Z.ai › GLM 4.5 Air › Pricing
$0.20 / $1.10per 1M tokens in / out
$0.03cache read · −85%
#192on OpenRouter by tokens · 11.5B / week
Price sheetper 1M tokens
| Input | $0.20 | list |
| Output | $1.10 | |
| Cache read | $0.03 | −85% vs input |
| Context · max output | 131K · 98K | tokens |
introductory price; end date not published
Where to buy3 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Novita | $0.13 | $0.85 | — |
| SiliconFlow | $0.14 | $0.86 | 131K |
| DeepInfra | $0.20 | $1.10 | — |
In Z.ai's line-upper 1M in / out
| GLM-OCR | $0.20 / $0.20 | −53% |
| GLM 5.3 Flash | $0.15 / $0.50 | −44% |
| GLM-4.1V-Thinking-Flash | $0.30 / $0.30 | −29% |
| GLM 4.5 Air | $0.20 / $1.10 | this model |
| GLM-4-Air-250414 | $0.50 / $0.50 | +18% |
| GLM-Z1-Air | $0.50 / $0.50 | +18% |
| GLM 5.3 FlashX | $0.37 / $1.25 | +39% |
Cheaper for the same workvs GLM 4.5 Air
| Claude Haiku 5.5 max | -53% | score ×3.9 | $0.21 |
| MiniMax M3.1 Flash thinking | -38% | score ×3.9 | $0.22 |
| GLM 5.3 Flash maxOpen | -44% | score ×3.8 | $0.28 |
| Qwen3.8 Flash thinkingOpen | -46% | score ×3.6 | $0.37 |
| GPT-6 Luna max | -53% | score ×3.4 | $0.068 |
Pricing questions
How much does GLM 4.5 Air cost?›
$0.20 per 1M input tokens and $1.10 per 1M output tokens. Cached input is $0.03.
Is GLM 4.5 Air free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
How much does prompt caching save?›
Cache reads cost $0.03 per 1M, 85% below the input price.
What is a cheaper alternative to GLM 4.5 Air?›
Claude Haiku 5.5 at max effort costs -53% per task with a score ×3.9 on Humanity's Last Exam.