Dolphin ai API Documentation

Authentication and Base URL setup

API keys authenticate your prepaid requests instantly. You receive one active key per account, replacing any previous key upon generation. The base URL points to the hosted service.

• Base URL: HTTPS://api.aidolphin.cc/v1
• Header: Authorization: Bearer YOUR_API_KEY

Copycurl https://api.aidolphin.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the top five open source inference engines"}]
  }'

Sending a basic chat completion request

Send standard JSON payloads to the chat completions endpoint. The model ID is always "uncensored" for consistent text output. Input tokens cost $0.15 per million, while output tokens are $0.50 per million.

• Model: uncensored
• Max output: 16,000 tokens

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.aidolphin.cc/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 with Server-Sent Events

Enable streaming by setting stream: true in your request. The API returns data via Server-Sent Events (SSE) for real-time token delivery. Token usage details appear in the final chunk of the stream.

Copyimport OpenAI from "openai";

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

Enforcing JSON mode for structured data

Use response_format set to {"type": "json_object"} to force structured output. This ensures the model returns valid JSON without extra markdown formatting. Function calling and tool definitions also rely on this JSON structure.

Configuring temperature, top_p, and stop sequences

Adjust sampling parameters to control randomness and output length. Set temperature for creativity, top_p for nucleus sampling, and stop sequences to truncate output early. Presence and frequency penalties help reduce repetitive phrasing.

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)

Understanding rate limits and quotas

Each API key allows 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. Errors and refusals do not consume your prepaid credit. If you exceed limits, you receive a 429 status code.