OpenAIProvisional

GPT-5.4 nano

GPT-5.4 / nano · gpt-5.4-nano

OpenAI cheapest GPT-5.4-class model for simple high-volume coding support tasks.

Objective score

26.7

Confidence

79%

Price evidence

Pricing evidence pending

Support this model Compare trend Official source

Other primary tiers in this family

Default mininano

Scenario evidence

Six task-specific rankings

Feature development#45Obj. 26.70 · 0%Debug and repair#37Obj. 420 · 0%Refactoring#34Obj. 420 · 0%Code review#33Obj. 43.50 · 0%Large-repo agent work#44Obj. 22.70 · 0%Frontend / UI#34Obj. 420 · 0%

Evidence state

Signal coverage

Benchmarks: 2
Rank points: 7
Usage: 2
Agent: 0
Sources: 2

Objective evidence

Benchmarks and public signals

Swebench: —
Livecodebench: —
Aider: —
Artificial Analysis: 56.1
Openrouter Usage: 0.6
Kilo Usage: —

Persistent history

Recent ranking points

Aug 1#44 · 28

Aug 1#44 · 28

Jul 31#44 · 28

Jul 31#44 · 28

Jul 31#44 · 28

Jul 31#44 · 28

Usage signals

OpenRouter0.6%

Overall0.4%

Agent and tool signals

Evidence is being collected. Missing data is not treated as zero.

Source trail

OpenAI all-models catalog lists GPT-5.4 nano as the cheapest GPT-5.4-class model.Artificial Analysis Coding Agents · ok WebDev Arena · ok