API Documentation

Base URL and Authentication

The base URL for all requests is HTTPS://api.dolphinllmuncensored.com/v1. You authenticate using a single API key generated via the Get API key page. Use either Continue with Google or an email and password to receive your key instantly. This key grants access to the uncensored model, an open-weight LLM tuned for unrestricted responses. There is no per-platform subscription fee, only prepaid credit charged by token usage. Errors and refusals incur no cost, ensuring you only pay for actual completion tokens.

• Base URL: https://api.dolphinllmuncensored.com/v1
• Auth Header: Authorization: Bearer YOUR_API_KEY

Chat Completions Endpoint

Send text prompts to the /v1/chat/completions endpoint to receive unrestricted responses. The model ID is uncensored. This endpoint accepts standard OpenAI JSON payloads and returns text output. It does not support embeddings, images, audio, or video. You must include the messages array with your prompt. The API key is passed in the HTTP header. Requests are processed on our dedicated servers. The context window supports up to 100,000 tokens total. Output is limited to 16,000 tokens per request. Use the following example to test connectivity.

Copycurl https://api.dolphinllmuncensored.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summarize the key features of the new API release"}]
  }'

Supported Parameters

Use standard parameters to control generation behavior. Set temperature for randomness and top_p for nucleus sampling. Enable json_object for structured data output. The stop sequence halts generation early. You can set a seed for reproducible results. Adjust presence_penalty and frequency_penalty to influence token repetition. Function calling is supported via tools and tool_choice. All parameters follow the OpenAI schema. This flexibility allows fine-tuning for various uncensored use cases. Configure these options within your request body. The API respects all valid OpenAI-compatible values.

Copyfrom openai import OpenAI

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

Streaming Responses

Enable streaming by setting stream: true in your request. The API returns Server-Sent Events (SSE) for each token. This reduces perceived latency for long responses. Token usage is reported in the final chunk of the stream. You can parse partial responses for real-time display. This is ideal for chat interfaces. The stream ends with an empty data object. Use your preferred client library to handle SSE. Streaming does not affect pricing or token counting. All tokens are billed normally upon completion. Process the stream events to build your UI.

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)

Node SDK Integration

Install the official OpenAI package for Node.js. Configure the base URL to point to our endpoint. Pass your API key from environment variables. Create a chat completion request with the uncensored model ID. Handle errors appropriately for network or auth issues. The SDK handles JSON serialization automatically. You can switch between streaming and non-streaming modes. The node environment supports async/await patterns. This makes integration straightforward for backend services. Test the connection before deploying to production. The SDK ensures compatibility with our API structure.

Copyimport OpenAI from "openai";

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

Rate Limits and Errors

Rate limits are set to 300 requests per minute per key. You can have up to 8 concurrent requests active simultaneously. The request body size is limited to 8 MB. If the API key is invalid, you will receive a 401 error. A 402 error indicates insufficient prepaid credit. Top up via crypto to resume service. A 429 error signals rate limit exhaustion. Wait before retrying or upgrade your usage tier. The context window is 100,000 tokens. Refusals for minor content are free. Errors do not consume your credit balance. Monitor your usage via the dashboard.