{ "data": { "similar": [ { "grade": "B", "json": "https://www.anchorterminal.com/tools/extend.json", "name": "Extend API + MCP", "score": 62.9, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "extend" }, { "grade": "B", "json": "https://www.anchorterminal.com/tools/reducto.json", "name": "Reducto API + MCP", "score": 62.9, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "reducto" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/llamaparse.json", "name": "LlamaParse API + MCP", "score": 59.2, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "llamaparse" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/mistral-ocr.json", "name": "Mistral OCR API", "score": 58.8, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "mistral-ocr" }, { "grade": "C", "json": "https://www.anchorterminal.com/tools/adobe-pdf-extract.json", "name": "Adobe PDF Services / PDF Extract API", "score": 55.9, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "adobe-pdf-extract" }, { "grade": "D", "json": "https://www.anchorterminal.com/tools/unstructured.json", "name": "Unstructured API + MCP", "score": 46.9, "shared": [ "docs.parse", "docs.ocr", "docs.tables" ], "slug": "unstructured" } ], "tool": { "slug": "opendocrouter", "name": "OpenDocRouter", "vendor": "LlamaIndex", "vendorUrl": "https://opendocrouter.ai", "kind": "http-api", "category": "document-extraction", "summary": "OpenDocRouter is a hosted API from LlamaIndex that sends PDFs and images to a document parsing model the caller picks and returns markdown for each page. It launched on 7 October 2026 and bills prepaid credit by tokens used.", "url": "https://www.anchorterminal.com/tools/opendocrouter", "markdownUrl": "https://www.anchorterminal.com/tools/opendocrouter.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/opendocrouter.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/opendocrouter.json", "repo": "https://github.com/run-llama/opendocrouter-py", "license": "Proprietary service under the LlamaIndex Terms of Service with an OpenDocRouter addendum. The Python and TypeScript SDKs are MIT", "transports": [ "http" ], "remoteUrl": "https://www.opendocrouter.ai/v1", "packages": [ { "registry": "pypi", "name": "opendocrouter" }, { "registry": "npm", "name": "@llamaindex/opendocrouter" } ], "auth": "api-key", "authNotes": "Bearer API key created in the dashboard after a browser sign-in, sent as `Authorization: Bearer \u003ckey\u003e` and read by the SDKs from OPEN_DOC_ROUTER_API_KEY. The terms say keys can be revoked. No scopes, expiry or read-only keys were found in the reviewed documentation. `GET /v1/models` answers without a key. This is a separate key from a LlamaCloud key.", "pricing": "usage", "pricingNotes": "Prepaid credit with no subscription. New accounts get $5 of promotional credit, and top-ups start at $10 with a 5% fee on each purchase. Each successful page is charged for its tokens at the chosen model's price, and layout adds $0.20 per 1M tokens. Failed, cached and blank pages are free. Whether sign-up needs a card wasn't established, because the dashboard needs a sign-in. LlamaIndex's launch post of 7 October 2026 gives a $25 minimum top-up, where the site, docs and terms say $10 (checked 2026-10-08).", "priceSummary": "$48.82 / 1k pages", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI document or the home page, and /.well-known/x402 returns 404. The 402 response is `insufficient_credits` for prepaid credit (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": 127, "asOf": "2026-10-08" }, "docsUrl": "https://opendocrouter.ai/docs", "openapi": "https://www.opendocrouter.ai/v1/openapi.json", "capabilities": [ "docs.parse", "docs.ocr", "docs.tables" ], "tags": [ "hosted", "usage", "prepaid", "router", "openapi", "python", "typescript", "async-jobs", "closed-source", "new" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 56.6, "grade": "C", "agentReady": false, "rank": 434, "ranked": true, "rankOf": 629, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 84, "maintenance": 65, "payments": 30, "reliability": 43, "schema": 85, "security": 40, "transparency": 47 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 43, "points": 8.6, "reason": "Read with the hosted lines. No status page was found. The site links none, /status returns 404 and llamaindex.statuspage.io lists seven LlamaParse components and none for OpenDocRouter (0). No readable incident history, and the service was announced on 7 October 2026, one day before this check (5). Limits are published with numbers, 300 parse calls and 60 polls a minute and 10 requests running at once per account (15). 429 and 503 carry Retry-After per the docs, each page error is marked as worth retrying or not, and `cache: true` makes a repeated request free. There is no idempotency key, and without the cache a resend is charged again (13 of 15). No SLA found, and the terms allow changes with or without notice (0). The API is version 1 with 1.0.0 SDKs and no beta or preview label (10)." }, { "key": "performance", "name": "Performance", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes." }, { "key": "schema", "name": "Schema \u0026 documentation", "weight": 13, "effectiveWeight": 16.25, "score": 85, "points": 13.81, "reason": "Public OpenAPI 3.1 document at /v1/openapi.json covering all six operations (25). No llms.txt (404), but the docs page is served as Markdown at /docs.md (10). The parse, get, delete and upload operations say when to use sync or async, when the cache is needed and what is charged. The credits and models operations have no description (16 of 20). `mode` and `mime_type` are enums, `expand` has a pattern and required fields are marked, while `pages` is a free string and `model` isn't enumerated (12 of 15). Examples in curl, Python and TypeScript, a table of 15 request errors and a table of 12 page errors (14 of 15). Models carry dated recipe versions and responses a `price_version`, and the SDKs have changelogs on GitHub, but there is no changelog for the service (8 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 84, "points": 13.65, "reason": "API reading. `pages` selects pages, markdown and layout are opt-in on GET through `expand`, and a poll returns no document text without it (22 of 25). Results over 4 MB come in parts with `next_cursor`, and `pages` and `expand` size the output. There is no endpoint to list past requests (16 of 20). Errors have stable codes, 402 includes `required_usd` and `available_usd`, 429 and 503 include Retry-After and every response has X-Request-Id (19 of 20). No idempotency key. `cache: true` returns stored pages free on a repeat and failed pages can be resent alone, but a sync request without the cache is charged again if resent (12 of 20). Two required fields, and official SDKs in Python and TypeScript (15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 40, "points": 7, "reason": "Bearer API keys created in the dashboard, and the terms say a key can be revoked. No scopes, expiry or rotation were found, and the dashboard needs a sign-in we didn't have (20 of 30). No read-only or restricted key found. One key can spend credit and read cached results, with spending bounded by the prepaid balance (6 of 20). The API returns untrusted document text and no prompt-injection guidance was found. Document URLs must be public HTTPS on the default port (0 of 15). GET /v1/parse/{id} shows what each request did and cost, and the docs mention a usage log keyed by X-Request-Id. No audit log found (8 of 15). SECURITY.md in the SDK repositories asks for private reports to security@runllama.ai. No security.txt on opendocrouter.ai or llamaindex.ai, and LlamaIndex's trust centre renders only with JavaScript, so no certification is confirmed for this service (6 of 20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 30, "points": 3.75, "reason": "No x402, MPP or L402 (0). Token prices for every model, an average and a maximum charge per page, the layout price and the 5% top-up fee are public on the models page, the docs and `GET /v1/models` (20). New accounts get $5 of promotional credit. Whether a card is needed at sign-up isn't stated and the dashboard needs a sign-in (10 of 20, our call until that's confirmed). A person signs in through a browser to create a key (0)." }, { "key": "tasks", "name": "Task success", "weight": 10, "effectiveWeight": 0, "pending": true, "points": 0, "reason": "Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored." }, { "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7, "effectiveWeight": 8.75, "score": 65, "points": 5.69, "reason": "Both SDKs published 1.0.0 on 7 October 2026, the day of the announcement, and the newest model recipe is dated the same day (30). There is one SDK release and no service changelog. The model list shows eight distinct recipe dates between 25 September and 7 October 2026 and a price version of 6 October, which we count as half (10 of 20). No public changelog or community channel found, support is by email, and GitHub issues weren't readable (3 of 15). Current official SDKs in Python and TypeScript (15). The SDK repositories have CI workflows for lint, build and test, release-please and lock files. Run results weren't readable (7 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 47, "points": 4.11, "note": "editorial 45, provenance 49", "reason": "Closed service under the LlamaIndex terms with an OpenDocRouter addendum, SDKs MIT (15). The docs, the OpenAPI document and the addendum agree that nothing is stored without `cache: true`, cached results are encrypted and kept 24 hours, uploads are deleted once read or after an hour, and request records are kept for billing. The terms say LlamaIndex trains no models on user content. No DPA or retention period for request records was found, and the privacy notice dates from March 2024 and doesn't mention the service (22 of 30). No deprecation policy. Recipe and price versions are dated, and the terms allow changes and price changes without notice (3 of 20). The addendum names Anthropic, Google and OpenAI as examples of model providers that receive pages, leaves its infrastructure providers unnamed and gives no data location beyond processing in the United States (5 of 20)." } ], "assessment": { "date": "2026-10-08", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "API reading. `pages` selects pages, markdown and layout are opt-in on GET through `expand`, and a poll returns no document text without it (22 of 25). Results over 4 MB come in parts with `next_cursor`, and `pages` and `expand` size the output. There is no endpoint to list past requests (16 of 20). Errors have stable codes, 402 includes `required_usd` and `available_usd`, 429 and 503 include Retry-After and every response has X-Request-Id (19 of 20). No idempotency key. `cache: true` returns stored pages free on a repeat and failed pages can be resent alone, but a sync request without the cache is charged again if resent (12 of 20). Two required fields, and official SDKs in Python and TypeScript (15).", "maintenance": "Both SDKs published 1.0.0 on 7 October 2026, the day of the announcement, and the newest model recipe is dated the same day (30). There is one SDK release and no service changelog. The model list shows eight distinct recipe dates between 25 September and 7 October 2026 and a price version of 6 October, which we count as half (10 of 20). No public changelog or community channel found, support is by email, and GitHub issues weren't readable (3 of 15). Current official SDKs in Python and TypeScript (15). The SDK repositories have CI workflows for lint, build and test, release-please and lock files. Run results weren't readable (7 of 10).", "payments": "No x402, MPP or L402 (0). Token prices for every model, an average and a maximum charge per page, the layout price and the 5% top-up fee are public on the models page, the docs and `GET /v1/models` (20). New accounts get $5 of promotional credit. Whether a card is needed at sign-up isn't stated and the dashboard needs a sign-in (10 of 20, our call until that's confirmed). A person signs in through a browser to create a key (0).", "reliability": "Read with the hosted lines. No status page was found. The site links none, /status returns 404 and llamaindex.statuspage.io lists seven LlamaParse components and none for OpenDocRouter (0). No readable incident history, and the service was announced on 7 October 2026, one day before this check (5). Limits are published with numbers, 300 parse calls and 60 polls a minute and 10 requests running at once per account (15). 429 and 503 carry Retry-After per the docs, each page error is marked as worth retrying or not, and `cache: true` makes a repeated request free. There is no idempotency key, and without the cache a resend is charged again (13 of 15). No SLA found, and the terms allow changes with or without notice (0). The API is version 1 with 1.0.0 SDKs and no beta or preview label (10).", "schema": "Public OpenAPI 3.1 document at /v1/openapi.json covering all six operations (25). No llms.txt (404), but the docs page is served as Markdown at /docs.md (10). The parse, get, delete and upload operations say when to use sync or async, when the cache is needed and what is charged. The credits and models operations have no description (16 of 20). `mode` and `mime_type` are enums, `expand` has a pattern and required fields are marked, while `pages` is a free string and `model` isn't enumerated (12 of 15). Examples in curl, Python and TypeScript, a table of 15 request errors and a table of 12 page errors (14 of 15). Models carry dated recipe versions and responses a `price_version`, and the SDKs have changelogs on GitHub, but there is no changelog for the service (8 of 15).", "security": "Bearer API keys created in the dashboard, and the terms say a key can be revoked. No scopes, expiry or rotation were found, and the dashboard needs a sign-in we didn't have (20 of 30). No read-only or restricted key found. One key can spend credit and read cached results, with spending bounded by the prepaid balance (6 of 20). The API returns untrusted document text and no prompt-injection guidance was found. Document URLs must be public HTTPS on the default port (0 of 15). GET /v1/parse/{id} shows what each request did and cost, and the docs mention a usage log keyed by X-Request-Id. No audit log found (8 of 15). SECURITY.md in the