Uncensored API Quickstart

Installation and setup

Configure your environment with the base URL and API key. This uncensored API uses the standard /v1/chat/completions endpoint. Change the base_url in your SDK client and provide the key from the dashboard.

• Base URL: https://api.openrouterapipricing.com/v1
• Model ID: uncensored

Authentication relies on a single key per account. You receive the key immediately after signup via Google or email. No phone number is required.

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

Basic chat completion

Send a standard chat completion request to get text responses. The model accepts text input and returns text output. Use the uncensored model ID for unrestricted generation.

You can control the response length and style using standard parameters. The API does not support embeddings or image generation. Requests are charged strictly on token usage.

Streaming responses

Enable streaming to receive tokens in real-time. This reduces perceived latency for your users. The final chunk contains the total token usage for the request.

Streaming works with all standard SDKs. Handle the stream events to update your UI incrementally. This is ideal for chatbot interfaces.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.openrouterapipricing.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 and tools

Define tools in your request to allow the model to call functions. Use the tools parameter to specify schemas. The model returns tool calls when appropriate.

Set tool_choice to enforce function usage. This works with the standard OpenAI-compatible format. Parse the tool calls in your application logic.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.openrouterapipricing.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

Force the model to output valid JSON. Set response_format to {"type": "json_object"}. This ensures structured data for your applications.

JSON mode improves reliability for data extraction tasks. The model adheres to the schema you provide. Use this for consistent parsing.

Parameters, limits, and errors

Control generation with temperature, top_p, and stop sequences. The context window is 100,000 tokens total. Max output is 16,000 tokens per request. Errors like 401 (invalid key) or 402 (no credit) are free. 429 indicates rate limits. Requests are limited to 300 per minute. The request body must be under 8 MB.

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)