工具
LLM 成本计算器
选择模型，输入每次请求的 input/output token 与每月请求量，即可估算 Claude、Gemini、GPT 的单次与每月 API 成本，并对比各家官方价的节省。价格实时取自 Kunavo 目录。
Your workload
Quick presets
Rate: $1.20 in / $6.00 out per 1M tokens · read live from the Kunavo catalog.
Estimated cost
Per request$0.00420
Per month (Kunavo)$420
Per month at Anthropic list$1,050
You save vs Anthropic list
$630/ month · ~60%
Estimate only. Reasoning models bill hidden reasoning tokens at the output rate; prompt caching bills cached input at a fraction of the input rate — both shift the real number. Failed requests are never billed.
延伸阅读