What is the openrouter API rate limit equivalent for this direct API?

You get 300 requests per minute and 8 concurrent requests per API key. This is a direct connection, so you avoid the unpredictable upstream proxy errors common with other services.

Does the uncensored model refuse adult content?

No, it does not refuse lawful adult, fictional, or controversial topics. The only hard limit is sexual content involving minors, which is always refused.

What happens if I hit my rate limit?

You receive a 429 error. Your prepaid credit is not charged for failed or rate-limited requests. You can wait for the window to reset or upgrade your throughput by getting a new key if needed.

Quickstart: Uncensored OpenAI-Compatible API

Install the OpenAI SDK

Install the standard library for your preferred language to handle requests immediately.

This library provides the necessary clients to communicate with our OpenAI-compatible endpoint. It manages authentication headers and response parsing for you.

Python: pip install openai
Node.js: npm install openai

No special drivers are required. The SDK handles the underlying HTTP connections efficiently.

Configure Base URL and Key

Point your client to our specific base URL and set your API key to bypass standard gateway restrictions.

Use https://api.openrouterapiratelimit.com/v1 as your base URL. This directs traffic to our direct servers instead of a proxy layer. Your API key authenticates your prepaid credit account.

We support standard headers. Pass your key in the Authorization header. This ensures your requests go straight to the uncensored model without intermediate hops.

Send Your First Uncensored Request

Send a POST request to /v1/chat/completions with the model ID uncensored to generate text without content filters.

Our model does not refuse lawful adult, fictional, or controversial topics. It answers directly based on your prompt.

curl https://api.openrouterapiratelimit.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Send a test message to verify endpoint availability."}]
  }'

Replace YOUR_API_KEY with your actual key. The response returns the generated text in the choices array. This confirms the model is working and uncensored.

Enable Streaming for Real-Time Output

Set stream: true to receive tokens as they are generated, reducing perceived latency for long responses.

Streaming allows your application to display output progressively. This is critical for chat interfaces where users expect instant feedback.

from openai import OpenAI

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

The SDK yields chunks as they arrive. Process each chunk to update your UI. The final chunk contains the total token usage for the request.

Use Tools and JSON Mode

Utilize function calling or strict JSON mode for structured data extraction from your uncensored model.

Our API supports standard OpenAI tool definitions. Define your tools in the request and let the model decide when to call them. Alternatively, use response_format: {"type": "json_object"} for deterministic JSON output.

import OpenAI from "openai";

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

This ensures your downstream systems receive parseable data. The model adheres to the schema you provide. Use this for reliable integration into your pipelines.

Check Token Usage and Limits

Monitor your usage against our 100,000 token context window and 300 requests per minute limit.

Your context window includes both prompt and completion tokens. Max output per request is 16,000 tokens. If you do not set max_tokens, it defaults to 2,048.

Rate limits are strict but predictable. You get 8 concurrent requests per key. Errors like 401 (invalid key) or 402 (no credit) are free. 429 errors indicate you hit the rate limit. Check the response headers for remaining quota.

Streaming

stream = 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)