by Z.AI
GLM-OCR is a lightweight professional OCR model with only 0.9B parameters, yet multiple capabilities have reached SOTA levels, establishing a new benchmark for document parsing with a "small size, high precision" approach.
| Input | $0.03 / 1M tokens |
| Output | $0.03 / 1M tokens |
| Context window | 32,000 tokens |
| Modalities | image |
Use glm-ocr via the AIHubMix unified API — one interface for every major LLM.