GPT-4o

OpenAI · workhorse · released May 13, 2024 · gpt-4o

GPT-4o family:GPT-4o·GPT-4o mini

OpenAI's previous multimodal flagship — strong vision, long-proven reliability, and broad platform support.

Pricing

Input$2.50 / 1M checked Jul 19, 2026
Cached input$1.25 / 1M
Output$10 / 1M checked Jul 19, 2026

Batch pricing is available.

Cost bandBalanced
Free tierFree tier in ChatGPT; API is paid.

Limits

Context window128k checked Jul 19, 2026
Max output16,384
Knowledge cutoffOct 1, 2023
DeploymentOpenAI API, Azure OpenAI
OpenAI-compatible APIYes
ModalitiesText, Image input

Where it fits

Best forProduction workloads requiring stable multimodal quality; drop-in for teams not yet on GPT-5.
Business fitReliable choice when you need battle-tested performance and GPT-5 migration isn't yet warranted.

Capabilities

Function callingStructured outputsVisionFile searchCode interpreter

Benchmark scores

Composite82 / 100
Coding82 / 100 (SWE-bench Verified)
Reasoning80 / 100 (GPQA Diamond)
Long context78 / 100 (RULER 128K)
Vision85 / 100 (MMMU)
Instruction following86 / 100 (IFEval)

Editorial aggregate of published benchmark results as of Nov 1, 2024. These are not independent measurements run by this site.

Change history

No recorded changes for this model yet. Pricing and context are checked daily; changes appear here with dates and sources.

Data

Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/openai/gpt-4o

Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.

Open in the comparison table JSON API