Azure OpenAI model

GPT-4o mini cost on Azure OpenAI

Low-cost small model for high-volume, latency-sensitive tasks.

Open the calculator All models
Illustrative pricing. Rates for GPT-4o mini are representative values for East US public Azure, last verified 1 Jun 2026. Verify against the Azure OpenAI pricing page before budgeting.

GPT-4o mini at a glance

Same context family as GPT-4o at a fraction of the token cost. Reach for it first on anything where a smaller model is good enough.

Input tokens $0.00015 per 1K
Output tokens $0.0006 per 1K
PTU floor / mo $2,448 15 PTU minimum
Example request $0.00078 2K in / 800 out

Best for

  • High-volume classification and routing
  • Cheap first-pass summarization
  • Cost-sensitive RAG

Estimate your bill

Run your own token counts and volume.

The calculator opens pre-set to GPT-4o mini. Enter your input/output token sizes and monthly requests to see pay-as-you-go cost and the PTU break-even for your workload.

Open the calculator with GPT-4o mini

Frequently asked questions

GPT-4o mini cost on Azure OpenAI.

How much does GPT-4o mini cost on Azure OpenAI? GPT-4o mini is priced at $0.00015 per 1,000 input tokens and $0.0006 per 1,000 output tokens (illustrative East US rates, verified 1 Jun 2026). A request with 2,000 input and 800 output tokens costs about $0.00078.
When is provisioned throughput (PTU) cheaper than pay-as-you-go for GPT-4o mini? Once steady monthly usage passes roughly 3,138,462 requests per month at typical token sizes, the PTU floor of $2,448 per month beats pay-as-you-go token spend. Below that, pay-as-you-go is cheaper — and PTU should only be committed if your tokens-per-minute throughput justifies the minimum deployment.
What is the minimum PTU deployment for GPT-4o mini? 15 provisioned throughput units, about $2,448 per month on a one-month reservation (illustrative). Verify current minimums and rates against the Azure pricing page before committing.