GLM-4.5-Air
GLM-4.5-Air is an open-weights AI model from Zhipu with an index score of 120 (GPT-4 = 100), provisional.
12064–176Index scoreProvisional · results in fewer than three areas so far; not ranked yet
$0.13/ $0.85Price per million tokensinput / output · via OpenRouter
131KContext windowtokens it reads at once
20 Jul 2025Released1 year 4 months ago
Where it sitson the frontier
o1-mini reached this score 10 months earlier.
Test resultsby area · tick = best by any model
Reasoning & knowledgeevidence
Mathsno evidence yet
Codingevidence
Agentsno evidence yet
Professional workno evidence yet
Novel problemsno evidence yet
Long tasksno evidence yet
Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.
What others sayrank on 6 leaderboards
LMArena · Mathsmaths questions in chat#147of 346 · 1386LMArena · Instruction followingfollowing detailed instructions#159of 362 · 1361LMArena · Codingcoding questions in chat#157of 357 · 1427LMArena · Textoverall chat quality, judged by people#160of 362 · 1373LMArena · Long promptslong, complex requests#157of 340 · 1380LMArena · Creative writingcreative writing#168of 360 · 1327
Best attop three among current models
Not in the top three among current models on any category we track.
Where to use itprices checked 18 Nov 2026
API providers 3 · per 1M tokens, in / out
Run it yourself
Official weightszai-org/GLM-4.5-Air↗Host prices from OpenRouter; going direct can differ.
Facts and sources
Released20 Jul 2025
Announcementnot linked yet
Release entry–
Scored asGLM-4.5-Air
Output speed–
Hugging Facezai-org/GLM-4.5-Air ↗