Dolphin llm online API documentation

Base URL and authentication headers

The base URL for all requests is HTTPS://api.dolphinllmonline.com/v1. You authenticate by passing your API key in the Authorization header as a Bearer token. This key is generated immediately after signing up with Google or an email address. There are no monthly fees, and credit never expires. You can only have one active key per account, so generating a new key replaces the previous one.

Copycurl https://api.dolphinllmonline.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "list all endpoints"}]
  }'

First request with Python

Send your first prompt using the standard OpenAI Python SDK. Set the base_url to our endpoint and specify the model as "uncensored". The model is an open-weight variant tuned for fewer refusals on adult or controversial topics. It is not a rebrand of GPT or Llama. You can stream responses or get them all at once.

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.dolphinllmonline.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.js integration

Use the official Node.js client to integrate the API into your JavaScript or TypeScript projects. Initialize the client with your key and the correct base URL. The client handles the HTTP details for you. This approach works well for server-side applications that need to process large amounts of text without external dependencies.

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.dolphinllmonline.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 responses and token usage

Enable streaming by setting stream to true in your request. The API returns chunks as they are generated. The final chunk contains the full token usage statistics for the request. This allows you to track costs in real time. Streaming is useful for user interfaces that need to display text progressively.

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)

Rate limits and request body constraints

You are limited to 300 requests per minute per key. You can have up to 8 concurrent requests at the same time. The maximum request body size is 8 MB. The context window is 100,000 tokens for the combined prompt and completion. If you do not set max_tokens, the default output is 2,048 tokens. These limits prevent abuse while ensuring stable performance for your application.

Error handling and status codes

The API uses standard HTTP status codes to indicate success or failure. A 401 status means your API key is invalid or missing. A 402 status indicates that your prepaid credit is exhausted. You can top up with USDT or USDC via crypto. A 429 status means you have exceeded the rate limit. Handle these errors gracefully in your application logic to ensure a smooth user experience.