EN ▾
Get API key
  1. Home
  2. Pricing

Transparent Pricing for Uncensored LLM API

Pay only for the tokens you use with our transparent, usage-based pricing. No subscriptions, no hidden fees, and no training on your data.

$0.15
per 1M input tokens
$0.50
Output tokens / 1M
100,000
token context
$0.50
trial credit
300
requests per minute

Top-ups from $20 to $500, any whole amount. Bonus credit: +5% from $50, +10% from $100, +15% from $200.

Cost calculator

$0.00

Worked examples

Code completion for a medium-sized Python module

A request containing a 15,000-token context (code + instructions) and generating a 500-token completion. Input cost: 15,000 / 1,000,000 * $0.15 = $0.00225. Output cost: 500 / 1,000,000 * $0.50 = $0.00025. Total: $0.0025 per request.

Roleplay session with streaming

A user sends a 2,000-token prompt and receives a 3,000-token response. Input cost: 2,000 / 1,000,000 * $0.15 = $0.0003. Output cost: 3,000 / 1,000,000 * $0.50 = $0.0015. Total: $0.0018 per turn.

Batch data extraction from documents

Processing 100 documents, each with a 500-token prompt and 100-token output. Input cost per doc: 500 / 1,000,000 * $0.15 = $0.000075. Output cost per doc: 100 / 1,000,000 * $0.50 = $0.00005. Total per doc: $0.000125. Total for 100 docs: $0.0125.

Pay-As-You-Go Rates

We charge strictly for compute usage. There are no monthly subscriptions, no minimum commitments, and no fees for idle time. You pay for the best uncensored llm performance based on actual token consumption.

The pricing structure is simple and consistent across all requests, whether you are streaming responses or using batch processing. Input tokens are charged at $0.15 per million tokens, while output tokens are charged at $0.50 per million tokens. This ratio reflects the higher computational cost of generating text compared to processing it.

Because we do not offer embeddings, image generation, or model routing, you never pay for features you do not use. You only pay for the text-in, text-out pipeline that powers your application.

Credit Bonuses

Prepaid credit gives you predictable costs and immediate access. When you top up your account, you can receive bonus credit that increases with larger deposits. This bonus is applied automatically to your balance and can be used for any request, just like base credit.

Top-ups start at $20. If you deposit $50 or more, you receive a 5% bonus. For deposits of $100 or more, the bonus increases to 10%. These bonuses effectively lower your effective cost per token for larger projects. There is no expiration on your credit, so you can use your bonus whenever you are ready to scale your usage.

Trial Credit

New accounts receive $0.50 of trial credit, valid for 7 days. Claim this credit with one click on your API key page. No credit card or phone number is required to start. This allows you to test the uncensored llm capabilities, verify streaming, and check tool calling before committing funds.

The trial is one per person. It provides enough tokens to evaluate the model's behavior and performance. Once the trial expires or the credit is exhausted, you can top up by crypto (USDT on TRC20, USDC on Base) to continue using the API. The trial credit is indistinguishable from paid credit in terms of model performance and speed.

Payment Methods

We accept top-ups by crypto (USDT on TRC20, USDC on Base). All transactions are processed securely. You can manage your billing details and view transaction history directly from your dashboard.

Your API key can be regenerated at any time, revoking the previous key instantly. This ensures that your usage remains secure and predictable. Since there are no subscriptions, you control exactly when you spend money. If you stop using the API, your balance remains available for future use until you decide to cash out or use it again.

What your credit buys

No tiers: every key gets the full feature set and the same limits.

ParameterDetails
JSON moderesponse_format: {"type": "json_object"}
Completion lengthprompt + completion fit within 100,000 tokens; max_tokens optional, no separate output cap
Context window100,000 tokens (prompt + completion together)
Tools / tool callsYes — tools, tool_choice; replies carry tool_calls, also when streaming; send results back as role: tool
Requests per minute300 requests per minute per key
Parallel requests8 requests at the same time per key
Subscriptionno monthly fee; paid credit does not expire
Free trial$0.50 for 7 days, no card · Trial key: 2 parallel requests, 60 req/min; full limits (8 and 300) after first top-up
Bonus credit+5% on $50+, +10% on $100+, +15% on $200+
Token prices$0.15 per 1M input tokens · $0.50 per 1M output tokens
Top-upUSDT (TRC20) or USDC (Base), any whole amount from $20 to $500

Full specifications and error codes: see the docs.

Questions and answers

Do you charge for embeddings or other model types?

No. Our API serves a single uncensored model for chat completions. We do not offer embeddings, image generation, audio, or video. You only pay for the input and output tokens of the text model.

Can I use this API for production workloads?

Yes. The API is designed for both evaluation and production use. It supports streaming, tool calling, and standard OpenAI-compatible endpoints. However, we do not guarantee specific SLA percentages, so you should monitor your usage and plan accordingly.

What happens to my unused credit?

Your prepaid credit never expires. It remains in your account until you choose to use it or withdraw it. You can top up at any time, and bonus credits are applied immediately to your available balance.

How many requests can I make per minute?

You are limited to 300 requests per minute per API key. Each request body must be under 8 MB. These limits ensure stable performance for all users. You can regenerate your key if you need to reset your rate limit status.

Your key is one form away

Create an account, copy the key, change the base URL. That is the whole setup.

Get API key