OpenAI · Very Fast · Updated 2026-11

GPT-4o mini API Pricing & Cost Breakdown

High-volume classification, routing, customer support chatbots, and lightweight RAG.

Input / 1M Tokens
$0.15
Cached Input / 1M
$0.075
Output / 1M Tokens
$0.60
Context Window
128K

Workload Cost Scenarios (30-Day Billing)

Over 16x cheaper than GPT-4o on both input and output tokens.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $1.40 $1.23
Growing Startup (2,500 req/day) 2500 / 700 $59.63 $52.59
Production Scale (50,000 req/day) 3000 / 800 $1,395.00 $1,226.25

Compare GPT-4o mini Against Alternatives

Lower-Cost Alternative Models

Gemini 2.0 Flash ($0.40/1M out) Qwen 2.5 72B ($0.40/1M out) Grok 3 Mini ($0.50/1M out)

Frequently Asked Questions

What is GPT-4o mini API pricing per 1M tokens?

Standard input is $0.15/1M, cached input is $0.075/1M, and output is $0.60/1M.

What is the context window of GPT-4o mini?

GPT-4o mini supports a 128K token context window with up to 16,384 max output tokens.

How much does prompt caching save on GPT-4o mini?

Prompt caching reduces cached input token rates by 50% compared with uncached input.

What workloads is GPT-4o mini best suited for?

High-volume classification, routing, customer support chatbots, and lightweight RAG.