π¨π³ Chinese model
GLM-4.7-FlashX
Text Function calling Reasoning
Pricing & specs
Input / 1M tokens $0.07
Output / 1M tokens $0.40
Cache / 1M tokens $0.01
Context window 200K tokens
Max output 131K tokens
Updated 2026-01-19
Docs Official docs β
Price source View source β
Providers
USD / 1M tokens Β· input / output
Zhipu GLM Official $0.07 / $0.40 Vercel AI Gateway lowest $0.06 / $0.40 LLM Gateway $0.07 / $0.40 Merge Gateway $0.07 / $0.40 ZenMux $0.07 / $0.42 DevPass (LLM Gateway) $0.07 / $0.40 302.AI $0.07 / $0.43 1 more at higher prices
Similar models Β· Top 5
GPT-5 Nano πΊπΈ 400K In $0.05 Β· Out $0.40 Β· Cache $0.01 Mistral Small 3.2 π«π· 128K In $0.10 Β· Out $0.30 Β· Cache β ERNIE 4.5 Turbo π¨π³ 128K In $0.12 Β· Out $0.48 Β· Cache $0.03 Doubao 1.5 Pro π¨π³ 256K In $0.12 Β· Out $0.30 Β· Cache $0.02 Hunyuan TurboS π¨π³ 256K In $0.12 Β· Out $0.30 Β· Cache β
Want to go deeper on AI and cloud cost management?
Explore more on AI infrastructure, model API cost and resource optimization at mofcloud.