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
$0.3100
OVHcloud AI Endpoints (ovhcloud/Qwen3-32B)
Highest Cost Provider
$1.80
Fireworks AI (fireworks_ai/accounts/fireworks/models/qwen3-32b)
最高與最低價差
$1.49
Total workload difference
最高可節省比例
82.8%
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 | OVHcloud AI Endpoints· Standard · Global ovhcloud/Qwen3-32B | $0.08 | $0.23 | $0.0800 | $0.2300 | $0.3100 | Cheapest |
| #2 | DeepInfra· Standard · Global deepinfra/Qwen/Qwen3-32B | $0.08 | $0.28 | $0.0800 | $0.2800 | $0.3600 | +$0.0500 (save 13.9%) |
| #3 | OpenRouter· Standard · Global openrouter/qwen/qwen3-32b | $0.08 | $0.28 | $0.0800 | $0.2800 | $0.3600 | +$0.0500 (save 13.9%) |
| #4 | Nebius AI Studio· Standard · Global nebius/Qwen/Qwen3-32B | $0.10 | $0.30 | $0.1000 | $0.3000 | $0.4000 | +$0.0900 (save 22.5%) |
| #5 | AWS Bedrock (Converse)· Standard · Global qwen.qwen3-32b-v1:0 | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.4400 (save 58.7%) |
| #6 | AWS Bedrock (Mantle)· Standard · Global bedrock_mantle/qwen.qwen3-32b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.4400 (save 58.7%) |
| #7 | Fireworks AI· Standard · Global fireworks_ai/accounts/fireworks/models/qwen3-32b | $0.90 | $0.90 | $0.9000 | $0.9000 | $1.80 | +$1.49 (save 82.8%) |