--- title: OpenDocRouter is a platform for document-to-Markdown... description: LlamaIndex launched OpenDocRouter, a unified API for document-to-markdown parsing that routes across multiple OCR and vision-language models, both frontier... canonical: https://daily.dev/posts/opendocrouter-is-a-platform-for-document-to-markdown-parsing-using-the-latest-open-source-and-fronti-bk1qsqxk5 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenDocRouter is a platform for document-to-Markdown parsing using the latest open-source and frontier models. Each model runs a versioned recipe consisting of prompts, processing, and settings. The API accepts PDFs, PNG, JPEG, or URLs to those file | daily.dev og:description: LlamaIndex launched OpenDocRouter, a unified API for document-to-markdown parsing that routes across multiple OCR and vision-language models, both frontier... og:url: https://daily.dev/posts/opendocrouter-is-a-platform-for-document-to-markdown-parsing-using-the-latest-open-source-and-fronti-bk1qsqxk5 og:image: https://api.daily.dev/og/posts/bK1QsqxK5.png og:image:alt: OpenDocRouter is a platform for document-to-Markdown parsing using the latest open-source and frontier models. Each model runs a versioned recipe consisting of prompts, processing, and settings. The API accepts PDFs, PNG, JPEG, or URLs to those file og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenDocRouter is a platform for document-to-Markdown parsing using the latest open-source and frontier models. Each model runs a versioned recipe consisting of prompts, processing, and settings. The API accepts PDFs, PNG, JPEG, or URLs to those file **[Andrew M](https://daily.dev/sources/dup6ye036hupdshygexyu)** · [@andrewma](https://daily.dev/andrewma) · 15 upvotes · 2 comments ## Summary LlamaIndex launched OpenDocRouter, a unified API for document-to-markdown parsing that routes across multiple OCR and vision-language models, both frontier (Claude Opus 5.5, Gemini 3 Flash/3.8 Flash, GPT-5.6 Terra, GPT-6 Luna) and open-source (Infinity-Parser2-Flash, MinerU2.5-Pro, TeleOCR, dots.mocr, PaddleOCR-VL-1.6). Every model is benchmarked on ParseBench for quality and cost, and a built-in grounding engine normalizes bounding boxes and layout classes across models that don't natively support them. Pricing is token-based with per-model rates, new accounts get $5 in credits, and layout extraction adds a small per-token surcharge. The platform is positioned as a lightweight routing layer distinct from LlamaParse, the company's managed, enterprise-focused parsing product. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Community discussion Top comments from developers on daily.dev. **@pdfopsdev** · 1 upvotes > versioning the recipe (prompt + settings) per model instead of just swapping the model is the right call. a silent model update changing output format has broken more than one of my parsing pipelines before I started pinning that. **@ahmetozel** · 1 upvotes > Versioned parsing recipes make model comparisons easier to interpret. The note that failed pages are not charged raises another useful contract: a document-level result should expose page coverage independently of billing or overall job completion. > > > I would test a three-page document with a forced failure on the middle page. The returned fragments should retain their original page numbers and an explicit gap, rather than presenting pages one and three as contiguous complete markdown. Downstream extraction needs to know that a missing section was never parsed. Stable page identifiers also let... ## Similar posts on daily.dev - [OpenRouter: Discover and use the latest LLMs](https://daily.dev/posts/openrouter-discover-and-use-the-latest-llms-scdb1pvuw) · Product Hunt · 3 upvotes · 0 comments - [OpenRouter: One API Key to Rule Them All](https://daily.dev/posts/openrouter-one-api-key-to-rule-them-all-ektckqyxv) · Playful Programming · 0 upvotes · 0 comments --- Tags: [#llama](https://daily.dev/tags/llama), [#llm](https://daily.dev/tags/llm), [#machine-learning](https://daily.dev/tags/machine-learning), [#rag](https://daily.dev/tags/rag) [View this post on daily.dev](https://daily.dev/posts/opendocrouter-is-a-platform-for-document-to-markdown-parsing-using-the-latest-open-source-and-fronti-bk1qsqxk5) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/opendocrouter-is-a-platform-for-document-to-markdown-parsing-using-the-latest-open-source-and-fronti-bk1qsqxk5","headline":"OpenDocRouter is a platform for document-to-Markdown parsing using the latest open-source and frontier models. Each model runs a versioned recipe consisting of prompts, processing, and settings. The API accepts PDFs, PNG, JPEG, or URLs to those file","text":"Shared: Introducing OpenDocRouter: every document model under one API","url":"https://daily.dev/posts/opendocrouter-is-a-platform-for-document-to-markdown-parsing-using-the-latest-open-source-and-fronti-bk1qsqxk5","datePublished":"2026-10-09T00:08:14.883Z","dateModified":"2026-10-15T02:14:36.543Z","author":{"@type":"Person","name":"Andrew M","url":"https://daily.dev/andrewma","image":"https://avatars.githubusercontent.com/u/102819214?v=4","description":"full time overthinker\n","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":3760}},"image":"https://media.daily.dev/image/upload/s--HRgLpUt6--/f_auto/v1722860399/public/Placeholder%2003","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":15},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/H1Ds3eh8c"},"comment":[{"@type":"Comment","text":"versioning the recipe (prompt + settings) per model instead of just swapping the model is the right call. a silent model update changing output format has broken more than one of my parsing pipelines before I started pinning that.","datePublished":"2026-10-10T18:10:51.465Z","url":"https://daily.dev/posts/bK1QsqxK5#c-yU08lL4iN","author":{"@type":"Person","name":"PDFops","url":"https://daily.dev/pdfopsdev","image":"https://media.daily.dev/image/upload/s---8isRBKc--/f_auto/v1782922291/avatars/avatar_orjMeK8QKaaVZwGq7ScPz?_a=BAMAMicg0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}},{"@type":"Comment","text":"Versioned parsing recipes make model comparisons easier to interpret. The note that failed pages are not charged raises another useful contract: a document-level result should expose page coverage independently of billing or overall job completion.\nI would test a three-page document with a forced failure on the middle page. The returned fragments should retain their original page numbers and an explicit gap, rather than presenting pages one and three as contiguous complete markdown. Downstream extraction needs to know that a missing section was never parsed. Stable page identifiers also let a later successful retry replace the gap without changing existing citations.","datePublished":"2026-10-09T06:56:25.489Z","url":"https://daily.dev/posts/bK1QsqxK5#c-Y9FknCU60","author":{"@type":"Person","name":"Ahmet Özel","url":"https://daily.dev/ahmetozel","image":"https://avatars.githubusercontent.com/u/70992231?v=4"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1}}],"isPartOf":{"@type":"WebPage","url":"https://daily.dev/sources/dup6ye036hupdshygexyu","name":"Andrew M"}} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Andrew M","item":"https://daily.dev/sources/dup6ye036hupdshygexyu"},{"@type":"ListItem","position":3,"name":"OpenDocRouter is a platform for document-to-Markdown parsing using the latest open-source and frontier models. Each model runs a versioned recipe consisting of prompts, processing, and settings. The API accepts PDFs, PNG, JPEG, or URLs to those file"}]} ```