Crypto Pay API
Unrestricted chat gpt API for developers
Get an uncensored chat GPT endpoint for your app with a 100,000 token context window and pay-as-you-go crypto pricing.
- $0.15 per 1M input tokens
- No content refusals for adults
- $0.50 trial credit included
Test with a single request
curl https://api.gptchatunrestricted.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "List all required headers for a POST request"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.gptchatunrestricted.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.gptchatunrestricted.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
Key features
OpenAI Compatible
Use existing SDKs with a simple base_url change.
Crypto Only
Top up with USDT or USDC without a credit card.
No Expiration
Paid credit never expires and errors are free.
Function Calling
Supports tools and JSON mode for robust apps.
Streaming SSE
Real-time token streaming with usage in the last chunk.
Strict Limits
300 requests per minute per key for stability.
Setup steps
Create Account
Sign in with Google or email to get a key instantly.
Top Up
Add crypto to receive bonus credit instantly.
Integrate
Point your client to our base URL and start sending.
Common use cases
NSFW Roleplay
Generate explicit fictional content without unexpected refusals.
Jailbreak Testing
Test model boundaries without complex prompt engineering.
Creative Writing
Draft stories with mature themes freely.
Data Extraction
Parse raw data without content filters interfering.
What makes this API truly uncensored
Our API refuses nothing lawful. You get a single uncensored model, not a subscription with hidden limits. Credits never expire. Errors cost nothing. Top up with USDT or USDC. The base URL is HTTPS://api.gptchatunrestricted.com/v1. Send model "uncensored". Context is 100,000 tokens. Output maxes at 16,000 tokens. Pricing is $0.15 per 1M input tokens and $0.50 per 1M output tokens.
Cost calculation: how much you actually pay
You pay only for tokens sent and received, not for idle time. Input costs $0.15 per million tokens while output is $0.50 per million tokens. A 5,000 token prompt with a 500 token response costs roughly $0.00275. Errors are free. Prepaid credit never expires. Use curl or the SDK to track usage in real-time. Top up via crypto starting at $20 for a +5% bonus.
unrestricted chat GPT: real use cases for uncensored models
We deliver uncensored content for adult fiction and roleplay without arbitrary refusals. Use our 100k context window to maintain continuity across long scenes.
NSFW Roleplay
Generate explicit narratives without hidden filters blocking vocabulary.
Adult Creative Writing
Write mature stories using our OpenAI-compatible SDK for seamless integration.
Content Creation
Produce raw, unfiltered text for applications needing direct answers without corporate moderation layers.
Questions from the community: honest answers
Is there truly 0 restrictions?
Yes, for lawful adult use. Our uncensored LLM answers without refusals, unlike subscription alternatives that silently reroute free users or apply hidden limits.
Does it require jailbreak prompts?
No. It is an uncensored model trained to comply directly. You send standard OpenAI-compatible requests.
What is the cost?
We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free. Top up with crypto only.
Common mistakes when switching to uncensored LLMs
Developers often assume an uncensored model behaves exactly like GPT-4. This assumption breaks when they send requests without setting the model parameter to "uncensored". Another error is ignoring the 100,000 token context window, which causes silent truncation during long sessions. Users also forget that errors remain free, but token usage charges apply immediately. Always verify your base URL points to our specific endpoint to avoid mixing up client libraries.
Migrate from another provider in 3 steps
Migrate from another provider in 3 steps
Switch to our uncensored API by updating your base URL and API key.
- Generate a new key via Continue with Google.
- Point your SDK to
https://api.gptchatunrestricted.com/v1. - Send requests using the
uncensoredmodel ID.
Costs are transparent: $0.15 per 1M input tokens and $0.50 per 1M output tokens. Errors are free.
Frequently asked questions
What is an unrestricted chat GPT API?
It is a hosted endpoint serving one uncensored large language model. Text in, text out. It uses the OpenAI-compatible format. You send requests to /v1/chat/completions. The model id is "uncensored". It answers without refusals for lawful adult use.
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.
How do I pay for this uncensored AI service?
You pay with crypto only. USDT on TRC20 or USDC on Base. Top-up amounts range from $20 to $500. Bonus credit applies from $50. Credit never expires. Sign in via Google.
What are the rate limits per key?
You get 300 requests per minute. You can run 8 requests simultaneously. The request body must be under 8 MB. One active key per account. A new key replaces the old one. Streaming works via SSE.
Does this model filter all NSFW content?
No. It answers without content refusals for lawful adult use. It allows fictional, security-research, or controversial topics. One hard limit always applies: no sexual content involving minors. Requests of that kind are refused. This is not a generic filter.
What is the context window size?
The context window is 100,000 tokens. This includes prompt plus completion together. The max output is 16,000 tokens per request. You must set max_tokens. Otherwise, the limit is 2,048. Features include streaming and JSON mode.
Access your API key
Sign up, copy the key, update the base URL. That’s all it takes.
