apiinference.com/Pay as you go
Transparent per-token inference api pricing
Transparent per-token inference API pricing eliminates billing surprises by charging only for actual usage. You pay $0.15 per million input tokens and $0.50 per million output tokens with zero subscription fees.
- $0.15
- per 1M input tokens
- $0.50
- Output tokens / 1M
- 100,000
- token context
- $0.50
- trial credit
- 300
- requests per minute
Usage examples
Resume parsing and data extraction
Sending 20,000 input tokens for a resume and receiving 1,500 output tokens for JSON data costs $0.003 + $0.00075, totaling exactly $0.00375 per request. This workload benefits from our high context window and structured output capabilities without paying for idle time.
Long-form creative writing session
Processing 50,000 input tokens for a prompt and generating 8,000 output tokens costs $0.0075 + $0.004, totaling $0.0115. You only pay for the tokens consumed during the generation process, ensuring that long outputs do not disproportionately inflate your costs.
High-volume chatbot interactions
Handling 50,000 input tokens and 50,000 output tokens for a conversation costs $0.0075 + $0.025, totaling $0.0325. This predictable rate structure allows you to model your unit economics accurately without hidden routing or model-switching fees.
Prepaid credit and transparent per-token inference API usage
Our pricing model charges $0.15 per million input tokens and $0.50 per million output tokens. Errors and refusals consume zero tokens, so you never pay for failed requests. Your prepaid balance deducts only for successful token generation, making your total cost of ownership highly predictable.
You can top up your account using cryptocurrency, which allows for instant credit activation without banking delays. The prepaid balance never expires, so you can pause usage during low-traffic periods without losing your funds. This structure removes the monthly subscription bloat found in other inference providers.
Crypto top-ups and bonuses
We accept USDT on the TRC20 network and USDC on the Base network for all top-ups. You can deposit any whole amount between $20 and $500 per transaction. This crypto-only approach ensures fast settlement and lower processing fees for our infrastructure. The bonus credit is applied immediately to your balance, giving you more tokens to test or deploy your application.
Free trial and limits
Every new account receives $0.50 of trial credit, which is valid for seven days. You can make up to 300 requests per minute and have eight concurrent requests active per key.
The request body limit is 8 MB, and you can use one active API key per account. If you need a new key, it replaces the old one. This trial is sufficient to verify integration with the OpenAI-compatible SDKs and ensure the model meets your content requirements before committing to a larger crypto top-up.
Common questions
Does the inference API charge for failed requests?
No, errors and refusals consume zero tokens. You only pay for the tokens successfully generated and sent back to your client. This means you are not billed for network timeouts or model processing errors.
How do I top up my account?
You can top up using USDT (TRC20) or USDC (Base). Deposits range from $20 to $500. You receive bonus credit based on the amount deposited, with up to a 15% bonus for a $200 top-up.
Is there a monthly subscription fee?
No, there is no monthly subscription fee. You pay strictly for the tokens you consume. Any prepaid credit you purchase remains in your account until you decide to use it.
What is the cost for input versus output tokens?
Input tokens cost $0.15 per million, while output tokens cost $0.50 per million. This reflects the higher computational cost of generation compared to processing the input prompt.
Generate your key now
Sign up, copy the key, update your base URL. That is the entire configuration.
