Reading documents models, tools and agents
101 in the catalogue today. Every one with what it costs, who sells it and where it stands. 101 in all, a hundred to a page; this is page 1 of 2.
Models that read documents — scans, photographs of pages, forms, tables — and return text or structure. The interesting difference between them is not whether they can read a clean page, which they all can, but what they do with a table, a stamp, a handwritten margin or a column that breaks across pages. Several are priced per page rather than per token, which makes them easy to budget and hard to compare with the rest.
- Bank Checks OCR APIVeryfi$0.25per call, starter lane1 selling
- Bank Statements OCR APIVeryfi$0.25per call, starter lane1 selling
- DeepSeek-OCRDeepSeek$0.03→$0.1per Mtok in / out3 selling
- DeepSeek-OCR 2DeepSeek$0.22→$0.22per Mtok in / out2 selling
- Document AIMistral AI$0.005per page1 selling
- Document OCRUpstage$0.0015per page1 selling
- ERNIE-4.5-Turbo-128KBaidu$0.12→$0.47per Mtok in / out1 selling
- File parsing (OCR)Writer$0.055per page1 selling
- FireRed-OCRFireRed Team
- GLM-OCRZ.ai
- GOT-OCR-2.0-hfstepfun-ai
- GOT-OCR2_0StepFun
- Hunyuan-t1-visionTencent Hunyuan$0.45→$1.34per Mtok in / out1 selling
- HunyuanOCRTencent Hunyuan
- Hy Vision 1.5 InstructTencent Hunyuan$0.45→$1.34per Mtok in / out1 selling
- Infinity-Parser2-Flashinftech.ai$0.32→$1.6per Mtok in / out1 selling
- Infinity-Parser2-Proinftech.ai
- Interfaze Betainterfaze$1.5→$3.5per Mtok in / out1 selling
- InternVL-UInternVL-U
- Invoices OCR APIVeryfi$0.16per call, starter lane1 selling
- Isaac 0.1Perceptron$0.15→$1.25per Mtok in / out1 selling
- Isaac 0.2 1BPerceptron$0.15→$1.25per Mtok in / out1 selling
- Isaac 0.2 2B PreviewPerceptron$0.15→$1.25per Mtok in / out1 selling
- LLaVA-OneVision-1.5-8B-InstructLMMs-Lab
- LightOnOCR-1B-1025LightOn AI
- LightOnOCR-2-1BLightOn AI$0.3→$1.2per Mtok in / out1 selling
- LightOnOCR-3-0.8BLightOn AI
- LightOnOCR-3-4BLightOn AI$0.4→$0.8per Mtok in / out1 selling
- Llama 3.2 Instruct (90B)Meta$0.72→$0.72per Mtok in / out1 selling
- LlamaParseLlamaIndex$0.056per page, agentic-plus lane1 selling
- MiniCPM-OCR-1.0OpenBMB
- MiniCPM-OCR-JevOpenBMB
- MiniCPM-V 4.5OpenBMB$0.66→$1.11per Mtok in / out1 selling
- Mistral Medium 2505Mistral AI38th of 108· 9 boards$3→$10per Mtok in / out4 selling
- Mistral OCR (25.05)Mistral AI
- MonkeyOCRecho840
- NVIDIA Nemotron 3.5 Super VLNVIDIA110th of 169· 6 boards$0.15→$0.5per Mtok in / out8 selling
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA
- NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4NVIDIA$0.2→$0.5per Mtok in / out, baseten lane1 selling
- Nanonets-OCR-sNanonets
- Nanonets-OCR2-1.5B-expNanonets
- Nanonets-OCR2-3BNanonets
- Nomic ParseNomic AI$0.012per page1 selling
- NuExtract3NuMind
- NuMarkdown-8B-ThinkingNuMind
- OCRHive$0.0015per image1 selling
- OCR 4.1Mistral AI$0.004per page1 selling
- OCR APIMindee$0.05per page1 selling
- OCR ModerationHive$0.002per image1 selling
- OCR-Donut-CORDjinhybr
- OCRFlux-3BChatDOC
- OvisOCR2ATH-MaaS$0.3→$1.2per Mtok in / out1 selling
- OvisOCR3ATH-MaaS
- PaddleOCR-VLpaddlepaddle$0.02→$0.02per Mtok in / out1 selling
- PaddleOCR-VL-0.9Bpaddlepaddle$0.14→$0.8per Mtok in / out1 selling
- PaddleOCR-VL-1.5paddlepaddle
- PaddleOCR-VL-1.6paddlepaddle
- PaddleOCR-VL-For-Mangajzhang533
- ParseReducto$0.01–$0.02per page1 selling
- Qianfan-OCRBaidu$0.067→$0.27per Mtok in / out1 selling
- Qianfan-VL-8BBaidu
- Qwen-VL OCRAlibaba$0.72→$0.72per Mtok in / out1 selling
- Qwen2-VL-OCR-2B-InstructprithivMLmods
- Qwen3 235B A22B ThinkingAlibaba
- Qwen3 VL 235B A22B InstructAlibaba$0.2→$0.88per Mtok in / out7 selling
- Qwen3.6 PlusAlibaba64th of 326· 28 boards$0.33→$1.95per Mtok in / out7 selling
- Receipts & Invoices OCR APIVeryfi$0.08per call, starter lane1 selling
- RolmOCRReducto$0.2→$0.2per Mtok in / out1 selling
- TB-OCR-preview-0.1yifeihu
- TeleOCRStarDoc-AI
- Unlimited-OCRBaidu
- Unlimited-OCR-2Baidu
- W-2 & W-9 OCR APIVeryfi$0.16per call, starter lane1 selling
- Xiaomi-OCR-0SeerRay-Lab
- chandraDatalab
- chandra-ocr-2Datalab
- dots.mocrdots studio
- dots.ocrdots studio
- falcon-OCRTechnology Innovation Institute
- granite-vision-3.1-2b-previewIBM Granite
- granite-vision-3.2-2bIBM Granite$0.1→$0.1per Mtok in / out1 selling
- indra-ocrDatalab
- jina-ocr-v1Jina AI
- llava-v1.6-34b-hfLlava Hugging Face
- llava-v1.6-mistral-7b-hfLlava Hugging Face
- manga-ocr-basekha-white
- nemotron-ocr-v2NVIDIA
- olmOCR-2Allen Institute for AI (Ai2)$0.14→$0.8per Mtok in / out1 selling
- olmOCR-2-7B-1025Allen Institute for AI (Ai2)$0.09→$0.19per Mtok in / out1 selling
- olmOCR-7B-0225-previewAi2
- olmOCR-7B-0725Ai2$0.4→$0.8per Mtok in / out1 selling
- olmOCR-7B-0725-FP8Allen Institute for AI (Ai2)$0.27→$1.5per Mtok in / out1 selling
- olmOCR-7B-0825Allen Institute for AI (Ai2)$0.14→$0.8per Mtok in / out1 selling
- olmOCR-7B-1025Allen Institute for AI (Ai2)$0.14→$0.8per Mtok in / out1 selling
- surya-ocr-2Datalab$0.3→$1.2per Mtok in / out1 selling
- trocr-base-handwrittenMicrosoft
- trocr-base-printedMicrosoft
- trocr-large-handwrittenMicrosoft
- trocr-large-printedMicrosoft
- typhoon-ocr-7btyphoon-ai