OpenAI Compatible
Drop-in replacement using standard endpoints and SDKs.
Uncensored LLM API
Get your venice AI API key for a single uncensored model with 100,000 token context and prepaid crypto billing.
Test with one API call
curl https://api.veniceaiapikey.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "uncensored",
"messages": [{"role": "user", "content": "Generate a summary of the current weather conditions"}]
}'from openai import OpenAI
client = OpenAI(base_url="https://api.veniceaiapikey.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.veniceaiapikey.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);Drop-in replacement using standard endpoints and SDKs.
Pay only for tokens used with crypto top-ups.
Handle massive prompts with up to 100,000 tokens.
Use tools and JSON mode for complex workflows.
Receive real-time tokens with streaming enabled.
Your prompts remain private and unused for training.
Sign up with Google or email to get your key.
Add credit using USDT or USDC to start.
Send prompts to the uncensored model endpoint immediately.
Generate raw text without content filters for creative writing.
Power adult-oriented chat applications with direct API access.
Test model behavior without standard refusal mechanisms interfering.
Parse large documents using the extensive context window.
We charge by actual token usage with prepaid credit that never expires, avoiding monthly subscriptions.
| Feature | Typical Alternative | Ours |
|---|---|---|
| Pricing | Monthly tiers | $0.15 per 1M input tokens, $0.50 per 1M output tokens |
| Billing | Cards or bank transfers | Crypto only: USDT (TRC20) or USDC (Base) |
| Expiration | Monthly reset | Paid credit never expires |
| Refunds | Complex | Credit is not refunded; errors are free |
Developers seeking an uncensored LLM for NSFW chatbots or unrestricted roleplay use this endpoint for raw text generation without refusals. It fits projects needing direct model responses via standard OpenAI-compatible SDKs. It is NOT for teams requiring image generation, embeddings, or multi-model routing. Users needing complex audio processing or fine-tuning should look elsewhere. This service delivers simple, token-based inference for creative writing and adult content applications efficiently.
Use the venice AI API key to generate unrestricted text for creative projects without content filters blocking your output.
Send raw dialogue to uncensored models for immersive storytelling where standard LLMs refuse mature themes.
Validate response formats with the OpenAI-compatible endpoint, ensuring your code handles streaming and JSON modes correctly.
Generate long-form articles or scripts with a 100,000-token context window, paying only for the tokens you actually consume.
Developers often assume all open-weight models handle adult content equally well. This is a false equivalence. Many providers charge premium rates for uncensored access or retain the right to train on your prompts. Venice AI offers a single, dedicated uncensored model without usage training. You pay only for tokens used, with prepaid credit that never expires. Avoid hidden fees by verifying the billing model matches your actual throughput needs.
Verify the billing model matches your usage. We charge $0.15 per 1M input tokens and $0.50 per 1M output tokens, with prepaid credit that never expires. Check context limits; our uncensored model supports 100,000 tokens. Ensure the endpoint is strictly OpenAI-compatible. Confirm no model training occurs on your prompts. Test streaming support. Avoid hidden fees or forced monthly subscriptions.
Create your account instantly using Google or an email and password. The system displays your unique API key immediately, with no phone number required.
Your first token arrives directly from the server.
Crypto only: USDT on TRC20 or USDC on Base, any whole amount from $20 to $500. Bonus credit applies from $50.
Yes, it supports streaming via Server-Sent Events. The final chunk includes token usage details for accurate billing. This allows real-time output without waiting for the full response. It is ideal for chat interfaces requiring immediate feedback.
No, there are no monthly subscriptions. You pay only for tokens used with prepaid credit. Errors and refusals are free. Credit never expires, so you can top up only when needed. This avoids hidden fees completely.
Yes, the model answers without content refusals for lawful adult use. It handles controversial or fictional topics freely. The only hard limit is no sexual content involving minors. This makes it ideal for unrestricted creative writing.
We accept only crypto: USDT on TRC20 or USDC on Base. Any whole amount from $20 to $500 is allowed. You receive bonus credit for larger top-ups.
The context window is 100,000 tokens. This includes both prompt and completion tokens. The maximum output per request is 16,000 tokens. This allows processing long documents or extended conversations efficiently.
Sign up, copy your unique key, and update your base URL. That is the entire configuration.