SDK repositories asks for private reports to security@runllama.ai. No security.txt on opendocrouter.ai or llamaindex.ai, and LlamaIndex's trust centre renders only with JavaScript, so no certification is confirmed for this service (6 of 20).", "transparency": "Closed service under the LlamaIndex terms with an OpenDocRouter addendum, SDKs MIT (15). The docs, the OpenAPI document and the addendum agree that nothing is stored without `cache: true`, cached results are encrypted and kept 24 hours, uploads are deleted once read or after an hour, and request records are kept for billing. The terms say LlamaIndex trains no models on user content. No DPA or retention period for request records was found, and the privacy notice dates from March 2024 and doesn't mention the service (22 of 30). No deprecation policy. Recipe and price versions are dated, and the terms allow changes and price changes without notice (3 of 20). The addendum names Anthropic, Google and OpenAI as examples of model providers that receive pages, leaves its infrastructure providers unnamed and gives no data location beyond processing in the United States (5 of 20)." }, "sources": [ { "what": "home page", "url": "https://www.opendocrouter.ai/", "seen": "2026-10-08" }, { "what": "docs", "url": "https://www.opendocrouter.ai/docs", "seen": "2026-10-08" }, { "what": "docs as Markdown", "url": "https://www.opendocrouter.ai/docs.md", "seen": "2026-10-08" }, { "what": "OpenAPI document", "url": "https://www.opendocrouter.ai/v1/openapi.json", "seen": "2026-10-08" }, { "what": "model list and prices (API)", "url": "https://www.opendocrouter.ai/v1/models", "seen": "2026-10-08" }, { "what": "models and pricing page", "url": "https://www.opendocrouter.ai/models", "seen": "2026-10-08" }, { "what": "terms with OpenDocRouter addendum", "url": "https://www.opendocrouter.ai/terms", "seen": "2026-10-08" }, { "what": "privacy notice", "url": "https://www.opendocrouter.ai/privacy", "seen": "2026-10-08" }, { "what": "launch post", "url": "https://www.llamaindex.ai/blog/introducing-opendocrouter", "seen": "2026-10-08" }, { "what": "LlamaIndex status page and components", "url": "https://llamaindex.statuspage.io/", "seen": "2026-10-08" }, { "what": "Python SDK repository (README, CHANGELOG, SECURITY.md, CI)", "url": "https://github.com/run-llama/opendocrouter-py", "seen": "2026-10-08" }, { "what": "TypeScript SDK repository", "url": "https://github.com/run-llama/opendocrouter-ts", "seen": "2026-10-08" }, { "what": "PyPI", "url": "https://pypi.org/pypi/opendocrouter/json", "seen": "2026-10-08" }, { "what": "npm", "url": "https://registry.npmjs.org/@llamaindex/opendocrouter", "seen": "2026-10-08" }, { "what": "RDAP for opendocrouter.ai", "url": "https://rdap.identitydigital.services/rdap/domain/opendocrouter.ai", "seen": "2026-10-08" }, { "what": "official MCP registry search (no result)", "url": "https://registry.modelcontextprotocol.io/v0/servers?search=opendocrouter", "seen": "2026-10-08" }, { "what": "LlamaIndex trust centre (JavaScript only)", "url": "https://security.llamaindex.ai/", "seen": "2026-10-08" } ], "openQuestions": [ "unchecked: the dashboard, which needs a sign-in. Key options (scopes, expiry, several keys), whether sign-up needs a card and what the usage log shows", "unchecked: GitHub stars, open issues and CI run results for the SDK repositories. The GitHub API answered with a rate limit", "unchecked: certifications and the subprocessor list in LlamaIndex's JavaScript-only trust centre, and whether they cover OpenDocRouter", "The launch post of 7 October 2026 says top-ups start at $25. The site, docs and terms addendum say $10", "The site says frontier models are charged at their providers' token prices with no markup. We didn't compare the listed prices with each provider's own", "ParseBench scores and per-page averages are the vendor's figures, and the launch post calls ParseBench 'our benchmarks'. We didn't reproduce them", "npm reports no download count yet for @llamaindex/opendocrouter, and the PyPI figure of 127 covers one day", "No status page or changelog URL is recorded in provenance because none exists for the service. The SDK changelogs are on GitHub" ] }, "negative": 0, "verdict": "One endpoint reaches 11 parsing models, each with a dated recipe version, a published token price and a ParseBench score, and failed pages aren't charged. The service launched on 7 October 2026, so it has no status page, incident history, SLA or changelog yet, and no key scopes were found in the reviewed documentation.", "bestFor": "Agents that need page-level markdown from PDFs and images and want to choose or compare models on price and published benchmark scores with one key.", "strengths": [ "Public OpenAPI 3.1 document for all six operations, and the docs page is also served as Markdown at /docs.md", "`GET /v1/models` lists 11 models without a key, each with token prices, an average and a maximum charge per page, and ParseBench scores", "Failed, cached and blank pages are free, and every page comes back with its own status, token usage and charge", "Fifteen request error codes and twelve page error codes are documented, with Retry-After on 429 and 503 and a retry verdict for each page error", "Nothing from a document is stored unless `cache: true` is sent, and cached results are encrypted and deleted after 24 hours or on DELETE" ], "weaknesses": [ "Launched on 7 October 2026. The domain was registered on 23 September 2026 and both SDKs have one release, 1.0.0", "No status page, SLA or service changelog was found. LlamaIndex's status page lists only LlamaParse components", "No scoped, expiring or read-only keys in the reviewed documentation, and no idempotency key", "A request holds the model's maximum charge per page, $0.784 on Claude Opus 5.5, so the $5 starting credit admits six Opus pages a request", "Without `cache: true` a dropped connection loses the markdown, the request is still charged and a resend is a new request" ], "agentNotes": [ "Call `GET /v1/models` first, which needs no key, and choose a model by `avg_charge_per_page_usd` and its ParseBench scores. Send its `id` as `model`", "Send `cache: true` on any request you might repeat. Without it the markdown exists only in the POST response and a resend is charged as a new request", "Raise the SDK timeout above its 60-second default for sync parses. Pages can run for 270 seconds and the SDKs retry a timed-out request twice", "Check every page's `status` before using its markdown. A 200 can be `partial`, and failed pages can be resent alone with `pages`", "Treat 402 as final until credit is added. The hold is the model's maximum charge per page times the page count, and `GET /v1/credits` shows `available_usd`" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 56.6 } ], "editorialScores": { "ergonomics": 84, "maintenance": 65, "payments": 30, "reliability": 43, "schema": 85, "security": 40, "transparency": 45 }, "provenanceScore": 49 }, "connect": { "install": "pip install opendocrouter # or: npm install @llamaindex/opendocrouter", "http": "curl https://www.opendocrouter.ai/v1/parse \\\n -H \"Authorization: Bearer $OPEN_DOC_ROUTER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"google/gemini-3.8-flash-low\", \"document\": {\"url\": \"https://arxiv.org/pdf/1706.03762\"}}'" }, "letme": { "capability": "https://letme.dev/docs.parse", "tool": "https://letme.dev/opendocrouter" }, "notable": [ "`GET /v1/models` returned 11 models on 8 October 2026 (Claude Opus 5.5 and Haiku 5.5, Gemini 3 Flash and 3.8 Flash, GPT-5.6 Terra, GPT-6 Luna, Infinity-Parser2-Flash, MinerU2.5-Pro, TeleOCR, dots.mocr, PaddleOCR-VL-1.6), each with a recipe version dated between 25 September and 7 October 2026 (https://www.opendocrouter.ai/v1/models)", "Sync requests take up to 50 pages and async requests up to 500, from a public HTTPS URL, a one-time upload of up to 50 MB or inline base64 of about 3 MB. PDF, PNG and JPEG only (https://www.opendocrouter.ai/docs)", "With `layout: true` each page also returns elements in reading order with a type from 15 classes, the markdown lines each spans and its boxes on the page, for $0.20 per 1M tokens (https://www.opendocrouter.ai/docs)", "The terms addendum of 7 October 2026 says third-party models such as Anthropic, Google and OpenAI receive the pages sent to them under their own policies, and that models LlamaIndex hosts run on its infrastructure providers (https://www.opendocrouter.ai/terms)", "LlamaIndex announced the service on 7 October 2026 and describes LlamaParse as its managed platform with tuned tiers, extraction and indexing, which OpenDocRouter doesn't have (https://www.llamaindex.ai/blog/introducing-opendocrouter)", "The site links no status page, and llamaindex.statuspage.io lists seven LlamaParse components and none for OpenDocRouter (https://llamaindex.statuspage.io/)" ], "area": "web-data", "details": [ { "label": "Endpoints", "value": "POST /v1/parse, GET and DELETE /v1/parse/{id}, POST /v1/uploads, GET /v1/credits, GET /v1/models, all at https://www.opendocrouter.ai. OpenAPI 3.1, API version 1" }, { "label": "Models", "value": "11 on 8 October 2026. Six from Anthropic, Google and OpenAI and five from other publishers (Infinity-Parser2-Flash, MinerU2.5-Pro, TeleOCR, dots.mocr, PaddleOCR-VL-1.6). Each runs a versioned parsing recipe, and responses carry `model_version` and `price_version`" }, { "label": "File types and sizes", "value": "PDF, PNG and JPEG. URLs and uploads up to 50 MB or 500 pages, inline base64 about 3 MB, request body capped at 4 MB" }, { "label": "Sync and async", "value": "Sync returns every page in the response, up to 50 pages. Async needs `cache: true`, returns 202, takes up to 500 pages and is polled at GET /v1/parse/{id}. No webhooks in the reviewed documentation" }, { "label": "Output", "value": "Markdown for each page with status, token usage and charge. Optional layout with element types, markdown line spans, boxes and a confidence value. No field extraction, classification, chunking or index endpoints" }, { "label": "Rate limits", "value": "300 POST /v1/parse calls a minute, 60 GET /v1/parse/{id} calls a minute, 10 requests and 5 async requests running at once per account, 100 unused uploads" }, { "label": "Errors and retries", "value": "15 request error codes and 12 page error codes. 429 and 503 carry Retry-After. Each page is retried once by the service on timeouts, rate limits, provider errors and capacity. Pages still running after 270 seconds return `timeout`" }, { "label": "Data retention", "value": "No document or result is stored unless `cache: true` is sent. Cached results are encrypted and kept 24 hours or until DELETE. Uploads are deleted once read, or after an hour. Page counts, tokens, errors and charges are kept" }, { "label": "Billing", "value": "Prepaid credit that doesn't expire and isn't refundable. $5 promotional credit for new accounts, top-ups from $10 plus 5%. A request holds its maximum possible charge and releases the unused part when it ends" }, { "label": "SDKs", "value": "Python `opendocrouter` 1.0.0 (Python 3.9+) and TypeScript `@llamaindex/opendocrouter` 1.0.0, both MIT and published on 7 October 2026. Two retries with backoff and a 60-second timeout by default" }, { "label": "MCP server", "value": "None found in the docs or the official MCP registry" }, { "label": "Status page", "value": "None found. llamaindex.statuspage.io has no OpenDocRouter component" } ], "unitPrices": [ { "item": "Parse with Claude Opus 5.5", "unit": "1k-pages", "usd": 48.82, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.784 a page" }, { "item": "Parse with Gemini 3 Flash", "unit": "1k-pages", "usd": 19.67, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.199 a page" }, { "item": "Parse with GPT-5.6 Terra", "unit": "1k-pages", "usd": 19.89, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.436 a page" }, { "item": "Parse with Gemini 3.8 Flash", "unit": "1k-pages", "usd": 5.91, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.126 a page" }, { "item": "Parse with Infinity-Parser2-Flash", "unit": "1k-pages", "usd": 4.34, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.050 a page" }, { "item": "Parse with dots.mocr", "unit": "1k-pages", "usd": 3.97, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.030 a page" }, { "item": "Parse with TeleOCR", "unit": "1k-pages", "usd": 2.7, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.045 a page" }, { "item": "Parse with PaddleOCR-VL-1.6", "unit": "1k-pages", "usd": 2.11, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.044 a page" }, { "item": "Parse with Claude Haiku 5.5", "unit": "1k-pages", "usd": 1.22, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.020 a page" }, { "item": "Parse with MinerU2.5-Pro", "unit": "1k-pages", "usd": 0.86, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.007 a page" }, { "item": "Parse with GPT-6 Luna", "unit": "1k-pages", "usd": 0.8, "note": "vendor's average on ParseBench documents, charged by tokens, at most $0.019 a page" }, { "item": "Layout add-on", "unit": "1m-tokens", "usd": 0.2, "note": "added to each page whose layout comes back" }, { "item": "Top-up fee", "unit": "pct", "usd": 5, "note": "on each credit purchase, minimum purchase $10, non-refundable" } ], "provenance": { "legalEntity": "LlamaIndex, Inc.", "domain": "opendocrouter.ai", "domainRegistered": "2026-09-23", "endpointOnVendorDomain": true, "terms": "https://www.opendocrouter.ai/terms", "privacy": "https://www.opendocrouter.