EN ▾
Claim trial key

OpenAI compatible endpoint transparent pricing

Stop overpaying for uncensored inference. This page details the transparent per-token pricing for our openai compatible endpoint, ensuring you know exactly what every request costs before you send a single byte.

No subscriptions. Prepaid funds do not expire.

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

Usage estimator

$0.00
Claim trial key

Usage examples

Long-context code analysis

A single request processes 50,000 input tokens and generates 2,000 output tokens. The cost is calculated as (50,000 / 1,000,000 * $0.15) + (2,000 / 1,000,000 * $0.50) = $0.0075 + $0.0010 = $0.0085 per request.

High-volume chat streaming

Processing 10,000 input tokens and 8,000 output tokens for a complex reasoning task. The cost is (10,000 / 1,000,000 * $0.15) + (8,000 / 1,000,000 * $0.50) = $0.0015 + $0.0040 = $0.0055.

Bulk data summarization

Summarizing a large dataset with 80,000 input tokens and 4,000 output tokens. The cost is (80,000 / 1,000,000 * $0.15) + (4,000 / 1,000,000 * $0.50) = $0.0120 + $0.0020 = $0.0140.

Per-token pricing breakdown

We charge strictly for actual inference. Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors are free. Refusals are free. You only pay when the model generates text.

This model is not a proxy. It is a single uncensored large language model running on our servers. The base URL is HTTPS://api.openaicompatibleendpoint.com/v1. Change your client configuration and keep your code. The pricing is transparent. No hidden fees. No per-request overhead. You see the exact cost in the response headers.

Crypto top-up tiers and bonuses

Top-up requires cryptocurrency. We accept USDT on TRC20 or USDC on Base. Minimum deposit is $20. Maximum deposit is $500. We apply bonus credit automatically. Deposits of $50 gain +5%. Deposits of $100 gain +10%. Deposits of $200 gain +15%. Credit never expires. You control your budget. The balance updates in real time. Request limits apply per key. You get 300 requests per minute. You get 8 concurrent requests. The body limit is 8 MB.

Rate limits and request rules

Rate limits protect the inference pipeline. You get 300 requests per minute per key. You get 8 concurrent requests per key. The request body limit is 8 MB. Context window is 100,000 tokens. Max output is 16,000 tokens. Set max_tokens to avoid unexpected costs. Unset max_tokens defaults to 2,048 tokens.

Function calling works. JSON mode works. Streaming via SSE works. Token usage appears in the last chunk. We do not offer embeddings. We do not offer image generation. We do not offer fine-tuning. This is a chat-completions endpoint only. POST /v1/chat/completions and GET /v1/models are the only endpoints.

Trial credit and refund policy

New accounts get $0.50 trial credit. It lasts 7 days. One per person. Signup uses Continue with Google or email plus password. The key shows immediately. Prompts are not used for training. Privacy is strict. Account needs only an email.

Credit is not refunded. It never expires. Mistakes like double charges are fixed via Support. Prepaid credit is final. You pay for tokens. Errors are free. Refusals are free. The hard content limit applies always. No sexual content involving minors. Everything else is uncensored.

Common questions

What is the openai compatible endpoint pricing?

Input tokens cost $0.15 per million. Output tokens cost $0.50 per million. Errors and refusals are free. You pay only for actual inference.

How do I top up my API key balance?

Top up with USDT on TRC20 or USDC on Base. Minimum amount is $20. Maximum amount is $500. We apply bonuses automatically based on your deposit size.

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.

What happens if I exceed my rate limits?

Requests fail. You pay nothing for failed requests. You get 300 requests per minute. You get 8 concurrent requests. The body limit is 8 MB. Context window is 100,000 tokens.

Unlock your API key

Sign up, copy the key, update your base URL. Simple.

Claim trial key