A RAG pipeline processing a 100k token document chunk
Sending 100,000 input tokens and receiving 2,000 output tokens costs: (100,000/1,000,000 * 0.15) + (2,000/1,000,000 * 0.50) = $0.015 + $0.001 = $0.016.
Transparent Per-Token Pricing
Get raw, uncensored inference power with transparent per-token pricing. Pay only for what you use, no subscriptions lock you in.
- per 1M input tokens
- $0.15
- Output tokens / 1M
- $0.50
- token context
- 100,000
- trial credit
- $0.50
- requests per minute
- 300
https://api.apiinferencellm.com/v1
Cost estimator
Usage examples
Transparent Token Rates
The uncensored LLM charges $0.15 per 1M input tokens and $0.50 per 1M output tokens. You see exactly what you spend before you send a single request. This abliterated model inference costs less than many enterprise alternatives while offering full freedom for lawful adult use.
Our pricing scales linearly with your token count. No hidden fees for streaming or function calling. Errors and refusals consume zero tokens, so you never pay for failed attempts. This direct pricing model keeps your infrastructure costs predictable and simple.
No Hidden Fees or Subscriptions
We do not charge monthly subscription fees or require long-term contracts. Your prepaid credit lasts until you use it. This approach eliminates the risk of paying for idle capacity when your agents are offline. You only pay for the inference you actually run.
The inference API supports up to 300 requests per minute with an 8 MB request body limit. These limits are hard caps, not soft tiers that surprise you. You get full access to the 100,000 token context window without extra charges. This simplicity helps developers focus on building rather than managing billing tiers.
Crypto Top-Up & Bonus Credits
Add funds using USDT on TRC20 or USDC on Base. We accept whole amounts between $20 and $500 per transaction. Larger top-ups trigger bonus credits to stretch your budget further. You get a +5% bonus starting at $50, +10% at $100, and +15% at $200.
Credit never expires, so you can top up whenever it suits your development cycle. This crypto-only method keeps overhead low and passes the savings directly to you.
Free Trial & Refund Policy
New accounts receive $0.50 of trial credit valid for 7 days. This allows you to verify compatibility with your stack before committing any funds. The trial is limited to one per person and requires only an email address.
If you make a mistake, such as a double charge, we fix it through the Support page. Your prepaid balance is not refunded because it never expires. You retain full ownership of your credit until you choose to spend it on future inference tasks. This policy ensures you are never locked out of your own funds.
Frequently asked questions
How does prepaid credit work with the uncensored LLM?
You top up with crypto and spend only what you use. Errors and refusals do not consume tokens, so you never pay for failed requests. Your balance persists until you use it, with no expiration date.
What payment methods do you accept?
We accept only USDT on TRC20 or USDC on Base. You can top up any whole amount between $20 and $500 to receive bonus credits.
Is there a free tier available?
Every new account gets $0.50 of trial credit valid for 7 days. It allows you to test the API without any financial commitment or phone number verification.
Do you charge for streaming responses?
No, streaming responses do not incur extra fees. You pay per token used in the final output. This applies to all response formats, including JSON mode and function calling. The cost remains transparent and linear.
Generate your key now
Register, copy the token, update the endpoint. That is all.
Get your keyhttps://api.apiinferencellm.com/v1
