Quickstart: Drop-in OpenAI Compatible API

Change base_url and set API key

The first step is pointing your SDK at our endpoint. Use https://api.whatisopenrouterai.com/v1 as your base URL and paste your key from the dashboard. This single change redirects all calls to our uncensored large language model while keeping your standard OpenAI-compatible headers intact.

• Generate a key via Google or email.
• Store it in your environment variables.
• Verify the key works with a simple request.

Copycurl https://api.whatisopenrouterai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set variable x to five"}]
  }'

Send requests to /v1/chat/completions

Our API accepts standard chat completions with text input and returns text output. You send a POST request to the /v1/chat/completions endpoint with your model ID and message history. The model ID is simply uncensored, which tunes the model to answer without refusals for lawful adult content.

Copyfrom openai import OpenAI

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

Stream tokens with SSE

Streaming provides real-time feedback via Server-Sent Events. Each chunk contains partial text, and the final chunk includes the token usage statistics. This approach keeps your user interface responsive while waiting for long-form responses to complete.

Copyimport OpenAI from "openai";

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

Force json_object with response_format

Use the response_format parameter set to {"type": "json_object"} to enforce strict JSON output. This ensures predictable parsing for your applications without relying on the model to guess the correct structure every time.

Use tools and tool_choice

Function calling works exactly like the standard OpenAI API. Define your tools in the request, and the model will return structured arguments when appropriate. You can force tool usage with tool_choice or let the model decide based on the context.

Check available models

Query GET /v1/models to see the single uncensored model available. This endpoint returns the model ID and details, confirming that our service is active and ready to receive requests. We do not offer multiple model choices, keeping the integration simple and focused.

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)