Token 成本試算器 (Price Calculator)
依據每次請求之 Input / Output Token 數量與請求次數，精確試算並排名各供應商總成本。
重要說明：下方輸入的 Input / Output Tokens 代表「每次請求 (Per Request)」的 Token 數量，總成本會自動乘以 Request Count（請求次數）。
Total Cost = ((Input Tokens × Input USD/1M + Output Tokens × Output USD/1M) / 1,000,000) × Request Count
常用試算情境預設:
最低總成本供應商
$0.0800
Nebius AI Studio (nebius/meta-llama/Llama-Guard-3-8B)
Highest Cost Provider
$0.5140
Cloudflare Workers AI (cloudflare/@cf/meta/llama-guard-3-8b)
最高與最低價差
$0.4340
Total workload difference
最高可節省比例
84.4%
Choosing lowest vs highest
Estimated Workload Cost by Provider (USD)
各供應商預估成本排名（僅列出具備完整 Input 與 Output 報價之方案）
若某供應商缺少 Input 或 Output 任一必要價格欄位，系統不會將其納入總成本排名，以避免不完整的成本比較。
| Rank | Provider · LiteLLM ID | Input / 1M | Output / 1M | Input Cost | Output Cost | Total Cost | vs Cheapest |
|---|---|---|---|---|---|---|---|
| #1 | Nebius AI Studio· Standard · Global nebius/meta-llama/Llama-Guard-3-8B | $0.02 | $0.06 | $0.0200 | $0.0600 | $0.0800 | Cheapest |
| #2 | DeepInfra· Standard · Global deepinfra/meta-llama/Llama-Guard-3-8B | $0.055 | $0.055 | $0.0550 | $0.0550 | $0.1100 | +$0.0300 (save 27.3%) |
| #3 | Groq· Standard · Global groq/llama-guard-3-8b | $0.20 | $0.20 | $0.2000 | $0.2000 | $0.4000 | +$0.3200 (save 80.0%) |
| #4 | Fireworks AI· Standard · Global fireworks_ai/accounts/fireworks/models/llama-guard-3-8b | $0.20 | $0.20 | $0.2000 | $0.2000 | $0.4000 | +$0.3200 (save 80.0%) |
| #5 | Cloudflare Workers AI· Standard · Global cloudflare/@cf/meta/llama-guard-3-8b | $0.484 | $0.03 | $0.4840 | $0.0300 | $0.5140 | +$0.4340 (save 84.4%) |