OpenAI Compatible
Use the official SDKs with a simple base_url change.
Uncensored API
Dolphin ai model: Uncensored API Alternative
Get your openai compatible API key in seconds. Access an uncensored LLM with 100,000 tokens context window and pay-as-you-go pricing starting at $0.15 per 1M input tokens.
POST /v1/chat/completions works instantly
100,000 token context window
No monthly subscription fees
Test with one request
curl 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"}]
}'from 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)import 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);- $0.15per 1M input tokens
- $0.50Output tokens / 1M
- 100,000token context
- $0.50trial credit
- 300requests per minute
Core capabilities
Strictly Uncensored
Answers freely for lawful adult use without content refusals.
Transparent Pricing
Pay only for real token usage with no hidden fees.
Crypto Payments
Top up with USDT or USDC for instant credit.
High Limits
300 requests per minute with streaming support via SSE.
Private & Fast
No phone number needed and prompts are not trained.
Setup process
Create Account
Sign up with Google or email to get your key.
Add Credit
Top up via crypto or start with free trial credit.
Send Request
Call the endpoint and receive text output immediately.
Build with it
Content Generation
Create unfiltered creative writing without standard model restrictions.
Data Extraction
Parse complex text with JSON mode for reliable output.
Function Calling
Integrate tools seamlessly using standard openai compatible API structure.
Research Testing
Explore controversial topics without unnecessary safety refusals.
From signup to first answer in 60 seconds
From signup to first answer in 60 seconds
- Sign up via Google or email to instantly receive your API key.
- Add prepaid credit starting at $20 using USDT or USDC.
- Configure your client with base URL HTTPS://api.dolphinaimodel.com/v1.
- Send a POST request to /v1/chat/completions with model "uncensored".
- Receive tokenized text output immediately, ready for your application.
Common uncensored API mistakes (and how to dodge them)
Developers often assume "uncensored" means zero refusal, but our model still blocks sexual content involving minors. Avoid this by explicitly setting `temperature` and `top_p` to control creativity without triggering unexpected filters. Also, never send the same request twice; errors are free, but duplicate tokens cost money. Always check the final streaming chunk for accurate token usage. This prevents billing surprises when using the uncensored LLM endpoint.
dolphin AI model: Powering Unfiltered Text Generation
The dolphin AI model delivers a single, uncensored LLM via standard OpenAI endpoints, eliminating proxy complexity.
Content Creation
Generate unrestricted creative fiction without arbitrary topic blocks.
Research
Retrieve detailed answers on controversial subjects freely.
Testing
Stress-test prompts using the 100k context window without filter interference.
Token arithmetic: exactly what you pay per request
Costs scale strictly by token volume, not subscription tiers. A 50k input prompt plus 2k output generates 52,000 tokens, totaling $0.0078. Streaming reveals usage in the final chunk. Errors cost zero credits. You pay only for delivered text.
- Input: $0.15 per 1M tokens
- Output: $0.50 per 1M tokens
- Errors: $0.00
The developer checklist for choosing an uncensored provider
Verify token pricing and latency before integrating. Ensure the base URL supports standard OpenAI endpoints like /v1/chat/completions. Confirm the context window handles your payload size; our API supports 100,000 tokens. Check if the provider charges for refusals or errors. Validate crypto payment flexibility without forced subscriptions. Test streaming support via SSE. Verify that prompts are not used for training your data.
What developers actually ask about uncensored LLMs
Is this the official Dolphin AI model?
We are an independent provider. We serve our own uncensored model via standard OpenAI-compatible endpoints, not the vendor’s proprietary service.
Do I need a subscription?
No monthly fees exist. You pay only for tokens used with prepaid crypto credit that never expires.
Can I use standard SDKs?
Yes. Connect via /v1/chat/completions using any OpenAI-compatible client library.
How fast is streaming?
We return tokens via Server-Sent Events for immediate UI updates without waiting for full completion.
Common questions
What is dolphin AI model?
It is a single uncensored large language model accessible via standard OpenAI-compatible endpoints. You send text in and receive text out using the /v1/chat/completions endpoint with the model ID set to uncensored for direct integration.
Is the uncensored API really cheap?
Yes, input tokens cost $0.15 per million and output tokens cost $0.50 per million. Errors and refusals do not incur charges, so you only pay for the actual tokens generated in successful responses.
How do I add credit to my account?
You can top up using USDT on the TRC20 network or USDC on the Base network. The minimum deposit is $20 and the maximum is $500 per transaction, with bonus credits applied automatically.
Does it support streaming responses?
Yes, the API supports streaming via Server-Sent Events to deliver tokens in real-time. You can also access token usage statistics embedded in the final chunk of the streaming response for accurate billing tracking.
What is the context window size?
The model supports a total context window of 100,000 tokens for both prompt and completion. You can request up to 16,000 output tokens per request, or default to 2,048 if you do not specify a limit.
Can I use it with the official OpenAI SDK?
Yes, it is fully compatible with standard OpenAI SDKs and clients. You simply update your base URL to HTTPS://api.dolphinaimodel.com/v1 and provide your API key to route requests to the uncensored model.
Generate your key instantly
Sign up, copy the key, update your base URL. Setup is complete.
