Token cost calculator

Enter input and output token counts for any model and get the exact cost, including the cached-input rate if your prompts repeat.

Model

Input tokens

Output tokens

Cached input share0%

$0.1300

Qwen Flash at $0.0500/1M in and $0.4000/1M out.

Uses rates verified 2026-08-31. Estimates only — actual bills depend on tokenizer behavior, caching hit rates, and provider-side rounding.