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.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
GPT-5.5 (xhigh) OpenAI | $1.25 | $10.00 | 922K |
GPT-5.5 (high) OpenAI | $1.25 | $10.00 | 922K |
GPT-5.5 (medium) OpenAI | $1.25 | $10.00 | 922K |
GPT-5.5 (low) OpenAI | $1.25 | $10.00 | 922K |
GPT-5.3 Codex (xhigh) OpenAI | $1.25 | $10.00 | 400K |
GPT-5.4 mini (xhigh) OpenAI | $0.25 | $2.00 | 400K |
GPT-5.4 nano (xhigh) OpenAI | $0.05 | $0.40 | 400K |
o3 OpenAI | $2.00 | $8.00 | 200K |
GPT-4o OpenAI | $2.50 | $10.00 | 128K |
GPT-4o mini OpenAI | $0.15 | $0.60 | 128K |
gpt-oss 120B OpenAI | $0.039 | $0.10 | 131K |
gpt-oss 20B OpenAI | $0.03 | $0.14 | 131K |
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.