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。

View Qwen3 235B A22b Instruct 2507 Matrix

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
$0.6400
DeepInfra (deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507)
Highest Cost Provider
$6.00
Crusoe Cloud (crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507)
最高與最低價差
$5.36
Total workload difference
最高可節省比例
89.3%
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。

RankProvider · LiteLLM IDInput / 1MOutput / 1MInput CostOutput CostTotal Costvs Cheapest
#1
DeepInfra· Standard · Global
deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507
$0.09$0.55$0.0900$0.5500$0.6400Cheapest
#2
Novita AI· Standard · Global
novita/qwen/qwen3-235b-a22b-instruct-2507
$0.09$0.58$0.0900$0.5800$0.6700+$0.0300 (save 4.5%)
#3
Nebius AI Studio· Standard · Global
nebius/Qwen/Qwen3-235B-A22B-Instruct-2507
$0.20$0.60$0.2000$0.6000$0.8000+$0.1600 (save 20.0%)
#4
Google Vertex AI (Qwen)· Standard · Global
vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas
$0.22$0.88$0.2200$0.8800$1.10+$0.4600 (save 41.8%)
#5
Fireworks AI· Standard · Global
fireworks_ai/accounts/fireworks/models/qwen3-235b-a22b-instruct-2507
$0.22$0.88$0.2200$0.8800$1.10+$0.4600 (save 41.8%)
#6
Replicate· Standard · Global
replicate/qwen/qwen3-235b-a22b-instruct-2507
$0.264$1.06$0.2640$1.06$1.32+$0.6840 (save 51.7%)
#7
Scaleway Generative APIs· Standard · Global
scaleway/qwen/qwen3-235b-a22b-instruct-2507
$0.75$2.25$0.7500$2.25$3.00+$2.36 (save 78.7%)
#8
Crusoe Cloud· Standard · Global
crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
$3.00$3.00$3.00$3.00$6.00+$5.36 (save 89.3%)