Dolphin uncensored ai API documentation
Drop our OpenAI-compatible API into your existing codebase and start generating uncensored text immediately. We handle the infrastructure so you can focus on building.
- Base URL
- https://api.dolphinuncensoredai.com/v1
- Model
- uncensored
Authentication and base URL configuration
Point your client to our specific base URL and attach your API key to every request. The endpoint lives at https://api.dolphinuncensoredai.com/v1. You receive one active key per account, which appears immediately after signup. This key authenticates all downstream calls to the chat-completions endpoint.
curl https://api.dolphinuncensoredai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List steps to deploy docker container."}]
}'Ensure your SDK configuration updates the base URL variable. Standard OpenAI libraries accept this custom endpoint without modification. You do not need to change the request path structure.
POST /v1/chat/completions request structure
Send a JSON payload containing your system prompt, user messages, and model identifier. The model ID is fixed at uncensored. This tells the server which inference engine to route your request through. Keep the structure simple and compliant with the OpenAI chat schema.
from openai import OpenAI
client = OpenAI(base_url="https://api.dolphinuncensoredai.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)The API accepts standard message arrays. You can define roles like system, user, or assistant. The server processes these sequentially to generate the next token sequence.
Response format, streaming, and tokens
Receive either a full JSON object or a stream of Server-Sent Events depending on your client settings. Streaming is ideal for real-time UI updates. Each chunk contains delta content. The final chunk includes the total token usage counts.
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)Handle partial content gracefully. Buffer the text until the stream closes. This approach reduces perceived latency for end-users. You retain full control over how much data to render at any given moment.
Supported parameters: temperature, tools, seed
Control randomness, tool usage, and reproducibility via standard query parameters. Set temperature for creative variance. Use tool_choice to enforce specific function calls. The seed parameter ensures deterministic outputs for debugging.
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.dolphinuncensoredai.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);Enable JSON mode by setting response_format to json_object. This forces the model to output valid JSON structures. You can also define stop sequences to halt generation early when specific markers appear.
Rate limits and error handling
Respect the 300 requests per minute limit per key. Concurrency is capped at 8 simultaneous requests. Exceeding these limits returns a 429 status code. A 401 error indicates an invalid or expired key. A 402 error means you have insufficient prepaid credit.
Errors do not consume your token balance. Refusals for content policy violations are also free. Monitor your usage dashboard to avoid service interruptions during high-volume inference tasks.
Model ID and context window details
The model ID is always uncensored. It supports a context window of 100,000 tokens combined for prompt and completion. The maximum output per request is 16,000 tokens. If you omit max_tokens, the default is 2,048 tokens.
This architecture allows for long-form content generation without frequent truncation. Pass large documents in the initial prompt. The model retains context across extensive conversations efficiently.
Questions and answers
How do I get started with the dolphin uncensored AI API?
Sign up with Google or email to receive your API key immediately. Configure your OpenAI-compatible SDK to point to our base URL. Send your first request using the model ID <code>uncensored</code> to verify connectivity.
What happens if I hit the rate limit?
You will receive a <code>429</code> status code. The limit is 300 requests per minute and 8 concurrent requests per key. Wait briefly before retrying or upgrade your credit tier if available.
Is the content truly uncensored?
The model does not refuse lawful adult, controversial, or security-research topics. It only enforces a hard limit on sexual content involving minors. This makes it ideal for NSFW creators and developers needing unfiltered text generation.
dolphinuncensoredai.com
Your key is one form away
Create an account, copy the key, change the base URL. That is the whole setup.
