GPT-5 mini
Near-frontier intelligence at a much lower price point, aimed at high-volume and latency-sensitive workloads.
Pricing
Input$0.25 / 1M checked Jul 19, 2026
Cached input$0.025 / 1M
Output$2 / 1M checked Jul 19, 2026
Batch pricing is available.
Cost bandBalanced
Free tierNo free API tier.
Limits
Context window400k checked Jul 19, 2026
Max output128k
Knowledge cutoffMay 31, 2024
DeploymentOpenAI API
OpenAI-compatible APIYes
ModalitiesText, Image input
Where it fits
Best forHigh-volume assistants, agent backplanes, budget-sensitive coding and workflow automation.
Business fitBest OpenAI default when you need quality near the top tier without flagship pricing.
Capabilities
Reasoning token supportFunction callingStructured outputsWeb searchFile searchCode interpreterMCP
Benchmark scores
Composite76 / 100
Coding78 / 100 (SWE-bench Verified)
Reasoning74 / 100 (GPQA Diamond)
Long context70 / 100 (RULER 128K)
Vision73 / 100 (MMMU)
Instruction following80 / 100 (IFEval)
Editorial aggregate of published benchmark results as of Aug 1, 2025. These are not independent measurements run by this site.
Change history
- Aug 7, 2025New modelGPT-5 mini stabilized Near-frontier quality at $0.25/$2 per 1M. Replaces GPT-4o mini as the OpenAI workhorse default.
Data
Last checkedJul 19, 2026
Cross-checked againstopenrouter.ai/openai/gpt-5-mini
Verify with provider documentation before committing spend. Report an error and it gets fixed with a logged correction.