$1 / $3.20per 1M tokens in / out
$0.20cache read · −80%
#126on OpenRouter by tokens · 38.2B / week
Price sheetper 1M tokens
| Input | $1 | list |
| Output | $3.20 | |
| Cache read | $0.20 | −80% vs input |
| Context · max output | 203K · 131K | tokens |
introductory price; end date not published
Where to buy8 providers · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| lab-qwen | $0.57 | $2.58 | — |
| DeepInfra | $0.60 | $2.08 | — |
| Baidu | $0.70 | $2.24 | 203K |
| SiliconFlow | $0.95 | $2.55 | 205K |
| Amazon Bedrock | $1 | $3.20 | 203K |
| AWS Bedrock | $1 | $3.20 | — |
| Novita | $1 | $3.20 | 203K |
| Venice | $1 | $3.20 | 198K |
In Z.ai's line-upper 1M in / out
| GLM 4.5 | $0.60 / $2.20 | −35% |
| GLM-4.6 | $0.60 / $2.20 | −35% |
| GLM-4-Long | $1 / $1 | −35% |
| GLM 5 | $1 / $3.20 | this model |
| GLM-4.5-AirX | $1.10 / $4.50 | +26% |
| GLM-4.1V-Thinking-FlashX | $2 / $2 | +29% |
| GLM 5.3 | $1.40 / $4.40 | +39% |
Cheaper for the same workvs GLM 5
| MiMo v2.6 Pro thinkingOpen | -65% | score +66% | $0.13 |
| DeepSeek V4.1 Flash 1017 maxOpen | -66% | score +62% | $0.26 |
| Step 5 Preview thinkingOpen | -8% | score +57% | $1.03 |
| Claude Haiku 5.5 max | -87% | score +55% | $0.21 |
| MiniMax M3.1 Flash thinking | -83% | score +53% | $0.22 |
Pricing questions
How much does GLM 5 cost?›
$1 per 1M input tokens and $3.20 per 1M output tokens. Cached input is $0.20.
Is GLM 5 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 $0.20 per 1M, 80% below the input price.
Is GLM 5 cheaper than GLM 4.7?›
No: $1 / $3.20 against $0.60 / $2.20, 55% more per token.
What is a cheaper alternative to GLM 5?›
MiMo v2.6 Pro at thinking effort costs -65% per task with a score +66% on Humanity's Last Exam.