Monthly cost calculator 核验日期 2026-09-17

Pick a model family, estimate your token usage, and see what each provider would charge you per month. All math runs in your browser — nothing is uploaded. The cache slider assumes part of your input tokens hit the provider's prompt cache (typical for coding agents: 40–70%).

Your usage

Model family
Input tokens / month
Output tokens / month
Cache-hit ratio on input: 50%

Where a provider's cache-read price is 待核验, we conservatively bill those tokens at the full input rate.

Provider	Model	Input $/1M	Cache $/1M	Output $/1M	Monthly est.

Estimates only — taxes, tiered long-context surcharges and off-peak discounts (DeepSeek) are not modeled. Verify on the provider's page before budgeting.