What is the context window for the dolphin AI model?

The model supports a 100,000-token context window, including both prompt and completion tokens. You can set a maximum output of 16,000 tokens per request. This allows for deep context analysis in a single call.

Does the dolphin AI sin censura apk API support function calling?

Yes, the API supports function calling with tools and tool_choice parameters. You can also enforce JSON mode using the response_format field. This enables structured data output for your applications.

How do I handle rate limits on the uncensored AI API?

You are limited to 300 requests per minute and 8 concurrent requests per key. If you exceed these limits, you receive a 429 status code. Implement exponential backoff in your client to handle these errors gracefully.

Документація API - Сумісні кінцеві точки OpenAI

Authentication and Base URL

Your API key grants access to the uncensored AI model. Send it in the Authorization header as a Bearer token. All requests route through https://api.dolphinaisincensuraapk.com/v1. This base URL works with any standard client that supports OpenAI-compatible endpoints. Keep your key secure and rotate it if necessary.

Chat Completions Endpoint

Send messages to generate text responses. Use the POST method on the /v1/chat/completions endpoint. Pass your messages as a JSON array with role and content fields. The model ID is uncensored. This single model handles all your text generation needs without extra routing fees.

curl https://api.dolphinaisincensuraapk.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Calculate the sum of 2 plus 2"}]
  }'

Node SDK Integration

Use the OpenAI Node.js package for JavaScript environments. Set the apiKey and baseURL properties before making requests. This setup ensures compatibility with existing codebases that already use OpenAI clients. It provides a familiar interface for web developers building uncensored AI applications.

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.dolphinaisincensuraapk.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 Responses and Token Usage

Enable streaming by setting stream: true in your request. You will receive a sequence of Server-Sent Events (SSE) chunks. The final chunk contains the token usage statistics for accurate billing. This allows real-time display of generated text without waiting for the full 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)

Rate Limits and Quotas

Each API key allows 300 requests per minute and 8 concurrent requests. The maximum request body size is 8 MB. You receive a 401 error for invalid keys, 402 if credit is insufficient, and 429 when exceeding limits. Errors and refusals do not consume tokens from your prepaid balance.

Python

from openai import OpenAI

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

API Documentation