GLM 4.5 Air
GLM 4.5 AirRankingin thinking mode?
Alternatives?
CheaperGLM 4.7 FlashthinkingOpen×2.1-66%$0.061 / $0.40
BetterGPT OSS 20BhighOpen+30%-92%$0.011
CheaperHy3 previewthinkingOpen+99%-33%$0.18 / $0.60Memory (4-bit): 66 GB → 179 GB
CheaperRing 2.6 1TOpen+99%-12%$0.29Context: 131K → 128K+1
CheaperQwen3.5 4BthinkingOpen+98%-86%$0.03 / $0.15GLM 4.7 FlashthinkingOpen×2.1-66%$0.061 / $0.40Hy3 previewthinkingOpen+99%-33%$0.18 / $0.60Memory (4-bit): 66 GB → 179 GBRing 2.6 1TOpen+99%-12%$0.29Context: 131K → 128K+1Qwen3.5 4BthinkingOpen+98%-86%$0.03 / $0.15
MiMo v2 Omnithinking+96%-59%$0.14 / $0.28GPT OSS 20BhighOpen+30%-92%$0.011MiMo v2.5thinkingOpen+95%-59%$0.019Memory (4-bit): 66 GB → 186 GB
Mercury 2high+52%-12%$0.039Context: 131K → 128KGPT-5 Minihigh+47%+62%$0.053MiMo v2.5 ProthinkingOpen×2+28%$0.054Memory (4-bit): 66 GB → 614 GBGLM 4.7 FlashthinkingOpen×2.1-66%$0.061 / $0.40
Step 3.7 FlashhighOpen×2.1same$0.20 / $1.15Memory (4-bit): 66 GB → 121 GB
MiniMax M2.5thinkingOpen×2.1+24%$0.30 / $1.20Memory (4-bit): 66 GB → 137 GBQwen3.6 35B A3BthinkingOpen×2.1+31%$0.48
Mistral Medium 3.5highOpen×2+606%$0.50Memory (4-bit): 66 GB → 77 GBGLM 5.2maxOpen×2.1—$1.47Memory (4-bit): 66 GB → 452 GBGLM 4.7 FlashthinkingOpen×2.1—$0.061 / $0.40GLM 5V Turbothinking×2.1—$1.20 / $4GLM 5 Turbothinking×2.1—$1.20 / $4GLM 5thinkingOpen×2.1—$1 / $3.20Memory (4-bit): 66 GB → 452 GBGLM 5.1thinkingOpen×2.1—$1.02Memory (4-bit): 66 GB → 452 GBGLM 4.7thinkingOpen×2.1—$0.60 / $2.20Memory (4-bit): 66 GB → 215 GBGLM-4.6non-thinkingOpen+65%—$0.60 / $2.20Memory (4-bit): not verifiedAll Z.ai models →Run it yourself
estimateBenchmarks
all categoriesFAQ
How much does GLM 4.5 Air cost?›
$0.20 per 1M input tokens and $1.10 per 1M output tokens; cached input $0.03 per 1M; cheapest via Novita at $0.13 / $0.85.
Is GLM 4.5 Air free to use?›
There is no free API; the cheapest paid price is $0.13 per 1M input tokens. The weights are open, so you can run it yourself.
How good is GLM 4.5 Air, and what is it best at?›
#221 of 334 in Chat & Knowledge, #90 of 239 in Coding, #116 of 242 in Agents & Tool Use, #114 of 195 in Writing & Language.
Is GLM 4.5 Air better than Sarvam 105B?›
On τ²-bench · AA, GLM 4.5 Air scores 46.5 vs 46.8 — about the same.
How can I use GLM 4.5 Air?›
Through the API of DeepInfra, Novita, SiliconFlow.
What is the context window of GLM 4.5 Air?›
131K tokens, with up to 98K output tokens.
When was GLM 4.5 Air released? Is there a newer version?›
Released 2025-07-28. It has been superseded by GLM 4.7 Flash.
Is GLM 4.5 Air open source?›
Yes, the weights are open (MIT licence).
Can I run GLM 4.5 Air locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can GLM 4.5 Air read images?›
No, it accepts text only.
What is GLM 4.5 Air?›
GLM 4.5 Air is an open-weights language model from Z.ai, released Jul 2025.
What are the best alternatives to GLM 4.5 Air?›
GLM 4.7 Flash (cheaper), GPT OSS 20B (better).