Dolphin ia API Quickstart

Base URL and Authentication

Our API lives at HTTPS://api.dolphinia.cc/v1 and requires a simple API key for every request. You get this key immediately after signing up with Google or email on the dashboard, and it never expires. Unlike aggregators that hide costs behind subscriptions, we charge only for the tokens you actually consume. Keep your key secure in your environment variables, as anyone with the key can spend your prepaid credit. The service enforces a strict 300 requests per minute limit per key to maintain stability for all users.

Sending a Chat Completion Request

Make your first call using the standard chat completions endpoint with the model ID "uncensored". This request sends your prompt to our server and returns a text response without the typical refusals found in other models. You can send up to 8MB of data in a single request body, which is sufficient for most standard use cases. If you exceed the rate limit, the server returns a 429 error indicating you need to back off briefly. Always verify your response includes a valid message object before processing further.

Streaming Responses and Token Usage

Enable streaming by setting the stream parameter to true, which delivers tokens as they are generated via Server-Sent Events. This approach reduces perceived latency significantly, especially when generating long outputs up to the 16,000 token maximum per request. The final chunk in the stream contains the complete token usage statistics, allowing you to track costs in real time. You can process these events in your application to display text progressively to the user without waiting for the full generation to finish.

Function Calling and JSON Mode

Leverage native function calling by providing a tools array in your request, allowing the model to return structured data for your applications. You can also enforce strict JSON output using the response_format parameter, which is ideal for integrating with downstream systems that require precise schema adherence. The model supports tool_choice options to control whether it must call a function or can generate text freely. Use these features to build robust agents that interact with external APIs or databases without parsing messy text.

Parameters: Temperature, Top P, and Seeds

Control the creativity and randomness of the output using temperature, top_p, and seed parameters just like you would with standard OpenAI clients. A lower temperature yields more deterministic results, while a higher value encourages more diverse and creative responses. Setting a seed ensures reproducibility, which is crucial for debugging specific behaviors in your uncensored LLM workflows. You can also define stop sequences to halt generation at specific markers, giving you precise control over the output boundaries.

Limits, Errors, and Context Window

Your model supports a massive 100,000 token context window, encompassing both the prompt and the completion together. This allows you to pass large documents or extensive conversation histories without losing earlier information. If you send an invalid key, you will receive a 401 error, and a 402 error indicates your prepaid credit is exhausted. The 429 rate limit triggers if you exceed 300 requests per minute or try to make 8 concurrent requests simultaneously. Handle these errors gracefully in your code to ensure smooth operation.

cURL

Copycurl https://api.dolphinia.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the three main benefits of using Redis for caching."}]
  }'

Python

Copyfrom openai import OpenAI

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

Node.js

Copyimport OpenAI from "openai";

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

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)