A compact Z.ai model for complex documents: tables, formulas and multi-column layouts. Runs on any card and processes many pages in parallel.
| OmniDocBench v1.5 | 94.6 |
|---|
Which GPU does GLM-OCR need?
The entry configuration is 1x RTX3080TI, which delivers around 105 tokens per second. For more parallel requests and headroom on speed, go with 1x H200.
How much does GLM-OCR cost?
An hour of GLM-OCR runs from $0.37 to $8.20 depending on the GPU configuration. Billing is hourly: you pay for server time, not for tokens.
How do I call GLM-OCR from my code?
Once deployed you get an OpenAI-compatible endpoint: point any OpenAI client at the base_url you receive and pass glm-ocr as the model name. Code written against the OpenAI API needs no changes.
Does the data stay private?
Yes. GLM-OCR runs on a dedicated GPU server inside a private environment: requests and responses never reach the model vendor and are not used for training.
What context window and license does GLM-OCR have?
GLM-OCR holds 32K tokens of context per request and ships under the MIT license, so you can use it commercially on your own hosting terms.