Dolphin Uncensored API Documentation

Base URL and Authentication

Start by pointing your client to https://api.openrouterdolphinuncensored.com/v1 and passing your key in the Authorization header. We issue a single active key per account that you generate via Continue with Google or email on the Get API key page. Send Authorization: Bearer YOUR_API_KEY with every request to access the uncensored model.

• Base URL: https://api.openrouterdolphinuncensored.com/v1
• Auth: Bearer token in the Authorization header
• Model ID: uncensored

First Request

Make a standard chat completion call to get immediate, uncensored text output. This endpoint works with any OpenAI-compatible SDK by simply updating the base URL and API key. You send a user prompt and receive a direct response from the Dolphin LLM. The model does not refuse lawful adult or controversial topics, providing true uncensored responses for your use case.

Copycurl https://api.openrouterdolphinuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "What is the current status of the API server?"}]
  }'

Python SDK Integration

Install the official OpenAI Python library and configure it to point at our base URL. This allows you to use familiar methods like chat.completions.create() to interact with the uncensored AI API. Set the base_url and api_key attributes before making calls. This approach ensures consistent quality and privacy while leveraging your existing Python workflows for unrestricted AI generation.

Copyfrom openai import OpenAI

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

Node SDK Integration

Initialize the Node.js OpenAI client with our specific base URL and your API key. This method is ideal for server-side applications or Node-based environments requiring direct uncensored LLM access. Import the client, configure the credentials, and invoke the chat completions endpoint. The library handles the HTTP requests, returning structured JSON responses that you can process directly in your JavaScript code.

Copyimport OpenAI from "openai";

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

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)