⚡
Azure OpenAI PTU Calculator
Provisioned Throughput Units
Parameters
Model
gpt-5.5
gpt-5.4
gpt-5.3-codex
gpt-5.2
gpt-5.2-codex
gpt-5.1
gpt-5.1-codex
gpt-5
gpt-5-mini
gpt-4.1
gpt-4.1-mini
gpt-4.1-nano
o3
o4-mini
gpt-4o
gpt-4o-mini
Target Input TPM (tokens/min)
Output / Input Ratio
0.30
Target PTU Utilization
70%
Deployment Type
Global — $260/PTU/month
Data Zone — $286/PTU/month
Regional — $286/PTU/month
💡 Formula
N_PTU = ⌈ Target Input TPM ÷ (Model Input TPM/PTU × Utilization%) ⌉
Break-even when PTU cost = PayGo cost at the same token volume.
🔢 Recommended PTU Purchase
—
Minimum PTUs (rounded)
—
Recommended PTUs (+10% buffer)
—
Max Input TPM (theoretical)
—
Max Output TPM (theoretical)
💰 Break-even Analysis
—
PTU Monthly Cost
—
PayGo (at full PTU load/month)
—
Break-even Input Tokens/month
—
Break-even Utilization %
—
📊 Cost Comparison by Utilization
Utilization
Input Tokens/month
PTU Cost
PayGo Cost
Savings
📈 Cost vs Token Volume