Cost decision lab

Which LLM API costs less for your workload?

Set your token mix, compare providers side by side, and see estimated spend — no account, no guesswork. Prices auto-synced from OpenRouter; updated when providers change rates.

Agentic flow · cost pipeline

Input

Model

OUT

Output

Cheapest match — /mo

Workload Live

Agent scenarios

One-click workload templates — active preset shows Best value for that scenario

Monthly requests 10,000

How many API calls per month

Input tokens / request 2,000

Prompt + context length

Output tokens / request 500

Completion length

Billing period

Total input tokens 20M

Total output tokens 5M

Token volume 25M /mo

Loading pricing data…

Which LLM API costs less for your workload?

Model comparison