GLM-OCR

Description

GLM-OCR is Z.ai's lightweight (about 0.9B) open-weight multimodal OCR model for complex document understanding: text, formula and table recognition, plus information extraction into a JSON template given in the prompt. Built on the GLM-V encoder-decoder architecture with a CogViT visual encoder and a GLM-0.5B decoder.

Providers

Nebul

View provider details and policies.

Quantization: BF16

Capabilities

EU-Compliant API Access

Use GLM-OCR with a simple API call. OpenAI-compatible endpoint, EU data residency guaranteed.

curl https://api.eurouter.pro/api/v1/chat/completions \
  -H "Authorization: Bearer $EUROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zhipu/glm-ocr",
    "messages": [{"role": "user", "content": "Hello"}]
  }'