OpenAI model product
GPT-5-Nano
GPT-5-Nano is an OpenAI large language model for summarization and classification with average reasoning capabilities and very fast speed.
Updated Sep 8, 2026. Default version: GPT-5 nano
LLMBoard Score29.5GPT-5 nano
Coverage20%5 benchmark families
Context window400KTokens
Official input price$0.05OpenAI API
GPT-5-Nano Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
GPT-5-Nano Benchmark Results
Benchmark scores for GPT-5 nano.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFrontierMath | Score9.60% | Rank14 | Participants17 | Percentile18.75% | EvidenceC | Evaluated |
| BenchmarkHMMT 2025 | Score75.60% | Rank26 | Participants33 | Percentile21.88% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score85.20% | Rank63 | Participants119 | Percentile47.46% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision | Score1,159.24 rating | Rank75 | Participants107 | Percentile30.19% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,145.21 rating | Rank81 | Participants107 | Percentile24.53% | EvidenceA | Evaluated |
| BenchmarkHumanity's Last Exam | Score8.70% | Rank94 | Participants103 | Percentile8.82% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score71.20% | Rank133 | Participants247 | Percentile46.34% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text | Score1,319.60 rating | Rank152 | Participants210 | Percentile27.75% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,337.22 rating | Rank155 | Participants210 | Percentile26.32% | EvidenceA | Evaluated |
GPT-5-Nano Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorycreative writing | Rank29 | Rating / score1,117.23 | Votes206 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing | Rank30 | Rating / score1,091.86 | Votes206 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank66 | Rating / score1,177.43 | Votes193 | ObservationsN/A | Result date |
| Arenavision | Categoryhumor | Rank68 | Rating / score1,108.06 | Votes175 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank68 | Rating / score1,183.07 | Votes264 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhumor | Rank70 | Rating / score1,089.05 | Votes175 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank73 | Rating / score1,152.06 | Votes1,680 | ObservationsN/A | Result date |
| Arenavision | Categorydiagram | Rank75 | Rating / score1,140.47 | Votes522 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank75 | Rating / score1,169.49 | Votes1,790 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank75 | Rating / score1,159.24 | Votes3,950 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank76 | Rating / score1,157.02 | Votes264 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank76 | Rating / score1,144.78 | Votes193 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank76 | Rating / score1,154.54 | Votes522 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank76 | Rating / score1,156.18 | Votes1,680 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank81 | Rating / score1,145.21 | Votes3,950 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank82 | Rating / score1,150.94 | Votes1,790 | ObservationsN/A | Result date |
| Arenatext style control | Categoryspanish | Rank113 | Rating / score1,380.44 | Votes236 | ObservationsN/A | Result date |
| Arenatext | Categoryspanish | Rank117 | Rating / score1,360.85 | Votes236 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank123 | Rating / score1,350.64 | Votes204 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank126 | Rating / score1,328.43 | Votes204 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank128 | Rating / score1,268.64 | Votes225 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank128 | Rating / score1,313.24 | Votes572 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank128 | Rating / score1,336.92 | Votes572 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank132 | Rating / score1,278.79 | Votes225 | ObservationsN/A | Result date |
| Arenatext | Categorychinese | Rank135 | Rating / score1,356.78 | Votes512 | ObservationsN/A | Result date |
| Arenatext style control | Categorychinese | Rank136 | Rating / score1,378.93 | Votes512 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry mathematical | Rank143 | Rating / score1,352.87 | Votes435 | ObservationsN/A | Result date |
| Arenatext style control | Categorymath | Rank143 | Rating / score1,345.72 | Votes492 | ObservationsN/A | Result date |
| Arenatext | Categorymath | Rank145 | Rating / score1,317.16 | Votes492 | ObservationsN/A | Result date |
| Arenatext | Categoryindustry medicine and healthcare | Rank146 | Rating / score1,334.03 | Votes473 | ObservationsN/A | Result date |
GPT-5-Nano Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.05 input, $0.40 output per 1M
- Official provider
- OpenAI
- Lowest third-party
- From $0.05 input, $0.40 output per 1M via OrcaRouter
- Tracked offerings
- 14
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderOrcaRouter | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderNanoGPT | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderImpossibl | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderOpenRouter | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderOpenAI | Provider model IDgpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderLLM Gateway | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderNEAR AI Cloud | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderMerge Gateway | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderCloudflare AI Gateway | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context128K | Updated |
| ProviderFastRouter | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderOfox | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderVercel AI Gateway | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderEden AI | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
| ProviderKilo Gateway | Provider model IDopenai/gpt-5-nano | Regionglobal | Input / 1M$0.05 | Output / 1M$0.40 | Context400K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
GPT-5-Nano Runtime Performance
Provider-specific output speed and catalog latency for GPT-5 nano. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderOpenAI | Output Speed500.00 tok/s | Catalog Latency0.30 s | Max Input400K | Max Output128K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
GPT-5-Nano Specifications
Technical details for the model's default version.
- Version
- GPT-5 nano
- Released
- Aug 7, 2025
- Knowledge cutoff
- May 30, 2024
- Parameters
- N/A
- Context window
- 400K
- Max output
- 128K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
GPT-5-Nano Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGPT-5 nano | Released | LLMBoard29.51 | ParametersN/A | Context400K | Max output128K | Open weightsNo | LicenseProprietary |
Models similar to GPT-5-Nano
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
OP
GPT-4.1
OpenAI
OP
o1 pro
OpenAI
OP
o3 mini
OpenAI
OP
GPT-4.5
OpenAI
OP
o1
OpenAI
OP
GPT-4.1-mini
OpenAI
What is GPT-5-Nano?
Key information about GPT-5-Nano and its available data.
GPT-5-Nano is a version of GPT-5 from OpenAI. It is intended for summarization and classification tasks.
Data as of 2026-09-08.
FAQ
Common questions about GPT-5-Nano.
When was GPT-5-Nano released?
GPT-5-Nano's default version was released on Aug 7, 2025.
How much does GPT-5-Nano cost?
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 OrcaRouter.
Who created GPT-5-Nano?
GPT-5-Nano was created by OpenAI.
What is the context window for GPT-5-Nano?
The default version has a 400K token context window.
Is GPT-5-Nano open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer GPT-5-Nano?
14 provider offerings are linked to the default version.