GLM 4.5 Air
by NanoGPT · listed Apr 2025T
Efficient GLM model for fast reasoning, coding, and agent workflows
Current rates USD per 1M tokens
Input$0.12
Output$0.80
Cache read—
Cache write—
Against the market
On the record
- Model id
zai-org/GLM-4.5-Air- Context window
- 128K tokens
- Max output
- 98K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-04-15
- Last updated
- 2025-04-15
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Z.AI Coding Planfree in · free out
- Zhipu AI Coding Planfree in · free out
- submodel$0.10 in · $0.50 out
- ZenMux$0.11 in · $0.56 out
- 302.AI$0.114 in · $0.286 out
- Hugging Face$0.13 in · $0.85 out
- NovitaAI$0.13 in · $0.85 out
- LLM Gateway$0.13 in · $0.85 out
- Kilo Gateway$0.13 in · $0.85 out
- OpenRouter$0.13 in · $0.85 out
- SiliconFlow (China)$0.14 in · $0.86 out
- SiliconFlow$0.14 in · $0.86 out
- Vercel AI Gateway$0.20 in · $1.10 out
- Zhipu AI$0.20 in · $1.10 out
- Merge Gateway$0.20 in · $1.10 out