The request names lucataco/glm-ocr, a compact 0.9B multimodal OCR model from Z.ai that is indexed as an action on Replicate 1. It is available through Replicate's cloud API 1, with other OCR-capable options such as Hugging Face's document question answering models 4 and NVIDIA's VLM-based optical character recognition 2 as alternatives.
- 1
Replicatereplicate.comverified and signed
Hosts lucataco/glm-ocr, a compact 0.9B multimodal OCR model from Z.ai, callable through Replicate's cloud API 1.
+14 community tools built for it
for agents: lucataco/glm-ocr · cuuupid/glm-4v-9b · lucataco/olmocr-7b
- 2
Hugging Facehuggingface.coverified and signed
Offers document question answering from document images using Hugging Face models, a comparable OCR-style option 4.
official:MCP server · @huggingface/mcp-clientSDK · huggingface-hubCLI · text-embeddings-inferencerepository · pwc-cliskill · hf-cli+23 community tools built for it
for agents: document_question_answering · huggingface-vision-trainer · huggingface-local-models
- 3
NVIDIAnvidia.comverified and signed
Provides a VLM-based optical character recognition task for extracting text from images 2.
official:MCP server · NVIDIA CUDA Docs+84 community tools built for it
for agents: vlm-based-optical-character-recognition · tao-train-ocrnet · natural-language-processing
Sources
- 1Replicate - Run AI with an APIreplicate.com · read 2026-10-29
- 2Brev.dev Consolebrev.nvidia.com · read 2026-10-29
- 4Hugging Face – The AI community building the future.huggingface.co · read 2026-10-29
For agents: the 10 actions behind this answer
lucataco/glm-ocr · lucataco/glm-ocr verified and signed
Compact 0.9B multimodal OCR model from Z.ai. State-of-the-art on OmniDocBench V1.5 (94.62, #1 overall). Four modes: text recognition, formula (LaTeX), table parsing, and JSON-schema information extraction. Fits on a single T4.
vlm-based-optical-character-recognition · nemoretriever-parse verified and signed
Task: VLM-based Optical Character Recognition
nano-banana-pro-openrouter · nano-banana-pro-openrouter verified and signed
Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.
document_question_answering · Hugging Face (Activepieces) verified and signed
Document Question Answering — Answer questions from document images using Hugging Face models
python · fastcore verified and signed
workers-ai-search-model · Cloudflare API verified and signed
Model Search
pdf-ocr-extraction · pdf-ocr-extraction verified and signed
Extract text from scanned PDFs using optical character recognition
Looker · looker-sdk verified and signed
ML · sagemaker verified and signed
retrieveModel · OpenAI API verified and signed
Retrieves a model instance, providing basic information about the model such as the owner and permissioning.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.