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
$0.0700
Novita AI (novita/meta-llama/llama-3.1-8b-instruct)
Highest Cost Provider
$0.4400
Weights & Biases (Weave) (wandb/meta-llama/Llama-3.1-8B-Instruct)
最高與最低價差
$0.3700
Total workload difference
最高可節省比例
84.1%
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 | Novita AI· Standard · Global novita/meta-llama/llama-3.1-8b-instruct | $0.02 | $0.05 | $0.0200 | $0.0500 | $0.0700 | Cheapest |
| #2 | OpenRouter· Standard · Global openrouter/meta-llama/llama-3.1-8b-instruct | $0.05 | $0.08 | $0.0500 | $0.0800 | $0.1300 | +$0.0600 (save 46.2%) |
| #3 | OVHcloud AI Endpoints· Standard · Global ovhcloud/Llama-3.1-8B-Instruct | $0.10 | $0.10 | $0.1000 | $0.1000 | $0.2000 | +$0.1300 (save 65.0%) |
| #4 | Perplexity· Standard · Global perplexity/llama-3.1-8b-instruct | $0.20 | $0.20 | $0.2000 | $0.2000 | $0.4000 | +$0.3300 (save 82.5%) |
| #5 | Weights & Biases (Weave)· Standard · Global wandb/meta-llama/Llama-3.1-8B-Instruct | $0.22 | $0.22 | $0.2200 | $0.2200 | $0.4400 | +$0.3700 (save 84.1%) |
1 offerings excluded from cost ranking (missing required price fields or filtered out):
Google Vertex AI (Llama) (vertex_ai/meta/llama-3.1-8b-instruct-maas): Local / Free ($0.00) tier (toggle checkbox above to include)