Uncensored API

Dolphin llm: The Uncensored API Alternative

Stop paying for refusals with our prepaid crypto-only uncensored LLM API. Get a 100k context window model that answers without locks for just $0.15 per million input tokens.

Create key View documentation

Crypto top-ups only, no cards
100k context window support
No hidden monthly fees

Test via single API call

curl https://api.llmdolphin.com/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "Set variable x to 5"}]
  }'

from openai import OpenAI

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

Core capabilities

Uncensored Model

Our open-weight model answers adult and controversial topics without standard content refusals.

OpenAI Compatible

Use standard SDKs with our base URL and your new API key.

Function Calling

Access tools and tool_choice parameters for robust automated agent workflows.

JSON Mode

Force structured output with response_format json_object for reliable parsing.

Streaming Support

Receive real-time tokens via Server-Sent Events with usage stats in the final chunk.

Privacy First

Prompts are not used for training your proprietary data or models.

Setup process

Create Account
Sign up with Google or email to receive your immediate API key.
Add Crypto Credit
Top up with USDT or USDC to start using the uncensored API.
Make Request
Send text to the chat completions endpoint and receive unrestricted responses.

Common implementations

Content Generation

Produce unrestricted creative writing and adult fiction without guardrail interruptions.

Developer Testing

Test model behavior and function calling in a clean uncensored environment.

Data Extraction

Parse large documents using the 100k context window for high accuracy.

Roleplay Agents

Run persistent characters that remember context without standard refusal triggers.

Get started in minutes with zero configuration. First, click Get API key and sign in via Google or email; your unique key appears instantly.

Secure Access — No phone number required.
Free Trial — Receive $0.50 credit valid for 7 days.
Configure SDK — Point your OpenAI-compatible client to https://api.llmdolphin.com/v1.
Generate — Send requests to POST /v1/chat/completions and receive unrestricted text output.

The Uncensored Provider Checklist: 7 Questions Before You Commit

Verify uncensored status and context limits

Check for a 100k context window and confirm no hidden monthly fees. Ensure the API is OpenAI-compatible, supporting streaming, function calling, and JSON mode. Confirm prompts are not used for training and that refunds are clear. Avoid providers with vague SLAs or limited token outputs.

Why Developers Choose the dolphin LLM for Unrestricted Generation

We provide a hosted, OpenAI-compatible API for unrestricted content generation without subscription locks or training usage of your prompts.

Function Calling with No Guardrails

Send JSON mode requests with full tool support. The model executes logic without refusing based on topic sensitivity.

Long Context Windows

Process up to 100,000 tokens per request. Ideal for indexing large memory structures or processing lengthy technical documentation in one call.

Predictable Crypto Billing

Pay only for real tokens used. Top up via USDT or USDC with bonus credits. Errors and refusals cost zero credits.

Common Traps in Uncensored LLM APIs and How We Avoid Them

Avoid Hidden Costs and Lock-Ins

Many uncensored LLM APIs charge for refusals or expire your credits monthly. We bill only for real token usage, so errors are free. Your prepaid credit never expires. You top up via crypto, keeping your workflow simple. There are no hidden monthly fees to drain your budget unexpectedly. Use our OpenAI-compatible API for consistent, predictable costs without subscription locks.

Real-World Cost Examples: Token Math for Your Budget

Our billing reflects actual token usage at $0.15 per million input tokens and $0.50 per million output tokens. A 5,000-token prompt with a 1,000-token response costs roughly $0.00125. This prepaid model ensures no hidden monthly fees or subscription locks. Errors remain free, so you only pay for valid completions. Use our calculator to estimate costs before top-up.

Developers Ask: Local Ollama vs. Cloud API for dolphin

Use Ollama locally if you need zero latency and privacy; choose our cloud API for unlimited 100k context windows without hardware constraints. Local inference demands significant GPU RAM, whereas our uncensored LLM handles heavy payloads via a simple POST request. You pay only for tokens used, avoiding idle server costs. This approach ensures consistent performance regardless of your local machine’s specifications.

Frequently asked questions

What is the dolphin LLM API endpoint and how do I connect?

Use POST /v1/chat/completions against HTTPS://api.llmdolphin.com/v1. Pass the model id "uncensored" in your request body. This standard OpenAI-compatible path ensures your existing client code works immediately without custom adapters or complex configuration steps.

Does this uncensored LLM service charge monthly fees?

No. You pay only for actual token usage with prepaid credit. Errors and refusals cost nothing. Your balance never expires, so you can top up once and use the credit whenever you need processing power for your projects.

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.

What is the context window limit for requests?

The model supports a 100,000 token context window for combined input and output. You can generate up to 16,000 tokens per request, or 2,048 if you omit the max_tokens parameter. This handles large document processing efficiently without truncation.

Is function calling supported for tool integration?

Yes. The API supports function calling with tool definitions and tool_choice parameters. You can also enforce JSON mode via the response_format field. This enables robust integration with external systems and structured data extraction workflows in your applications.

How many requests per minute are allowed per key?

You get 300 requests per minute and 8 concurrent requests per key. Each request body is limited to 8 MB. One active key per account ensures simple usage tracking and straightforward rate limit management for your automated workflows.

Generate your API key

Create key