Model

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

1595.3

Elo · rank #100

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%#72

best: GPT-5.2 · 100.0%

ARC-AGI-1Reasoning20.7%#16

best: GPT-5.6 · 96.5%

ARC-AGI-2Reasoning22.6%#17

best: GPT-5.6 · 92.5%

FrontierMath (Tiers 1-3)Math8.3%#12

best: GPT-5.6 · 89.0%

FrontierMath (Tier 4)Math2.1%#10

best: GPT-5.6 · 83.0%

GPQA DiamondReasoning71.2%#120

best: GPT-5.6 · 94.6%

Humanity's Last ExamReasoning8.2%#96

best: Claude Sonnet 5 · 57.4%

LiveCodeBenchCoding78.9%#53

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

GPT-5 family

Elo progression across releases

GPT-5Aug 20252082.7 GPT-5 miniAug 20251873.5 GPT-5 nanoAug 20251595.3 GPT-5 ProAug 20252349.9 GPT-5-CodexSep 20252103.4

Resources

DOCSdevelopers.openai.com/api/docs/models/gpt-5-nano APIAvailable via OpenAI API

API price $0.05/$0.4 · each benchmark row carries its own source badge (see methodology)