{"slug": "run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api", "title": "Run GLM-OCR, DeepSeek-OCR-2, Dots.mocr with an OpenAI Compatible API", "summary": "Dots.mocr, a multimodal AI gateway, now offers an OpenAI-compatible API for running open-weight vision models including GLM-OCR, DeepSeek-OCR-2, and Dots.mocr, with pricing starting at $0.01 per 1M input tokens for Florence-2 and PP-OCRv6. The service supports OCR, detection, segmentation, pose, and captioning across 14 models, with a claimed 99-100% cost savings versus frontier models and a 99.9% uptime SLA.", "body_md": "### Multimodal, Multitask\n\nOne catalog spanning multi-modal inputs and multi-task outputs: OCR, detection, segmentation, pose, keypoints, and more.\n\nDocument OCR, captioning, and multi-modal chat: every visual capability behind one MCP server.\n\n| Model | Capabilities | Context | Input / 1M | Output / 1M |\n|---|---|---|---|---|\ndots.mocr\n| markdown | 32K | $0.15 | $0.30 |\nFlorence-2\n| ocrdetectioncaption | — | $0.01 | $0.01 |\nPP-OCRv6\n| ocr | — | $0.01 | $0.20 |\nDeepSeek-OCR-2\n| markdownocr | 32K | $0.06 | $0.12 |\nGLM-OCR\n| markdown | 8K | $0.10 | $0.20 |\nPaddleOCR-VL\n| markdownocr | 16K | $0.05 | $0.10 |\nQwen3.5 0.8B\n| chatcaptiondetection | 262K | $0.08 | $0.15 |\nLightOnOCR Coming soon\n| markdown | - | — | — |\nUnlimited-OCR Coming soon\n| markdownocr | — | — | — |\nQwen3.8 27B Coming soon\n| chatcaptiondetection | — | — | — |\nGemma 4 26B-A4B Coming soon\n| chatcaptiondetection | — | — | — |\nSAM 3 Coming soon\n| segmentation | — | — | — |\nRF-DETR Large Coming soon\n| detection | — | — | — |\nViTPose+ Coming soon\n| pose | — | — | — |\n\n14 of 14 models\n\nPricing calculator\n\nPick a document type, page volume, and OCR model. See cost savings versus closed vision APIs.\n\nPage volume / month\n\nGateway OCR tokens (in / out)\n\n120M - 250M / 100M\n\nFrontier billed tokens (in / out)\n\n250M / 200M\n\n2.5K image tokens per page; output includes reasoning at 2× OCR text.\n\nTotal cost savingsfrom frontier models\n\n$7.2K - $7.2K\n\nYou savefrom frontier models\n\n99 - 100%/mo\n\nDocuments / month\n\n100Kpages\n\nEstimates vs typical OCR, Document AI, and frontier VLM pricing.[Source: llm-prices.com](https://www.llm-prices.com/current-v1.json)\n\nLLM routers and gateways route to 100s of LLMs, yet only a handful of VLMs, and often no OCR or classical CV models. Visual AI deserves its own stack.\n\nOne catalog spanning multi-modal inputs and multi-task outputs: OCR, detection, segmentation, pose, keypoints, and more.\n\nOCR, captioning, and multimodal chat run through the same OpenAI-compatible chat completions API you already use.\n\nSend a 500-page PDF or a 2-hour video in a single call. The gateway chunks, batches, and reassembles for you. No pipelines to build.\n\nJSON-schema enforcement on every call. CV wrappers emit fixed schemas; VLMs honor response_format.\n\nEvery model is open-weight, served through the OpenAI-compatible API you already use. Swap models or providers freely, your client code never changes.\n\nGive any MCP client instant access to the full visual model catalog. Agents see, read, and reason over images out of the box.\n\nOptimized for production workloads and cost-efficiency. Every model deployed gets its own performance tune-up.\n\nModels Supported\n\n7\n\np50 Latency\n\n<100ms\n\nUptime SLA\n\n99.9%\n\nType II · HIPAA · BAA\n\nSOC 2\n\nPoint the OpenAI SDK at the gateway and swap the model. Same signature, exhaustive visual model catalog.\n\nUse cases\n\nCompose vision models like building blocks. One SDK. One key. One bill.\n\nLayout, OCR, and markdown extraction across contracts, statements, and forms, at sub-cent per-page economics.\n\nBuild powerful multi-modal chatbots and agents with VLMs that pack native support for multi-modal inputs such as images, PDFs, or videos in a single chat completion.\n\nAuto-caption, tag, and index large image and video libraries for search, dedup, and recommendations.\n\nDetection and segmentation behind one URL. Ship visual features without standing up CV infra.", "url": "https://wpnews.pro/news/run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api", "canonical_source": "https://www.vlm.run/product/gateway", "published_at": "2026-08-19 18:49:17+00:00", "updated_at": "2026-08-19 18:59:20.154504+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "computer-vision", "ai-products", "ai-infrastructure"], "entities": ["Dots.mocr", "GLM-OCR", "DeepSeek-OCR-2", "Florence-2", "PP-OCRv6", "PaddleOCR-VL", "Qwen3.5 0.8B", "OpenAI"], "alternates": {"html": "https://wpnews.pro/news/run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api", "markdown": "https://wpnews.pro/news/run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api.md", "text": "https://wpnews.pro/news/run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api.txt", "jsonld": "https://wpnews.pro/news/run-glm-ocr-deepseek-ocr-2-dots-mocr-with-an-openai-compatible-api.jsonld"}}