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
$0.2000
Weights & Biases (Weave) (wandb/openai/gpt-oss-120b)
Highest Cost Provider
$4.00
NCHC TAIWAN AI RAP (gpt-oss-120b)
最高與最低價差
$3.80
Total workload difference
最高可節省比例
95.0%
Choosing lowest vs highest
國網 TAIWAN AI RAP 試算
gpt-oss-120b$4.00排名第 32 / 32· 比最便宜（Weights & Biases (Weave)）多 $3.80
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 | Weights & Biases (Weave)· Standard · Global wandb/openai/gpt-oss-120b | $0.03 | $0.17 | $0.0300 | $0.1700 | $0.2000 | Cheapest |
| #2 | DeepInfra· Standard · Global deepinfra/openai/gpt-oss-120b | $0.037 | $0.17 | $0.0370 | $0.1700 | $0.2070 | +$0.007000 (save 3.4%) |
| #3 | OpenRouter· Standard · Global openrouter/openai/gpt-oss-120b | $0.037 | $0.17 | $0.0370 | $0.1700 | $0.2070 | +$0.007000 (save 3.4%) |
| #4 | Novita AI· Standard · Global novita/openai/gpt-oss-120b | $0.05 | $0.25 | $0.0500 | $0.2500 | $0.3000 | +$0.1000 (save 33.3%) |
| #5 | Google Vertex AI (MaaS)· Standard · Global vertex_ai/openai/gpt-oss-120b-maas | $0.09 | $0.36 | $0.0900 | $0.3600 | $0.4500 | +$0.2500 (save 55.6%) |
| #6 | Sail· Standard · Global sail/openai/gpt-oss-120b | $0.06 | $0.40 | $0.0600 | $0.4000 | $0.4600 | +$0.2600 (save 56.5%) |
| #7 | OVHcloud AI Endpoints· Standard · Global ovhcloud/gpt-oss-120b | $0.08 | $0.40 | $0.0800 | $0.4000 | $0.4800 | +$0.2800 (save 58.3%) |
| #8 | Baseten· Standard · Global baseten/openai/gpt-oss-120b | $0.10 | $0.50 | $0.1000 | $0.5000 | $0.6000 | +$0.4000 (save 66.7%) |
| #9 | Databricks· Standard · Global databricks/databricks-gpt-oss-120b | $0.15001 | $0.59997 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #10 | Azure AI Foundry· Standard · Global azure_ai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #11 | Fireworks AI· Standard · Global fireworks_ai/accounts/fireworks/models/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #12 | Fireworks AI· Standard · Global fireworks_ai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #13 | Groq· Standard · Global groq/openai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #14 | Nebius AI Studio· Standard · Global nebius/openai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #15 | AWS Bedrock (Converse)· Standard · Global openai.gpt-oss-120b-1:0 | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #16 | Together AI· Standard · Global together_ai/openai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #17 | Scaleway Generative APIs· Standard · Global scaleway/openai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #18 | AWS Bedrock (Mantle)· Standard · Global bedrock_mantle/openai.gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #19 | TensorMesh· Standard · Global tensormesh/openai/gpt-oss-120b | $0.15 | $0.60 | $0.1500 | $0.6000 | $0.7500 | +$0.5500 (save 73.3%) |
| #20 | IBM watsonx.ai· Standard · Global watsonx/openai/gpt-oss-120b | $0.159 | $0.636 | $0.1590 | $0.6360 | $0.7950 | +$0.5950 (save 74.8%) |
| #21 | SambaNova· Standard · Global sambanova/gpt-oss-120b | $0.22 | $0.59 | $0.2200 | $0.5900 | $0.8100 | +$0.6100 (save 75.3%) |
| #22 | Azure AI Foundry· Standard · Global azure_ai/FW-GPT-OSS-120B | $0.165 | $0.66 | $0.1650 | $0.6600 | $0.8250 | +$0.6250 (save 75.8%) |
| #23 | Replicate· Standard · Global replicate/openai/gpt-oss-120b | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #24 | AWS Bedrock (Converse)· Standard · us-gov us-gov.openai.gpt-oss-120b-1:0 | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #25 | AWS Bedrock· Standard · us-gov-west-1 bedrock/us-gov-west-1/openai.gpt-oss-120b-1:0 | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #26 | AWS Bedrock· Standard · us-gov-east-1 bedrock/us-gov-east-1/openai.gpt-oss-120b-1:0 | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #27 | AWS Bedrock (Mantle)· Standard · us-gov-west-1 bedrock_mantle/us-gov-west-1/openai.gpt-oss-120b | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #28 | AWS Bedrock (Mantle)· Standard · us-gov-east-1 bedrock_mantle/us-gov-east-1/openai.gpt-oss-120b | $0.18 | $0.72 | $0.1800 | $0.7200 | $0.9000 | +$0.7000 (save 77.8%) |
| #29 | Cerebras· Standard · Global cerebras/gpt-oss-120b | $0.35 | $0.75 | $0.3500 | $0.7500 | $1.10 | +$0.9000 (save 81.8%) |
| #30 | Cloudflare Workers AI· Standard · Global cloudflare/@cf/openai/gpt-oss-120b | $0.35 | $0.75 | $0.3500 | $0.7500 | $1.10 | +$0.9000 (save 81.8%) |
| #31 | Crusoe Cloud· Standard · Global crusoe/openai/gpt-oss-120b | $0.80 | $0.80 | $0.8000 | $0.8000 | $1.60 | +$1.40 (save 87.5%) |
| #32 | NCHC TAIWAN AI RAP國網· Standard · Taiwan gpt-oss-120b | $2.00 | $2.00 | $2.00 | $2.00 | $4.00 | +$3.80 (save 95.0%) |
1 offerings excluded from cost ranking (missing required price fields or filtered out):
Ollama (ollama/gpt-oss:120b-cloud): Local / Free ($0.00) tier (toggle checkbox above to include)