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms page carries an OpenDocRouter addendum last modified 2026-10-07 above the LlamaIndex Terms of Service of 2024-06-07, which name LlamaIndex, Inc. The SDK licence files read Copyright 2026 LlamaIndex, Inc.", "The privacy page is the LlamaIndex Privacy Notice last updated 2024-03-30. It covers LlamaIndex as a controller and doesn't mention OpenDocRouter.", "RDAP for opendocrouter.ai gives a registration date of 2026-09-23 with the registrant behind a privacy service. The link to LlamaIndex rests on the site footer, the terms and the announcement on llamaindex.ai.", "www.opendocrouter.ai/.well-known/security.txt and www.llamaindex.ai/.well-known/security.txt both return 404. SECURITY.md in the SDK repositories sends reports to security@runllama.ai.", "No status page or service changelog is linked from the site, and /status and /changelog return 404. The only changelogs are the SDKs' CHANGELOG.md files on GitHub." ], "score": 49, "checks": [ { "check": "Legal entity named", "value": "LlamaIndex, Inc.", "points": 20, "max": 20, "state": "ok" }, { "check": "Domain age", "value": "opendocrouter.ai, registered 2026-09-23 (under a year)", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "www.opendocrouter.ai", "points": 15, "max": 15, "state": "ok" }, { "check": "Terms of service", "value": "read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points", "points": 5.1, "max": 10, "state": "part" }, { "check": "Privacy policy", "value": "read, states 6 of the 8 things a reader expects", "points": 8.5, "max": 10, "state": "part" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ], "policies": [ { "kind": "terms", "url": "https://www.opendocrouter.ai/terms", "state": "read", "readAt": "2026-10-08", "statedDate": "2026-10-07", "words": 9711, "points": 5.1, "max": 10, "expected": [ { "key": "terms.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last modified 2026-10-07", "says": "Last updated 2026-10-07" }, { "key": "terms.law", "label": "Names the governing law or courts", "found": true, "quote": "These Terms will be governed by the internal substantive laws of the State of Delaware, without respect to its conflict of laws principles.", "says": "The law of the State of Delaware" }, { "key": "terms.liability", "label": "States a limit on its liability", "found": true, "quote": "TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT WILL ANY LLAMAINDEX INDEMNITEE BE LIABLE FOR ANY INDIRECT, PUNITIVE, INCIDENTAL, SPECIAL, CONSEQUENTIAL, OR EXEMPLARY DAMAGES, INCLUDING, WITHOUT LIMITATION, DAMAGES FOR LOSS OF PROFITS, GOODWILL, USE, OR DATA, OR OTHER INTANGIBLE LOSSES, ARISING OUT OF OR…", "says": "Rules out indirect and consequential losses, with no cap named in this sentence" }, { "key": "terms.termination", "label": "Says how the agreement or account can be ended", "found": true, "quote": "(vi) such individual’s right to access and use the Service may be suspended or terminated (and the administration of the applicable User Account may be transferred) if such individual ceases to be associated with, or ceases to use an email address associated with or provisioned by, that Organization;" }, { "key": "terms.changes", "label": "Says how changes to the terms are announced", "found": true, "quote": "We reserve the right to modify these Terms, and we will provide notice of material changes as described below.", "says": "Says it gives notice of a change" }, { "key": "terms.use", "label": "Lists what users may not do", "found": true, "quote": "If you do not agree, you may not use the Service." }, { "key": "terms.sla", "label": "Refers to a service level or uptime commitment", "found": false } ], "toKnow": [ { "key": "terms.benchmark", "label": "Restricts benchmarking or competitive use", "found": true, "quote": "(h) use or display the Service in competition with us, to develop competing products or services, for benchmarking or competitive analysis of the Service, or otherwise to our detriment or disadvantage;", "costsPoints": true }, { "key": "terms.nonotice", "label": "Says the terms or the service can change without notice", "found": true, "quote": "We may, with or without prior notice, change the Service, stop providing the Service or features of the Service to you or to Users generally, or create usage limits for the Service.", "costsPoints": true }, { "key": "terms.cutoff", "label": "Says access can be ended without notice or for any reason", "found": true, "quote": "We may, with or without prior notice, permanently terminate or temporarily suspend your access to your User Account and/or the Service without liability, with or without cause, and for any or no reason, including if, in our sole determination, you violate any provision of these Terms." }, { "key": "terms.arbitration", "label": "Requires arbitration or waives class actions", "found": true, "quote": "…YOU OPT OUT PURSUANT TO THE INSTRUCTIONS IN THE ARBITRATION AGREEMENT, THE EXCLUSIVE USE OF FINAL AND BINDING ARBITRATION ON AN INDIVIDUAL BASIS TO RESOLVE DISPUTES BETWEEN YOU AND US, INCLUDING ANY CLAIMS THAT AROSE OR WERE ASSERTED BEFORE YOU AGREED TO THESE TERMS." } ], "notes": [ { "date": "2026-10-08", "text": "Third-party models such as Anthropic, Google and OpenAI receive the pages sent to them, and their own usage policies apply to that content.", "quote": "Models from third parties, such as Anthropic, Google and OpenAI, receive the pages you send them, and their own usage policies apply to that content." }, { "date": "2026-10-08", "text": "Prepaid credit is non-refundable except where the law requires or at the vendor's discretion, and each purchase carries a non-refundable fee of 5% of the credit bought.", "quote": "Credit is non-refundable, except where Applicable Law requires or at our discretion." }, { "date": "2026-10-08", "text": "The licence granted over User Content is perpetual, irrevocable, transferable and sublicensable, for use as reasonably necessary to run the Service and as the Privacy Notice describes.", "quote": "to LlamaIndex a fully paid, royalty-free, transferable, perpetual, irrevocable, non-exclusive, and worldwide license, with the right to grant and authorize sublicenses" } ] }, { "kind": "privacy", "url": "https://www.opendocrouter.ai/privacy", "state": "read", "readAt": "2026-10-08", "statedDate": "2024-03-30", "words": 4774, "points": 8.5, "max": 10, "expected": [ { "key": "privacy.date", "label": "Gives the date it was last updated", "found": true, "quote": "Last updated 2024-03-30", "says": "Last updated 2024-03-30" }, { "key": "privacy.collected", "label": "Says what personal data is collected", "found": true, "quote": "The categories of personal data we collect depend on how you interact with us and our services." }, { "key": "privacy.retention", "label": "Says how long data is kept", "found": true, "quote": "We will usually retain the personal data we collect about you for no longer than reasonably necessary to fulfil the purposes for which it was collected, and in accordance with our legitimate business interests and applicable law." }, { "key": "privacy.processors", "label": "Says who else receives the data", "found": true, "quote": "A “processor,” which is sometimes referred to as a “service provider,” processes personal data on behalf of a controller subject to the controller’s instructions." }, { "key": "privacy.sale", "label": "Says whether personal data is sold or shared for advertising", "found": true, "quote": "This information is used to provide and inform targeted advertising, as well as to provide advertising-related services such as reporting, attribution, analytics, and market research." }, { "key": "privacy.rights", "label": "Says what rights people have over their data", "found": false }, { "key": "privacy.contact", "label": "Gives a privacy contact", "found": true, "quote": "If you have any questions or requests in connection with this Privacy Notice or other privacy-related matters, please send an email to privacy@runllama.ai.", "says": "privacy@runllama.ai" }, { "key": "privacy.transfers", "label": "Says