GPT-4o Pricing Calculator

GPT-4o lists at $2.50 / 1M input and $10.00 / 1M output. The table below shows GPT-4o alongside every other current OpenAI tier so you can pick the cheapest model that meets your quality bar. Plug your real traffic into the cost calculator for an exact monthly figure, or see the head-to-head with Anthropic on the Claude pricing page.
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

When GPT-4o is the right pick

GPT-4o still earns its $10/1M output rate on vision-heavy workloads, mature fine-tuned pipelines, and apps that rely on its specific tool-calling reliability. For pure text reasoning, GPT-5.5 is both cheaper on input and smarter on most benchmarks — switching is a one-line change.

GPT-4o vs GPT-4o mini at scale

At 10M requests/month with 1.5K input and 400 output tokens each, GPT-4o costs roughly $77,500/mo. The same workload on GPT-4o mini is about $4,650/mo — a 16× saving. Most teams cascade: GPT-4o mini handles 80% of traffic, GPT-4o handles the rest. See the 60% savings playbook for the exact routing logic.

Related guides

Compare with Claude pricing, Gemini pricing, or jump to the full OpenAI pricing page. For long-term price trends, see the LLM pricing history.

Frequently asked questions