Dolphin model ai API Quickstart Guide

Prerequisites: Installing the OpenAI SDK

Install the official OpenAI client library for your preferred programming language. This library handles authentication and request formatting automatically.

• Python: pip install openai
• Node.js: npm install openai

Ensure you are using a recent version of the SDK to support streaming and function calling features. Our API follows the standard OpenAI protocol closely.

Configuration: Setting your base_url and API key

Configure your client to point to our API endpoint instead of the default OpenAI servers. Use the API key generated from your dashboard.

• Base URL: https://api.dolphinmodelai.com/v1
• Model ID: uncensored

This configuration ensures all requests route to our uncensored model. The client will authenticate using your unique key for each request.

Basic Request: Sending a prompt to the uncensored model

Send a simple text prompt to receive a direct response from the model. The model answers without standard content refusals for lawful adult topics.

Here is a basic cURL example:

Copycurl https://api.dolphinmodelai.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Run unit tests for the payment module"}]
  }'

Replace <YOUR_API_KEY> with your actual key. The response contains the generated text in the choices array.

Streaming: Handling SSE responses for real-time output

Enable streaming to receive tokens as they are generated. This reduces perceived latency for long responses.

Use the Python SDK for efficient streaming:

Copyfrom openai import OpenAI

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

Each chunk contains partial text. The final chunk includes token usage statistics. This approach is ideal for chat interfaces.

Advanced Features: Function calling and JSON mode

Request structured data or tool definitions using standard parameters. Set response_format to {"type": "json_object"} for strict JSON output.

Use the Node SDK for tool integration:

Copyimport OpenAI from "openai";

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

The model supports tool_choice and tools parameters. This allows integration with external functions and APIs.

Rate Limits and Quotas: Managing 300 RPM and 8 concurrency

Monitor your request volume to avoid interruptions. The API enforces a limit of 300 requests per minute per key.

You can have 8 concurrent requests at any time. The request body must stay under 8 MB. If you exceed these limits, you will receive a 429 status code.

Use 401 errors to check key validity. Use 402 errors to check credit balance. Errors and refusals do not consume tokens.

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)