GPT-5 nano (2025-08-07)

No priced offering is listed for this model yet.

Family

gpt-nano

Not stated on OpenAI’s pages: max input, input modalities, output modalities, reasoning efforts, reasoning can be off, max thinking budget, built-in tools, knowledge cutoff, aliases.

• Epoch AI · Chess Puzzles 22%

  #57 of 85 listed models · high effort · ±4.16

  Also listed: low effort 15% · minimal effort 2%

• Epoch AI · FrontierMath Tier 4 v2 2.4%

  #60 of 65 listed models · high effort · ±2.44

• Epoch AI · FrontierMath Tiers 1–3 20%

  #72 of 84 listed models · high effort · ±2.37

  Also listed: low effort 6% · minimal effort 1.8%

• Epoch AI · GPQA Diamond 69.4%

  #97 of 168 listed models · high effort · ±2.76

  Also listed: medium effort 67.4% · low effort 57.6% · minimal effort 48.5%

• Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 18 – Nov 5, 2026
• EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 28, 2026
• changes we made

No changes recorded yet.

• Deprecations (opens in a new tab) developers.openai.com · checked Nov 8, 2026
• LiteLLM model prices: gpt-5-nano-2025-08-07 (community data, MIT) (opens in a new tab) github.com · checked Nov 4, 2026

OpenAI’s official policies: data use, privacy, terms →

Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data

OpenAI · United States · openai.com

Snapshots, the same family and other models from this provider

• GPT-5 nano
• GPT-6-Cyber
• gpt-6-astra-law
• GPT-6 Rosalind
• GPT-6.1 Terra
• GPT-6.1 Sol
• GPT-6 Luna
• GPT-6 Sol