Open-weight inference

Dolphin ai chat: The Uncensored LLM API for Developers

Drop uncensored LLM code into your existing stack with our 100k context window API that refuses nothing for lawful adult content.

$0.15 per 1M input tokens
100,000 token context window
OpenAI SDK compatible

Claim trial key View documentation

$0.15per 1M input tokens

$0.50Output tokens / 1M

100,000token context

$0.50trial credit

300requests per minute

Test with a single request

curl https://api.dolphinaichat.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Summit the daily server load statistics for the last week"}]
  }'

from openai import OpenAI

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

https://api.dolphinaichat.com/v1uncensored

Features included

Uncensored Inference

Get raw text responses without content filters for creative, NSFW, or controversial topics.

Standard Compatibility

Use your existing OpenAI SDK clients by simply changing the base URL and API key.

No Hidden Fees

Prepaid credit lasts forever and errors cost nothing because you only pay for real tokens.

Streaming Support

Receive token usage and text updates via SSE streams for real-time application integration.

Function Calling

Enable tools and tool_choice parameters for structured data extraction and automated agent workflows.

Privacy First

Prompts are not used for training your data and no phone number is required for signup.

Setup process

Generate Key
Sign up with Google or email to receive your single active API key instantly.
Add Credit
Top up with USDT or USDC to start paying only for the tokens you actually use.
Send Request
Point your client to our base URL and send prompts to the uncensored model endpoint.

Use cases

Creative Writing

Generate unrestricted fictional narratives and character dialogues without hitting sudden content policy walls.

Code Generation

Debug complex logic or generate large code blocks within the 100k context window limits.

Data Extraction

Parse structured JSON responses from unstructured text using the built-in JSON mode feature.

Adult Content

Process lawful adult themes in your applications without paying extra for premium uncensored tiers.

6-Point Checklist for Choosing an Uncensored LLM Provider

Verify the model ID, not just the endpoint. We serve the specific "uncensored" model directly, ensuring zero vendor lock-in and predictable behavior without hidden routing layers. Check the context window limits carefully; our API supports 100,000 tokens, preventing early truncation during complex tasks. Confirm pricing transparency by examining raw token rates and whether errors incur charges. Our prepaid credit covers real usage only, with errors remaining free. Ensure the API key system allows immediate rotation without downtime. Finally, test the streaming response format to guarantee real-time token delivery via SSE for your applications.

dolphin AI chat: Use Cases for Unrestricted Text Generation

Our uncensored LLM API powers unrestricted text generation by removing standard content filters.

NSFW Creative Writing

Authors generate adult fiction without unexpected refusals blocking their narrative flow.

VR Character Integration

Developers deploy uncensored AI personalities directly into virtual reality environments.

Social Media Automation

Bots post unfiltered commentary across platforms without needing constant moderation overrides.

Security Research

Teams test prompt injection attacks using models that do not refuse controversial topics.

Start generating uncensored responses immediately by following these four simple steps.

Sign Up: Use your Google account or email to create an account instantly; no phone number is required.
Get Your Key: Retrieve your unique API key from the dashboard to authenticate your requests.
Configure SDK: Update your OpenAI-compatible client with the base URL and your key.
Send a Request: Post to the chat completions endpoint and receive streaming tokens.

Every new account receives $0.50 in trial credit to test the service right away.

Dolphin vs. Typical Alternatives: 5 Concrete Differences

Feature	Typical Aggregators	Our API
Model Choice	Multiple models	Single uncensored model
Pricing	Complex tiers	$0.15 input, $0.50 output per 1M tokens
Payment	Crypto (USDT, USDC)	Crypto only
Refusals	Common	None for lawful use
Lock-in	Vendor specific	OpenAI compatible

Real Developer Questions: Debugging, Limits, and Latency

Debugging missing citations in parallel chat API responses?

We do not use citations. Our model generates text directly without reference anchors.

Why do refusals happen?

Minor sexual content is strictly blocked. Everything else passes.

What are the limits?

You get 300 requests per minute and a 100k context window. Output caps at 16k tokens.

Latency depends on server load.
Streaming via SSE works normally.

Cost Calculator: Token Arithmetic for Your Use Case

Cost depends entirely on input and output volume. Each million input tokens cost $0.15, while outputs charge $0.50 per million. A 10k token prompt paired with a 2k token response consumes roughly $0.0015 plus $0.001. Streaming responses via SSE ensure you only pay for delivered tokens, eliminating waste from truncated generation errors.

Common questions

What is dolphin AI chat and how does it differ from standard LLMs?

It is an uncensored LLM API. The model does not refuse lawful adult topics. It uses a single endpoint. You get raw token efficiency. Standard OpenAI SDKs work with base_url changes. No complex routing logic required for integration.

Does the API support function calling and JSON mode?

Yes. It supports function calling and JSON mode. You can use tool_choice parameters. Response format accepts json_object. Streaming via SSE works. Token usage appears in the last chunk. All standard parameters like temperature are available.

How much does it cost per million tokens?

$0.15 for input, $0.50 for output. Errors are free. Prepaid credit charges real usage. No monthly fees apply. Credit never expires. You pay only for tokens sent. This model offers transparent pricing without hidden subscription costs.

Can I use cryptocurrency to top up my account?

Yes. USDT (TRC20) and USDC (Base) work. Minimum top-up is $20. Bonus credit increases at higher tiers. Sign-up takes seconds. Trial credit requires no payment method. Crypto payments are the only option.

What is the maximum context window size?

100,000 tokens combined. Prompt plus completion share this limit. Max output is 16,000 tokens. Default max tokens is 2,048. Streaming works within these bounds. Large documents fit easily. Long conversations maintain context effectively without truncation errors.

Which payment methods do you accept?

Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.

Retrieve your API key

Claim trial key