Dolphin ai model API Quickstart

Install your preferred SDK

Start by installing the library for your language. This package handles serialization and authentication automatically.

Run the command for your environment. It adds the necessary dependencies to your project.

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

These SDKs support the same interfaces used by major providers. You get standard error types and response objects.

Configure the base URL and key

Point your client to our hosted endpoint. Replace the default URL with our specific base address.

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

Set your API key in the environment variable OPENAI_API_KEY. The SDK reads this automatically. Authentication uses standard bearer token headers. No special headers are required.

This setup works with any OpenAI-compatible client. You avoid proxy complexity by using the standard interface directly.

Send your first completion

Make a POST request to /v1/chat/completions. The model answers freely for lawful adult use. It does not refuse controversial or explicit topics by default.

Send your prompt in the messages array. The response contains the generated text in the content field. You can adjust temperature and top_p for control.

This endpoint handles text generation only. It does not support embeddings or image generation. Keep your requests simple for best results.

Errors return standard HTTP status codes. Check the response body for details on failures.

Handle streaming responses

Enable streaming by setting stream: true. The server sends chunks via Server-Sent Events (SSE). Each chunk contains partial text.

Process each chunk as it arrives. This reduces perceived latency for long responses. The final chunk includes token usage statistics.

Streaming works with all parameters. You can stop mid-stream if needed. The connection closes cleanly after completion.

Use this for interactive applications. It provides immediate feedback to users without waiting for full generation.

Use tools and JSON mode

Define function definitions in the request. The model can call these functions based on your prompt. Use tool_choice to force specific behavior.

Enable JSON mode with response_format. The output is strictly formatted as a JSON object. This ensures reliable parsing in your code.

Combine tools with streaming for complex workflows. You can handle multiple function calls in a single turn. The model follows your schema precisely.

Test with simple tools first. Verify the output structure before integrating into production systems.

Manage token limits

The context window is 100,000 tokens total. This includes both input and output tokens. Plan your prompts accordingly.

Maximum output is 16,000 tokens per request. If you do not set max_tokens, the limit defaults to 2,048. Adjust this parameter for longer responses.

Rate limits are 300 requests per minute. You can have 8 concurrent requests per key. Exceeding these limits returns a 429 status code.

Monitor your usage via the response headers. Token counts are included in every response. This helps you stay within your prepaid credit limits.

cURL

Copycurl https://api.dolphinaimodel.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the factorial of 42"}]
  }'

Python

Copyfrom openai import OpenAI

client = OpenAI(base_url="https://api.dolphinaimodel.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

Copyimport OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.dolphinaimodel.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

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)