Uncensored API
OpenRouter openai compatible uncensored api
Drop an openrouter openai compatible endpoint into your code. Get a dedicated uncensored LLM with 100,000 token context and zero proxy routing.
- 100k token context window
- Crypto only.
- Function calling supported
Test with one call
curl https://api.openrouteropenaicompatible.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "list all installed npm packages in current directory"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.openrouteropenaicompatible.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.openrouteropenaicompatible.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);Core capabilities
Direct endpoint
POST /v1/chat/completions with no model routing layers.
Function calling
Full tool support for structured data extraction.
JSON mode
Force json_object responses for reliable parsing.
Streaming
SSE support with token usage in last chunk.
Crypto payments
Top up with USDT or USDC only.
No subscriptions
Pay per token. Credit never expires.
Setup guide
Create account
Sign up with Google or email.
Get key
Receive your API key immediately.
Top up
Add crypto credit to start.
Community projects
Content generation
Produce uncensored text without refusal filters.
Code assistants
Use function calling for complex tasks.
Data extraction
Parse structured JSON with high accuracy.
Long context
Process documents up to 100k tokens.
Why developers choose an openrouter openai compatible alternative
Dedicated infrastructure
We run a single uncensored model on our own servers, not a proxy routing traffic between vendors. This guarantees direct control and transparent pricing.
Zero code changes
Our API accepts standard chat-completions requests. You update the base URL and API key to switch from OpenAI without modifying your application logic.
Transparent costs
You pay only for tokens used. Prepaid credit never expires, and errors are free.
Crypto payments
Top up via USDT or USDC with bonus credit. No subscriptions or hidden fees.
Cost breakdown: 100k context vs standard output
Our pricing scales with actual usage, not model tiers. You pay $0.15 per 1M input tokens and $0.50 per 1M output tokens. A 100,000 token context window with a standard 2,048 token completion costs just $0.026. Errors incur no charge. This transparent arithmetic ensures you only pay for what you consume, avoiding hidden subscription fees.
Common integration pitfalls and how to avoid them
Switching from OpenAI to an openrouter openai compatible API requires updating your base URL and model ID. Many developers forget that our dedicated uncensored LLM uses the model ID "uncensored" instead of generic names like GPT-4. Also, our context window spans 100,000 tokens, so adjust your logic accordingly. Ensure you handle streaming via SSE for real-time token delivery, as our endpoint supports this natively without extra configuration.
Developers ask: Does it support function calling?
Yes. The API supports function calling via the standard tools and tool_choice parameters, ensuring compatibility with existing OpenAI SDK clients.
- Define tools in your request payload.
- The model returns structured tool calls.
- Execute them on your server.
This feature works alongside JSON mode for strict output formats. You can use the official OpenAI SDKs by simply updating the base_url to our endpoint. No code changes are needed for standard integrations.
Get your uncensored API key in 3 steps
- Sign up instantly. Use Continue with Google or create a standard email and password account. We do not require a phone number, so you can start testing your new uncensored LLM immediately without verification delays.
- Grab your key. Your unique API key appears on the screen right after registration. Copy it now because we do not store it for later retrieval, ensuring your credentials stay private.
- Send your first request. Point your existing OpenAI-compatible SDK to our base URL and send a
POSTto/v1/chat/completions. The model responds with text without content refusals.
Signs this is a dedicated model, not a proxy
Why developers choose an openrouter openai compatible alternative
This infrastructure runs a single uncensored model directly on its own servers, eliminating third-party routing hops that complicate debugging and pricing. Unlike proxy services that aggregate diverse vendors, we control the entire stack from silicon to response. This design guarantees predictable latency, transparent token billing, and consistent behavior without hidden vendor markups or model switching surprises during high traffic spikes.
| Feature | Dedicated Infrastructure | Typical Proxy |
|---|---|---|
| Routing | Single model path | Multi-vendor aggregation |
| Pricing | Transparent per token | Hidden markups |
Common questions
What makes openrouter openai compatible your API different from standard proxies?
We run a single, dedicated uncensored model on our own infrastructure, not a routing layer. This ensures direct control, transparent token pricing, and zero code changes when switching from OpenAI SDKs to our endpoint.
Does the API support streaming responses?
Yes. We support streaming via Server-Sent Events (SSE). Token usage details are included in the final chunk, allowing your application to update progress in real-time without waiting for the entire completion.
Can I use my existing OpenAI SDK code?
Yes. The endpoint is fully OpenAI-compatible. You only need to change the base URL and provide your API key. All standard parameters like temperature, top_p, and stop sequences work exactly as documented.
What is the context window size?
The model supports a 100,000-token context window for both prompt and completion combined. You can specify a max output of 16,000 tokens, or fall back to 2,048 tokens if you do not set a limit.
How do I top up my credit?
We accept crypto only: USDT on TRC20 or USDC on Base. Top-ups range from $20 to $500. You receive bonus credit starting at +5% for $50 up to +15% for $200 contributions.
Is there a free trial available?
Yes. Every new account receives $0.50 of trial credit valid for 7 days.
Unlock your API key
Register, retrieve your key, and update the endpoint URL. Complete integration.
Start now