where data is transferred or stored", "found": false } ], "toKnow": [ { "key": "privacy.sells", "label": "Says it sells personal data or shares it for advertising", "found": true, "quote": "We may share a common account identifier (such as a hashed email address or user ID) with our third-party advertising partners to help link the personal data we and our third-party partners collect to the same person, or otherwise target advertising to an individual on a third-party website or platform." } ], "notes": [ { "date": "2026-10-08", "text": "The notice covers LlamaIndex as controller only and does not cover personal data it processes on a customer's behalf as a processor.", "quote": "However, this Privacy Notice does not cover or address how our customers may process personal data when they use our services, or how we may process personal data on their behalf in accordance with their instructions where we are acting as their processor." }, { "date": "2026-10-08", "text": "Customer Content, including uploaded files and documents, is used to run the services, handle requests and improve the services.", "quote": "We use this content primarily to provide you with our services, to facilitate your requests, and to improve our services." } ] } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/opendocrouter.json", "live": { "slug": "opendocrouter", "probe": { "target": "https://www.opendocrouter.ai/v1", "method": "get", "lastAt": "2026-10-08T17:36:42.023349109Z", "lastOk": true, "lastStatus": 404, "lastMs": 146, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 148, "p95ms24h": 244, "samples24h": 25, "samples30d": 25, "days": [ { "date": "2026-10-08", "probes": 25, "ok": 25 } ] }, "versions": [ { "registry": "github", "name": "run-llama/opendocrouter-py", "version": "v1.0.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:24:05.510654236Z" }, { "registry": "npm", "name": "@llamaindex/opendocrouter", "version": "1.0.0", "seenAt": "2026-10-08T16:24:04.668181235Z" }, { "registry": "pypi", "name": "opendocrouter", "version": "1.0.0", "released": "2026-10-07", "seenAt": "2026-10-08T16:24:04.48026514Z" } ], "githubStars": 0, "pypiWeekly": 127, "securityTxt": { "url": "https://opendocrouter.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-08T15:38:43.225873715Z" }, "updatedAt": "2026-10-08T17:36:42.023349109Z" } }, "verify": { "accepts": "a page on opendocrouter.ai or one of its subdomains, or the README of github.com/run-llama/opendocrouter-py", "badgeUrl": "https://www.anchorterminal.com/badges/opendocrouter.svg", "body": { "slug": "opendocrouter", "url": "the page with the badge or the link" }, "docs": "https://www.anchorterminal.com/builders/#verify", "effect": "none, it never changes a grade, rank or review", "endpoint": "https://www.anchorterminal.com/api/v1/verify", "listingUrl": "https://www.anchorterminal.com/tools/opendocrouter", "mcpTool": "verify_listing", "recheck": "weekly; two failed checks in a row and it lapses, a later pass restores it", "snippets": { "html": "\u003ca href=\"https://www.anchorterminal.com/tools/opendocrouter\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/opendocrouter.svg\" alt=\"OpenDocRouter on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e", "markdown": "[![OpenDocRouter on Anchor Terminal](https://www.anchorterminal.com/badges/opendocrouter.svg)](https://www.anchorterminal.com/tools/opendocrouter)", "link": "\u003ca href=\"https://www.anchorterminal.com/tools/opendocrouter\"\u003eOpenDocRouter on Anchor Terminal\u003c/a\u003e" } } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/tools/opendocrouter", "json": "https://www.anchorterminal.com/tools/opendocrouter.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/tools/opendocrouter.md", "slim": "https://www.anchorterminal.com/tools/opendocrouter.min.md" }, "markdown": "## Overview\n\n**Grade C · 56.6/100 · rank #434 of 629 · #6 in Document parsing \u0026 extraction · not agent-ready · confidence medium**\n\n\n## Assessment\n\nOne endpoint reaches 11 parsing models, each with a dated recipe version, a published token price and a ParseBench score, and failed pages aren't charged. The service launched on 7 October 2026, so it has no status page, incident history, SLA or changelog yet, and no key scopes were found in the reviewed documentation.\n\n## Facts\n\n| Field | Value |\n| --- | --- |\n| Vendor | LlamaIndex (https://opendocrouter.ai) |\n| Kind | HTTP API |\n| Category | Document parsing \u0026 extraction (https://www.anchorterminal.com/categories/document-extraction) |\n| Transport | HTTP |\n| Endpoint | `https://www.opendocrouter.ai/v1` |\n| Auth | API key · Bearer API key created in the dashboard after a browser sign-in, sent as `Authorization: Bearer \u003ckey\u003e` and read by the SDKs from OPEN_DOC_ROUTER_API_KEY. The terms say keys can be revoked. No scopes, expiry or read-only keys were found in the reviewed documentation. `GET /v1/models` answers without a key. This is a separate key from a LlamaCloud key. |\n| Pricing | Pay per use ($48.82 / 1k pages) · Prepaid credit with no subscription. New accounts get $5 of promotional credit, and top-ups start at $10 with a 5% fee on each purchase. Each successful page is charged for its tokens at the chosen model's price, and layout adds $0.20 per 1M tokens. Failed, cached and blank pages are free. Whether sign-up needs a card wasn't established, because the dashboard needs a sign-in. LlamaIndex's launch post of 7 October 2026 gives a $25 minimum top-up, where the site, docs and terms say $10 (checked 2026-10-08). |\n| x402 | No · No x402, MPP or L402 in the docs, the OpenAPI document or the home page, and /.well-known/x402 returns 404. The 402 response is `insufficient_credits` for prepaid credit (checked 2026-10-08). |\n| Licence | Proprietary service under the LlamaIndex Terms of Service with an OpenDocRouter addendum. The Python and TypeScript SDKs are MIT |\n| Packages | pypi: `opendocrouter`; npm: `@llamaindex/opendocrouter` |\n| Source | https://github.com/run-llama/opendocrouter-py |\n| Docs | https://opendocrouter.ai/docs |\n| llms.txt | not found |\n| Last release | 2026-10-07 |\n| PyPI downloads / week | 127 |\n| Endpoints | POST /v1/parse, GET and DELETE /v1/parse/{id}, POST /v1/uploads, GET /v1/credits, GET /v1/models, all at https://www.opendocrouter.ai. OpenAPI 3.1, API version 1 |\n| Models | 11 on 8 October 2026. Six from Anthropic, Google and OpenAI and five from other publishers (Infinity-Parser2-Flash, MinerU2.5-Pro, TeleOCR, dots.mocr, PaddleOCR-VL-1.6). Each runs a versioned parsing recipe, and responses carry `model_version` and `price_version` |\n| File types and sizes | PDF, PNG and JPEG. URLs and uploads up to 50 MB or 500 pages, inline base64 about 3 MB, request body capped at 4 MB |\n| Sync and async | Sync returns every page in the response, up to 50 pages. Async needs `cache: true`, returns 202, takes up to 500 pages and is polled at GET /v1/parse/{id}. No webhooks in the reviewed documentation |\n| Output | Markdown for each page with status, token usage and charge. Optional layout with element types, markdown line spans, boxes and a confidence value. No field extraction, classification, chunking or index endpoints |\n| Rate limits | 300 POST /v1/parse calls a minute, 60 GET /v1/parse/{id} calls a minute, 10 requests and 5 async requests running at once per account, 100 unused uploads |\n| Errors and retries | 15 request error codes and 12 page error codes. 