles complex instructions and long contexts effectively.

Model Listing Endpoint

Retrieve available models using GET /v1/models. This returns the uncensored model ID, confirming your connection to the correct service. Use this to verify your API key permissions before sending heavy workloads.

Copyimport OpenAI from "openai";

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

Unlike multi-vendor gateways, we serve one tuned open-weight model. Check the pricing page for token rates, as this endpoint does not return billing details.

Streaming and Token Usage

Enable streaming by setting stream: true to receive Server-Sent Events (SSE). Token usage metrics appear in the final chunk of the stream, allowing you to track costs in real-time. This reduces perceived latency for long outputs.

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)

Parse the SSE data carefully to reconstruct the full response. The API returns partial tokens as they are generated, providing immediate feedback for interactive applications.

Parameters: Temperature, Top-P, and Seed

Control creativity with temperature and top_p. Set seed for reproducible outputs during debugging. These parameters adjust how the model selects tokens from its probability distribution. Higher temperatures increase randomness for diverse content.

Copycurl https://api.llmanonymous.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the root cause of 503 errors in this log?"}]
  }'

Use stop sequences to truncate responses early. The model respects these constraints, allowing precise control over output length and format without extra processing.

JSON Mode and Function Calling

Force structured output using response_format: {"type": "json_object"} for reliable JSON parsing. Enable function calling with tools and tool_choice to integrate external services. The model supports tool definitions with function names, descriptions, and parameter schemas.

Copyfrom openai import OpenAI

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

Combine JSON mode with streaming for real-time structured data ingestion. This approach works well for data extraction tasks requiring consistent formatting across multiple requests.