OpenAI Pricing Calculator (GPT-5, GPT-4o, gpt-oss)

Every current OpenAI API model and its price per million tokens. For monthly bill projections based on your traffic, use the full cost calculator. Pricing sourced from OpenAI's official pricing page and refreshed weekly.
ModelInput / 1MOutput / 1MContext
GPT-5.5 (xhigh)
OpenAI
$1.25$10.00922K
GPT-5.5 (high)
OpenAI
$1.25$10.00922K
GPT-5.5 (medium)
OpenAI
$1.25$10.00922K
GPT-5.5 (low)
OpenAI
$1.25$10.00922K
GPT-5.3 Codex (xhigh)
OpenAI
$1.25$10.00400K
GPT-5.4 mini (xhigh)
OpenAI
$0.25$2.00400K
GPT-5.4 nano (xhigh)
OpenAI
$0.05$0.40400K
o3
OpenAI
$2.00$8.00200K
GPT-4o
OpenAI
$2.50$10.00128K
GPT-4o mini
OpenAI
$0.15$0.60128K
gpt-oss 120B
OpenAI
$0.039$0.10131K
gpt-oss 20B
OpenAI
$0.03$0.14131K

Which OpenAI model should you use?

GPT-5.5 is the new default for production — smarter than GPT-4o at half the input cost. GPT-5.4 mini ($0.25/1M input) handles 80% of chat and RAG workloads at a fraction of the price. GPT-5.4 nano ($0.05/1M) is the cheapest first-class option; use it for classification, routing, and high-volume tool calls.

GPT-4o vs GPT-5 pricing

GPT-4o is still listed but is almost never the right choice in 2026 — GPT-5.5 is cheaper on input, matches on output, and scores higher on every public benchmark. Migration is a one-line model-name change.

How to lower your OpenAI bill

Three levers, ordered by impact: (1) Enable prompt caching for any system prompt over 1,024 tokens — 50% off the cached portion. (2) Use the Batch API for non-realtime workloads — another 50% off. (3) Tier down: a lot of GPT-5.5 traffic can move to GPT-5.4 mini with no measurable quality drop.

Frequently asked questions