429 and 503 carry Retry-After. Each page is retried once by the service on timeouts, rate limits, provider errors and capacity. Pages still running after 270 seconds return `timeout` |\n| Data retention | No document or result is stored unless `cache: true` is sent. Cached results are encrypted and kept 24 hours or until DELETE. Uploads are deleted once read, or after an hour. Page counts, tokens, errors and charges are kept |\n| Billing | Prepaid credit that doesn't expire and isn't refundable. $5 promotional credit for new accounts, top-ups from $10 plus 5%. A request holds its maximum possible charge and releases the unused part when it ends |\n| SDKs | Python `opendocrouter` 1.0.0 (Python 3.9+) and TypeScript `@llamaindex/opendocrouter` 1.0.0, both MIT and published on 7 October 2026. Two retries with backoff and a 60-second timeout by default |\n| MCP server | None found in the docs or the official MCP registry |\n| Status page | None found. llamaindex.statuspage.io has no OpenDocRouter component |\n| Capabilities | docs.parse, docs.ocr, docs.tables |\n| Tags | hosted, usage, prepaid, router, openapi, python, typescript, async-jobs, closed-source, new |\n| JSON | https://www.anchorterminal.com/api/v1/tools/opendocrouter.json |\n\n## Score breakdown (methodology v0.4, October 2026 research run)\n\nAssessed 2026-10-08 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. \"This run\" is each category's share of the 100 points.\n\n| Category | Weight | This run | Score (0–100) | Points |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% | 20 | 43 | 8.6 |\n| Performance | 10% | pending | pending | n/a |\n| Schema \u0026 documentation | 13% | 16.2 | 85 | 13.8 |\n| Agent ergonomics | 13% | 16.2 | 84 | 13.7 |\n| Security \u0026 auth | 14% | 17.5 | 40 | 7.0 |\n| Payments \u0026 pricing | 10% | 12.5 | 30 | 3.8 |\n| Task success | 10% | pending | pending | n/a |\n| Maintenance \u0026 community | 7% | 8.8 | 65 | 5.7 |\n| Transparency \u0026 trust (editorial 45, provenance 49) | 7% | 8.8 | 47 | 4.1 |\n| Negative events | up to −15 | up to −15 | none recorded | 0 |\n| **Total** | | | | **56.6 → C** |\n\n### Why each score\n\n- Reliability 43: Read with the hosted lines. No status page was found. The site links none, /status returns 404 and llamaindex.statuspage.io lists seven LlamaParse components and none for OpenDocRouter (0). No readable incident history, and the service was announced on 7 October 2026, one day before this check (5). Limits are published with numbers, 300 parse calls and 60 polls a minute and 10 requests running at once per account (15). 429 and 503 carry Retry-After per the docs, each page error is marked as worth retrying or not, and `cache: true` makes a repeated request free. There is no idempotency key, and without the cache a resend is charged again (13 of 15). No SLA found, and the terms allow changes with or without notice (0). The API is version 1 with 1.0.0 SDKs and no beta or preview label (10).\n- Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes.\n- Schema \u0026 documentation 85: Public OpenAPI 3.1 document at /v1/openapi.json covering all six operations (25). No llms.txt (404), but the docs page is served as Markdown at /docs.md (10). The parse, get, delete and upload operations say when to use sync or async, when the cache is needed and what is charged. The credits and models operations have no description (16 of 20). `mode` and `mime_type` are enums, `expand` has a pattern and required fields are marked, while `pages` is a free string and `model` isn't enumerated (12 of 15). Examples in curl, Python and TypeScript, a table of 15 request errors and a table of 12 page errors (14 of 15). Models carry dated recipe versions and responses a `price_version`, and the SDKs have changelogs on GitHub, but there is no changelog for the service (8 of 15).\n- Agent ergonomics 84: API reading. `pages` selects pages, markdown and layout are opt-in on GET through `expand`, and a poll returns no document text without it (22 of 25). Results over 4 MB come in parts with `next_cursor`, and `pages` and `expand` size the output. There is no endpoint to list past requests (16 of 20). Errors have stable codes, 402 includes `required_usd` and `available_usd`, 429 and 503 include Retry-After and every response has X-Request-Id (19 of 20). No idempotency key. `cache: true` returns stored pages free on a repeat and failed pages can be resent alone, but a sync request without the cache is charged again if resent (12 of 20). Two required fields, and official SDKs in Python and TypeScript (15).\n- Security \u0026 auth 40: Bearer API keys created in the dashboard, and the terms say a key can be revoked. No scopes, expiry or rotation were found, and the dashboard needs a sign-in we didn't have (20 of 30). No read-only or restricted key found. One key can spend credit and read cached results, with spending bounded by the prepaid balance (6 of 20). The API returns untrusted document text and no prompt-injection guidance was found. Document URLs must be public HTTPS on the default port (0 of 15). GET /v1/parse/{id} shows what each request did and cost, and the docs mention a usage log keyed by X-Request-Id. No audit log found (8 of 15). SECURITY.md in the SDK repositories asks for private reports to security@runllama.ai. No security.txt on opendocrouter.ai or llamaindex.ai, and LlamaIndex's trust centre renders only with JavaScript, so no certification is confirmed for this service (6 of 20).\n- Payments \u0026 pricing 30: No x402, MPP or L402 (0). Token prices for every model, an average and a maximum charge per page, the layout price and the 5% top-up fee are public on the models page, the docs and `GET /v1/models` (20). New accounts get $5 of promotional credit. Whether a card is needed at sign-up isn't stated and the dashboard needs a sign-in (10 of 20, our call until that's confirmed). A person signs in through a browser to create a key (0).\n- Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored.\n- Maintenance \u0026 community 65: Both SDKs published 1.0.0 on 7 October 2026, the day of the announcement, and the newest model recipe is dated the same day (30). There is one SDK release and no service changelog. The model list shows eight distinct recipe dates between 25 September and 7 October 2026 and a price version of 6 October, which we count as half (10 of 20). No public changelog or community channel found, support is by email, and GitHub issues weren't readable (3 of 15). Current official SDKs in Python and TypeScript (15). The SDK repositories have CI workflows for lint, build and test, release-please and lock files. Run results weren't readable (7 of 10).