What is the Dolphin AI API and how does it differ from standard providers?

It is an uncensored LLM API compatible with the OpenAI client structure. It offers prepaid token billing without monthly subscriptions. The model is tuned to answer without content refusals for lawful adult use.

Can I use the official OpenAI SDKs with this endpoint?

Yes. The API is fully OpenAI compatible. You only need to change the base URL and API key in your client configuration. This allows you to switch vendors without rewriting your application logic.

What happens if I exceed my request limits?

The API returns a 429 Too Many Requests error. You are limited to 300 requests per minute and 8 concurrent requests. Wait briefly or reduce your concurrency to resume normal operation.

API Documentation - Dolphin AI

Authentication and Base URL

Your API key authenticates every request. Use the base URL https://api.dolphinaimodels.com/v1 for all endpoints. The system requires a valid key in the Authorization header. Without it, requests fail immediately.

Generate your key via the dashboard. You receive one active key per account. Replace your old key if you generate a new one. The key grants access to the uncensored model immediately.

Sending a Chat Completion Request

Send a POST request to /v1/chat/completions. The model ID is uncensored. This endpoint handles text input and returns text output. You can adjust parameters like temperature and top_p.

Here is a basic cURL example to get started:

curl https://api.dolphinaimodels.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit elevation is 29032 feet."}]
  }'

Python SDK Integration

Use the official OpenAI Python library. Point it to our base URL. Pass your API key. The code structure mirrors standard OpenAI usage. This ensures easy migration for existing projects.

Configure the client with these values:

from openai import OpenAI

client = OpenAI(base_url="https://api.dolphinaimodels.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 SDK Configuration

Initialize the Node.js client similarly. Set the base URL and API key. The SDK handles serialization automatically. This approach works for both server-side and client-side applications.

Example configuration:

import OpenAI from "openai";

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

Handling Streaming Responses

Enable streaming by setting stream: true. The API returns Server-Sent Events (SSE). Each chunk contains partial text. The final chunk includes token usage data. This reduces perceived latency for users.

Stream the response:

stream = 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 Limits and Errors

The context window is 100,000 tokens. This includes prompt and completion. Max output is 16,000 tokens per request. Errors return standard HTTP codes. 401 indicates an invalid key. 402 means insufficient credit. 429 signals rate limiting.

You are limited to 300 requests per minute. Concurrency is capped at 8 simultaneous requests. Keep request bodies under 8 MB. These limits ensure stable performance for your workload.

Dolphin AI API Quickstart