Uncensored API

Dolphin ia: The Uncensored API Alternative

Dolphin ia offers a direct uncensored ia API with a 100,000 token context window, letting developers swap in their key and start generating immediately.

100,000 token context window
Prepaid credit, no expiry
Crypto top-ups only

Try with trial credit View documentation

Test with one call

curl https://api.dolphinia.cc/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "uncensored",
    "messages": [{"role": "user", "content": "List the three main benefits of using Redis for caching."}]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.dolphinia.cc/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.dolphinia.cc/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

Uncensored Model

Answer without refusals for lawful adult or controversial topics using our tuned open-weight model.

OpenAI Compatible

Use standard Python or Node SDKs by just changing the base URL and API key.

Streaming Support

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

JSON Mode

Force structured output using the response_format parameter for reliable machine-readable text generation.

Tool Calling

Define functions and let the model decide when to call them with tool_choice.

Transparent Pricing

Pay only for tokens used with errors and refusals charged at zero cost.

Setup process

Create Account

Add Credits

Top up with USDT or USDC to receive bonus credit based on your deposit amount.

Start Coding

Update your client base_url to our endpoint and begin sending chat completion requests immediately.

Community projects

Content Generation

Generate unrestricted creative stories or articles without hitting standard content filters or refusals.

Data Extraction

Parse large documents using the extended context window for comprehensive information extraction tasks.

API Integration

Drop this provider into existing OpenAI-compatible workflows for testing or production uncensored responses.

Research Analysis

Analyze controversial topics or security research papers with a model that does not judge tone.

How much does a million tokens really cost? (Worked examples)

A million tokens cost $0.65 when input and output are equal. Your total bill depends entirely on the ratio of prompt tokens to completion tokens. We charge $0.15 per million input tokens and $0.50 per million output tokens. This transparent per-token billing means you only pay for what you use, with no hidden tiers or expiration. Errors and refusals are free.

Developers ask: Is this just another proxy or the real model?

Yes. We do not route your requests through GPT or Claude.

Our API serves a single, open-weight uncensored LLM hosted on our own infrastructure.

You get direct, transparent access to that specific model without aggregator fees.

Every request uses our dedicated servers, ensuring consistent performance and content policies.

Switch your base URL and keep your existing OpenAI-compatible client code.

You receive exactly what you see: one high-performance model, billed per token.

dolphin ia: Why developers switch from standard providers

Developers switch because dolphin ia removes subscription tiers and content filters while keeping standard OpenAI client code.

Predictable billing

You pay $0.15 per million input tokens and $0.50 per million output tokens. Prepaid credit never expires. Errors are free.

Direct access

No model routing fees. You get one uncensored model via POST /v1/chat/completions. Streaming works via SSE.

No hidden limits

Get 100k context windows. Send 16k tokens per request. Use tools and JSON mode. Just change the base URL.

The uncensored ia provider checklist: 7 things to verify

Verify these seven points before committing.

Confirm direct model access, not proxy routing.
Check per-token billing matches usage, not subscriptions.
Ensure prepaid credit never expires.
Verify streaming support via SSE.
Confirm 100k context windows.
Check crypto-only top-ups if preferred.
Ensure no model training on prompts.

These steps prevent hidden fees and data surprises.

From signup to API key: How it works in 4 steps

Visit the Get API key page and click Continue with Google or enter your email with a password.
Receive your unique API key instantly; no phone number or payment card is required.
Add crypto credit via USDT (TRC20) or USDC (Base) to activate your account.
Send requests to HTTPS://api.dolphinia.cc/v1 and pay only for tokens used at $0.15 per 1M input and $0.50 per 1M output.

Migrate from OpenAI-compatible providers in 3 steps

Switch your client code in three minutes by updating the base URL and API key. First, generate a key on our dashboard. Second, replace the existing endpoint with https://api.dolphinia.cc/v1. Third, send requests using the model id "uncensored". You now have direct access to our uncensored ia service without vendor routing fees.

Common questions

What is dolphin ia and how does it differ from standard providers?

It is an open-weight model served via an OpenAI-compatible API. You get direct access without model routing fees. The base URL is api.dolphinia.cc/v1, and you send model id uncensored for consistent, uncensored responses without hidden tiers or subscriptions.

Is this service just another proxy or the real model?

It is the real model running on our own servers. We do not route requests to other vendors like GPT or Claude. You receive direct access to our uncensored large language model with transparent per-token billing and no monthly fees.

How much does a million tokens really cost per million input tokens?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. You only pay for what you use. Errors and refusals are free. Prepaid credit never expires, and you can top up with crypto starting from twenty dollars.

Does the API support function calling and JSON mode simultaneously?

Yes, it supports both features in the same request. You can use tools, tool_choice, and response_format json_object together. Streaming via SSE also includes token usage in the last chunk. Parameters like temperature and top_p are fully available.

Can I use my existing OpenAI SDK client code with this API?

Yes, it works with the official OpenAI SDKs and any compatible client. You simply change the base_url to HTTPS://api.dolphinia.cc/v1 and update the API key. The model id is uncensored. No embeddings, images, or audio are supported.

What happens if I make a request that gets refused?

Refused requests are free. You do not pay for tokens in failed requests. The only hard content limit is sexual content involving minors. All other lawful adult, fictional, or controversial topics are answered without refusal, ensuring consistent performance.

Get your API key instantly

Try with trial credit View documentation