AI API cost glossary

Tokens per minute

Tokens per minute is a throughput or rate-limit measure describing how many input or output tokens an account or model can process during a minute.

Why it matters for API cost

A workload can fit its dollar budget but still exceed provider throughput limits during traffic spikes.

required tokens per minute = peak requests per minute × average tokens per request

Twenty peak requests per minute with 1,300 combined tokens each require about 26,000 tokens per minute before retries.

Is tokens per minute a price?

No. It is a throughput measure. Token rates and account limits are related operational constraints but not the same thing.

How to Calculate LLM Tokens and Estimate API Cost

Learn how to estimate LLM tokens, convert input and output usage into API cost, and build a realistic monthly AI budget.

OpenAI API Pricing Explained: Tokens, Cache, Batch, and Cost

Understand OpenAI API input, output, cached input, batch, image, audio, and embedding pricing with practical formulas.