OpenAI Compatible
Use official SDKs by changing the base URL to our hosted endpoint.
Uncensored API
Dolphin series ai: The Uncensored API Alternative
Get an uncensored AI model via our OpenAI compatible API, featuring a 100,000 token context window and transparent per-token billing.
- POST /v1/chat/completions endpoint
- $0.15 per 1M input tokens
- No model routing or SLA
curl https://api.dolphinseriesai.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List the three key features of the current API tier."}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.dolphinseriesai.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)import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.dolphinseriesai.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);$0.15per 1M input tokens
$0.50Output tokens / 1M
100,000token context
$0.50trial credit
300requests per minute
Core features
Raw Output
No content filters refuse lawful adult topics or controversial security research.
Streaming Support
Receive tokens via Server-Sent Events with usage data in the final chunk.
Function Calling
Support for tools, tool_choice, and JSON mode in requests.
Large Context
Handle up to 100,000 tokens combined for prompt and completion.
Crypto Payments
Top up with USDT or USDC without needing a credit card.
Setup process
Create Account
Sign up with Google or email to get your API key instantly.
Add Credits
Deposit crypto to start generating text with no monthly subscription fees.
Call Endpoint
Send POST requests to /v1/chat/completions using your preferred client.
Community projects
NSFW Creative Writing
Generate unrestricted adult content without unexpected refusal blocks or filters.
Coding Assistance
Get raw code outputs for development tasks without safety interruptions.
Data Extraction
Parse large documents using the extensive context window for accuracy.
Research Testing
Test model behavior on controversial topics without policy-based censorship.
Why developers choose dolphin series AI for unrestricted generation
We deliver raw, uncensored text output via a direct endpoint with zero content filters for lawful adult use.
NSFW Creative Writing
Generate explicit narratives without unexpected refusals or soft filters blocking creative freedom.
Uncensored Coding Assist
Get unfiltered code suggestions and technical explanations that ignore standard corporate politeness rules.
Unfiltered Chatbot Data
Train or test models on diverse, unmoderated human dialogue without artificial safety constraints.
Security Research
Probe model boundaries and edge cases in a pure, unadulterated inference environment.
Migrate from OpenAI or Ollama in three simple steps
Switch your client code to our endpoint in minutes by updating just two fields.
- Update Base URL: Point your SDK to
https://api.dolphinseriesai.com/v1. - Set Model ID: Change the model string to
uncensoredin your requests. - Swap API Key: Replace your current key with the one from your dashboard.
Streaming, tools, and JSON modes work immediately with zero config changes.
From signup to inference: how the API works
Get your key and start generating
- Create an account. Click "Get API key" and sign in with Google or an email and password. No phone number required.
- Get your credentials. Your unique API key appears immediately on the screen. Save it securely.
- Send a request. Point your OpenAI-compatible client to HTTPS://api.dolphinseriesai.com/v1. Use model id "uncensored" and POST to /v1/chat/completions.
- Receive text. Get raw, unfiltered text output. Streaming is supported via Server-Sent Events.
Common pitfalls in uncensored LLM APIs and how we avoid them
Most uncensored LLM APIs hide usage behind subscriptions or route your prompts through third parties. We avoid these traps by offering a direct, single-model endpoint with transparent per-token billing. You pay only for real tokens, and errors are free. We never train on your data or lock you into monthly fees. Our API supports OpenAI-compatible SDKs with zero model routing, ensuring consistent output for NSFW or unrestricted coding tasks without hidden infrastructure surprises.
Frequently Asked Questions
The API supports streaming, function calling, and JSON mode via the standard chat-completions endpoint. Each account receives one active API key; generating a new key immediately invalidates the previous one. Input tokens cost $0.15 per million, while output tokens are $0.50 per million. Errors incur zero charges, and prepaid credit never expires. You can top up using USDT (TRC20) or USDC (Base), starting from $20. A $0.50 trial credit activates instantly upon signup, requiring no payment method.
Checklist for choosing an uncensored AI provider
Uncensored LLM Provider Checklist
- Verify endpoint compatibility: Ensure the service exposes
POST /v1/chat/completionsfor direct OpenAI SDK migration. - Check token billing: Confirm charges apply only to real tokens used, not fixed subscription fees.
- Confirm payment methods: Look for crypto-only options like USDT or USDC without card requirements.
- Review data privacy: Verify that prompts are not used for training your data.
- Test latency limits: Check if the provider supports streaming via SSE for real-time usage.
Common questions
What is dolphin series AI and how does it differ from standard models?
It is an uncensored AI model serving unrestricted text output for lawful adult use. Our API lacks content filters while maintaining high quality. You pay per token with no monthly subscription required for access.
Does the API support streaming responses for real-time applications?
Yes. We support streaming via Server-Sent Events to deliver tokens progressively. You receive token usage details in the final chunk. This ensures low latency for chat interfaces and real-time generation workflows.
What payment methods are accepted for topping up credit?
We accept crypto only, specifically USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is allowed. Bonus credit applies automatically based on your top-up tier amount.
Is there a free trial available for new accounts?
Yes. Every new account receives $0.50 of trial credit valid for seven days. You can test the uncensored capabilities immediately before committing to prepaid usage.
What is the maximum context window supported by this API?
The context window is 100,000 tokens for both prompt and completion combined. You can request up to 16,000 tokens per output. This allows for extensive document processing and long conversation histories.
Do you use user prompts for training the model?
No. Prompts are not used for training your data. Your inputs remain private and are processed solely for generating the requested text response. This ensures your data stays within your control.
Get your API key
Sign up, copy the key, update the base URL. That is all you need.
