About GPT-4o
GPT-4o is OpenAI's omni-generation model, the first in its lineup designed from the start around multimodal input, and the ChatGPT default for a long stretch before the GPT-5 era. In the API it takes text and images and returns text, with a context window that is modest by later standards.
OpenAI keeps it available primarily for continuity: a large base of integrations was built against its exact behaviour, and like-for-like stability matters more there than headline capability. New work generally starts on the GPT-5 family, which OpenAI positions as its successor in every role GPT-4o played.
GPT-4o's list price tells the migration story: it costs more per token than GPT-5 while offering a smaller context window — the classic pattern of a provider encouraging upgrades without breaking existing deployments. Its cached-input discount is also shallower than the newer families offer, halving input rather than cutting it by an order of magnitude, which compounds the gap for system-prompt-heavy services. For teams pinned to it by prompt-tuned behaviour, the practical move is measuring a sample workload on GPT-5 with the calculator here before committing to a switch; for everyone else it is mainly a reference point.
Frequently asked questions
How much does the GPT-4o API cost?
GPT-4o costs $2.5 per million input tokens and $10 per million output tokens, with cached input at $1.25 per million (50% off).
How much does a typical chat message cost with GPT-4o?
A short chat message (about 500 input and 250 output tokens) costs roughly $0.0037 with GPT-4o. At 1,000 such requests a day, that is about $112.50 per month.
Is GPT-4o cheap compared to similar models?
GPT-4o has the #23 cheapest input rate of the 29 models we track. On a mixed workload (10K input / 2K output), it costs $0.045 per request, versus $0.033 for Gemini 2.5 Pro.
What does GPT-4o cost per 1,000 tokens?
Per 1,000 tokens, GPT-4o costs $0.0025 for input and $0.0100 for output, or $0.0013 for cached input. Providers quote rates per million tokens ($2.5/M in, $10/M out here), so divide by a thousand for the per-1K figure older pricing pages used.
How large a prompt can GPT-4o take?
GPT-4o accepts up to 125K tokens of input context and can generate up to 16K tokens of output per request. At its input rate, filling the entire 125K-token window costs about $0.320 per request before any output.
Related
Compare all models at once ·Count tokens in your prompt · GPT-4o vs Gemini 2.5 Pro head-to-head
All OpenAI model costs: GPT-5.6 Sol · GPT-5.6 Terra · GPT-5.6 Luna · GPT-5.4 · GPT-5 · GPT-5 mini · GPT-5 nano · GPT-4o mini · o3 · o4-mini
Last updated 2026-09-03. Prices verified against OpenAI's official pricing page; see the methodology.