Model
Model explorer

GPT-5 nano

CLOSED
OpenAI · GPT-5 family · released Aug 7, 2025

Smallest, fastest GPT-5 variant for high-volume, latency-sensitive workloads.

ReasoningCodingVisionFunction callingTool useAgentic
1583.9
Elo · rank #121
Parameters
Undisclosed
Active params
Context
400K tokens
Architecture
Smallest, fastest sibling of GPT-5's unified architecture; dense transformer, exact size undisclosed
License
Proprietary (OpenAI API Terms)
Languages
API price (in/out)
$0.05 / $0.4
Modalities
text · vision
Benchmark results
Bar shows position within the tracked field; marker = field best
AIMEMath81.1%#73
best: GPT-5.2 · 100.0%
ARC-AGI-1Reasoning20.7%#19
best: GPT-6 Astra · 98.5%
ARC-AGI-2Reasoning22.6%#20
best: GPT-6 Astra · 95.0%
best: GPT-5.6 Sol · 89.0%
best: GPT-5.6 Sol · 83.0%
GPQA DiamondReasoning71.2%#127
best: GPT-6 Astra · 96.0%
Humanity's Last ExamReasoning8.2%#103
best: Claude Opus 5 · 64.7%
LiveCodeBenchCoding78.9%#55
best: DeepSeek-V4-Pro (Think Max) · 93.5%
MMLU-ProKnowledge78.0%#65
best: Claude Fable 5 · 91.5%
SimpleQAKnowledge11.0%#34
best: GPT-4.5 · 62.5%
Run it locally
Closed weights — available via API only. No local deployment.
Input / M tok
$0.05
Output / M tok
$0.4
API price $0.05/$0.4 · each benchmark row carries its own source badge (see methodology)