Input

Output

Text Recognition
Table Recognition
Information Structuring
Retrieval-Augmented Generation (RAG)
Beyond public benchmarks, we conducted internal evaluations across six core real-world scenarios. Results show GLM-OCR delivers significant advantages across dimensions including code documentation, real-world tables, handwriting, multilingual text, seal recognition, and invoice extraction.
Pricing is uniform for both API input and output, costing just Β₯0.2 per million tokens. Processing one image costs approximately Β₯0.05, while a 100-page PDF requires only Β₯0.06βroughly one-tenth the cost of traditional OCR solutions.
