Routerapi: The Uncensored OpenAI-Compatible Endpoint

Copycurl https://api.routerapi.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize this 1000 word article in three sentences."}]
  }'

Copyfrom openai import OpenAI

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

Copyimport OpenAI from "openai";

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

I struggled to get the API key working with my local UI. Is it just a config change?

Yes, switching to routerapi is strictly a configuration update. You only need to change your base_url to HTTPS://api.routerapi.cc/v1 and replace your existing API key. The endpoint structure matches the standard OpenAI chat-completions format exactly. This means your local UI or custom scripts require zero code modifications. You simply paste the new credentials, and the connection works immediately without complex routing logic.

routerapi: Drop-In Compatibility for Existing Code

routerapi provides a direct, OpenAI-compatible endpoint that lets you swap your base URL and keep your existing integration logic intact.

Does this work with the standard OpenAI Python SDK or do I need custom code?

Yes, it works with the standard OpenAI Python SDK. You only need to change the base URL and API key to point to our service.

What specific parameters does the endpoint support?

The endpoint supports streaming via SSE, function calling, and JSON mode. You can also adjust temperature, top_p, and stop sequences just like you would with any other provider.

How does the token context window affect my integration?

Our model handles a 100,000 token context window for both prompt and completion together. This allows you to process long documents without complex chunking strategies.

Do I need to rewrite my error handling logic?

No, the error responses follow the standard OpenAI format. Your existing retry logic and error parsing will continue to work without modification.

Is the uncensored model strictly for adult content or is it good for creative writing too?

The uncensored model excels at creative writing by removing standard refusals that often truncate narrative flow or flavor text.

• Test a 100,000-token context window with complex roleplay prompts.
• Verify JSON mode stability for structured story generation.
• Check streaming latency via SSE for real-time updates.

It handles nuanced adult themes without blocking, yet remains ideal for fiction where tone consistency matters more than rigid safety filters.

How do I top up if I don't have a credit card, and does the credit expire?

Start with a $20 whole amount. You receive +5% bonus at $50, +10% at $100, and +15% at $200. Your prepaid credit never expires, so you can pause usage anytime. Mistakes like double charges are fixed through Support. Prices are $0.15 per 1M input tokens and $0.50 per 1M output tokens.

Why is it cheaper than OpenAI or Grok, and what are the actual rate limits?

Pricing is straightforward: $0.15 per 1M input tokens and $0.50 per 1M output tokens.

A 10k input and 2k output request costs just $0.0025.

You pay for real usage; errors are free.

Rate limits allow 300 requests per minute per key.

Concurrent requests cap at eight simultaneously.

Each key handles an 8 MB request body.

No monthly fees or subscription lock-ins apply.

Who fits this service and who needs more?

Developers building chat or roleplay apps need a drop-in, uncensored endpoint without content refusals. Change base_url and keep existing code. It suits those wanting simple prepaid credit for lawful adult or creative writing use. It is not for teams needing embeddings, image generation, or strict enterprise SLAs. You also skip it if you require multi-model routing or a subscription with monthly billing cycles.