$0.60 / $2.20per 1M tokens in / out
$0.11cache read · −82%
Price sheetper 1M tokens
| Input | $0.60 | list |
| Output | $2.20 | |
| Cache read | $0.11 | −82% vs input |
| Context | 200K | tokens |
introductory price; end date not published
Where to buy4 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.40 | $1.60 | — |
| Featherless | $0.55 | $2.20 | — |
| Novita | $0.55 | $2.20 | — |
| Z.AIlab | $0.60 | $2.20 | — |
In Z.ai's line-upper 1M in / out
| GLM-Z1-Air | $0.50 / $0.50 | −50% |
| GLM 5.3 FlashX | $0.37 / $1.25 | −41% |
| GLM 4.5 | $0.60 / $2.20 | 0% |
| GLM-4.6 | $0.60 / $2.20 | this model |
| GLM-4-Long | $1 / $1 | 0% |
| GLM-4.5-AirX | $1.10 / $4.50 | +95% |
| GLM-4.1V-Thinking-FlashX | $2 / $2 | 2× |
Cheaper for the same workvs GLM-4.6
| MiMo v2.6 Pro thinkingOpen | -46% | score ×3.1 | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -48% | score ×3 | $0.26 |
| Claude Haiku 5.5 max | -80% | score ×2.9 | $0.21 |
| MiniMax M3.1 Flash thinking | -74% | score ×2.9 | $0.22 |
| GLM 5.3 Flash maxOpen | -76% | score ×2.8 | $0.28 |
Pricing questions
How much does GLM-4.6 cost?›
$0.60 per 1M input tokens and $2.20 per 1M output tokens. Cached input is $0.11.
Is GLM-4.6 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-4.6?›
MiMo v2.6 Pro at thinking effort costs -46% per task with a score ×3.1 on Humanity's Last Exam.