$0.60 / $1.80per 1M tokens in / out
$0.11cache read · −82%
#432on OpenRouter by tokens · 134M / week
Price sheetper 1M tokens
| Input | $0.60 | list |
| Output | $1.80 | |
| Cache read | $0.11 | −82% vs input |
| Context · max output | 66K · 16K | tokens |
introductory price; end date not published
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| Novita | $0.60 | $1.80 | 66K |
In Z.ai's line-upper 1M in / out
| GLM-4-Air-250414 | $0.50 / $0.50 | −44% |
| GLM-Z1-Air | $0.50 / $0.50 | −44% |
| GLM 5.3 FlashX | $0.37 / $1.25 | −34% |
| GLM 4.5V | $0.60 / $1.80 | this model |
| GLM 4.5 | $0.60 / $2.20 | +11% |
| GLM-4.6 | $0.60 / $2.20 | +11% |
| GLM-4-Long | $1 / $1 | +11% |
Cheaper for the same workvs GLM 4.5V
| MiMo v2.6 Pro thinkingOpen | -40% | score ×6.9 | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -42% | score ×6.7 | $0.26 |
| Claude Haiku 5.5 max | -78% | score ×6.5 | $0.21 |
| MiniMax M3.1 Flash thinking | -71% | score ×6.4 | $0.22 |
| GLM 5.3 Flash maxOpen | -74% | score ×6.2 | $0.28 |
Pricing questions
How much does GLM 4.5V cost?›
$0.60 per 1M input tokens and $1.80 per 1M output tokens. Cached input is $0.11.
Is GLM 4.5V 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 $0.11 per 1M, 82% below the input price.
What is a cheaper alternative to GLM 4.5V?›
MiMo v2.6 Pro at thinking effort costs -40% per task with a score ×6.9 on Humanity's Last Exam.