OpenAI model product
GPT-5 nano is the fastest, cheapest version of GPT-5 from OpenAI.
Updated Aug 12, 2026. Default version: GPT-5 nano
Technical details for the model's default version.
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Benchmark scores for GPT-5 nano.
| FrontierMath | 9.6% | 14 | 17 | 18.8% | C | |
| HMMT 2025 | 75.6% | 26 | 33 | 21.9% | C | |
| AIME 2025 | 85.2% | 60 | 114 | 47.8% | C | |
| Humanity's Last Exam | 8.7% | 84 | 93 | 9.8% | C | |
| GPQA | 71.2% | 123 | 234 | 47.6% | C |
Preference and agent-evaluation results for the default version.
| vision | overall | 92 | 1161.7 | 3,973 | N/A | |
| vision style control | overall | 98 | 1147.6 | 3,973 | N/A | |
| text | overall | 204 | 1320.4 | 8,293 | N/A | |
| text style control | overall | 208 | 1337.5 | 8,293 | N/A |
Provider-specific output speed and catalog latency for GPT-5 nano. Runtime does not affect the capability score.
| OpenAI | 500 tok/s | 0.3 s | 400K | 128K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Official vendor API pricing appears first, followed by individual provider offers.
| Impossibl | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| NanoGPT | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| FastRouter | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| NEAR AI Cloud | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| OrcaRouter | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| Kilo Gateway | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| Merge Gateway | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| Vercel AI Gateway | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| OpenRouter | openai/gpt-5-nano | global | $0.05 | $0.40 | 400K | |
| OpenAI | gpt-5-nano | global | $0.05 | $0.40 | 400K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Available versions of this model. The score column identifies the version used in the overall ranking.
| GPT-5 nano | 31.1 | N/A | 400K | 128K | No | Proprietary |
Key information about GPT-5-nano and its available data.
GPT-5 nano is the fastest, cheapest version of GPT-5 from OpenAI. It is well-suited for summarization and classification tasks with average reasoning capabilities and very fast speed.
Data as of 2026-08-11.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
Common questions about GPT-5-nano.
GPT-5-nano's default version was released on Aug 7, 2025.
GPT-5-nano's official API price is $0.05 per million input tokens and $0.40 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.05 input and $0.40 output via Impossibl.
GPT-5-nano was created by OpenAI.
The default version has a 400K token context window.
No. The default version is not marked as having publicly available weights.
10 provider offerings are linked to the default version.
Nearby ranked alternatives include GPT-4.1, Qwen3 VL 30B A3B Thinking, Qwen3 32B.