\n- Transparency \u0026 trust 47: Closed service under the LlamaIndex terms with an OpenDocRouter addendum, SDKs MIT (15). The docs, the OpenAPI document and the addendum agree that nothing is stored without `cache: true`, cached results are encrypted and kept 24 hours, uploads are deleted once read or after an hour, and request records are kept for billing. The terms say LlamaIndex trains no models on user content. No DPA or retention period for request records was found, and the privacy notice dates from March 2024 and doesn't mention the service (22 of 30). No deprecation policy. Recipe and price versions are dated, and the terms allow changes and price changes without notice (3 of 20). The addendum names Anthropic, Google and OpenAI as examples of model providers that receive pages, leaves its infrastructure providers unnamed and gives no data location beyond processing in the United States (5 of 20).\n\nFix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (21 items): https://www.anchorterminal.com/fixes/opendocrouter.md (JSON https://www.anchorterminal.com/fixes/opendocrouter.json)\n\n### What we couldn't check\n\n- unchecked: the dashboard, which needs a sign-in. Key options (scopes, expiry, several keys), whether sign-up needs a card and what the usage log shows\n- unchecked: GitHub stars, open issues and CI run results for the SDK repositories. The GitHub API answered with a rate limit\n- unchecked: certifications and the subprocessor list in LlamaIndex's JavaScript-only trust centre, and whether they cover OpenDocRouter\n- The launch post of 7 October 2026 says top-ups start at $25. The site, docs and terms addendum say $10\n- The site says frontier models are charged at their providers' token prices with no markup. We didn't compare the listed prices with each provider's own\n- ParseBench scores and per-page averages are the vendor's figures, and the launch post calls ParseBench 'our benchmarks'. We didn't reproduce them\n- npm reports no download count yet for @llamaindex/opendocrouter, and the PyPI figure of 127 covers one day\n- No status page or changelog URL is recorded in provenance because none exists for the service. The SDK changelogs are on GitHub\n\n### Sources\n\n- home page: \u003chttps://www.opendocrouter.ai/\u003e (seen 2026-10-08)\n- docs: \u003chttps://www.opendocrouter.ai/docs\u003e (seen 2026-10-08)\n- docs as Markdown: \u003chttps://www.opendocrouter.ai/docs.md\u003e (seen 2026-10-08)\n- OpenAPI document: \u003chttps://www.opendocrouter.ai/v1/openapi.json\u003e (seen 2026-10-08)\n- model list and prices (API): \u003chttps://www.opendocrouter.ai/v1/models\u003e (seen 2026-10-08)\n- models and pricing page: \u003chttps://www.opendocrouter.ai/models\u003e (seen 2026-10-08)\n- terms with OpenDocRouter addendum: \u003chttps://www.opendocrouter.ai/terms\u003e (seen 2026-10-08)\n- privacy notice: \u003chttps://www.opendocrouter.ai/privacy\u003e (seen 2026-10-08)\n- launch post: \u003chttps://www.llamaindex.ai/blog/introducing-opendocrouter\u003e (seen 2026-10-08)\n- LlamaIndex status page and components: \u003chttps://llamaindex.statuspage.io/\u003e (seen 2026-10-08)\n- Python SDK repository (README, CHANGELOG, SECURITY.md, CI): \u003chttps://github.com/run-llama/opendocrouter-py\u003e (seen 2026-10-08)\n- TypeScript SDK repository: \u003chttps://github.com/run-llama/opendocrouter-ts\u003e (seen 2026-10-08)\n- PyPI: \u003chttps://pypi.org/pypi/opendocrouter/json\u003e (seen 2026-10-08)\n- npm: \u003chttps://registry.npmjs.org/@llamaindex/opendocrouter\u003e (seen 2026-10-08)\n- RDAP for opendocrouter.ai: \u003chttps://rdap.identitydigital.services/rdap/domain/opendocrouter.ai\u003e (seen 2026-10-08)\n- official MCP registry search (no result): \u003chttps://registry.modelcontextprotocol.io/v0/servers?search=opendocrouter\u003e (seen 2026-10-08)\n- LlamaIndex trust centre (JavaScript only): \u003chttps://security.llamaindex.ai/\u003e (seen 2026-10-08)\n\n## Who's behind it (provenance 49/100, checked 2026-10-08)\n\n| Check | Finding | Points |\n| --- | --- | --- |\n| Legal entity named | LlamaIndex, Inc. | 20/20 |\n| Domain age | opendocrouter.ai, registered 2026-09-23 (under a year) | 0/15 |\n| Endpoint on the vendor's domain | www.opendocrouter.ai | 15/15 |\n| Terms of service | read, states 6 of the 7 things a reader expects, and has 2 clauses that cost points | 5.1/10 |\n| Privacy policy | read, states 6 of the 8 things a reader expects | 8.5/10 |\n| Status page | not found | 0/10 |\n| Changelog | not found | 0/10 |\n| security.txt | not found | 0/10 |\n\nThe terms page carries an OpenDocRouter addendum last modified 2026-10-07 above the LlamaIndex Terms of Service of 2024-06-07, which name LlamaIndex, Inc. The SDK licence files read Copyright 2026 LlamaIndex, Inc.\n\nThe privacy page is the LlamaIndex Privacy Notice last updated 2024-03-30. It covers LlamaIndex as a controller and doesn't mention OpenDocRouter.\n\nRDAP for opendocrouter.ai gives a registration date of 2026-09-23 with the registrant behind a privacy service. The link to LlamaIndex rests on the site footer, the terms and the announcement on llamaindex.ai.\n\nwww.opendocrouter.ai/.well-known/security.txt and www.llamaindex.ai/.well-known/security.txt both return 404. SECURITY.md in the SDK repositories sends reports to security@runllama.ai.\n\nNo status page or service changelog is linked from the site, and /status and /changelog return 404. The only changelogs are the SDKs' CHANGELOG.md files on GitHub.\n\n### Terms and privacy, as read\n\nA reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice.\n\n**Terms of service** (https://www.opendocrouter.ai/terms), read 2026-10-08, dated 2026-10-07, states 6 of the 7 things a reader expects.\n\n- To know. Restricts benchmarking or competitive use (costs points). \"(h) use or display the Service in competition with us, to develop competing products or services, for benchmarking or competitive analysis of the Service, or otherwise to our detriment or disadvantage;\"\n- To know. Says the terms or the service can change without notice (costs points). \"We may, with or without prior notice, change the Service, stop providing the Service or features of the Service to you or to Users generally, or create usage limits for the Service.\"\n- To know. Says access can be ended without notice or for any reason. \"We may, with or without prior notice, permanently terminate or temporarily suspend your access to your User Account and/or the Service without liability, with or without cause, and for any or no reason, including if, in our sole determination, you violate any provision of these Terms.\"\n- To know. Requires arbitration or waives class actions. \"…YOU OPT OUT PURSUANT TO THE INSTRUCTIONS IN THE ARBITRATION AGREEMENT, THE EXCLUSIVE USE OF FINAL AND BINDING ARBITRATION ON AN INDIVIDUAL BASIS TO RESOLVE DISPUTES BETWEEN YOU AND US, INCLUDING ANY CLAIMS THAT AROSE OR WERE ASSERTED BEFORE YOU AGREED TO THESE TERMS.\"\n- Gives the date it was last updated. Last updated 2026-10-07.\n- Names the governing law or courts. The law of the State of Delaware.\n- States a limit on its liability. Rules out indirect and consequential losses, with no cap named in this sentence.\n- Says how changes to the terms are announced. Says it gives notice of a change.\n- Not found in the text. Refers to a service level or uptime commitment.\n- Also in the text (2026-10-08). Third-party models such as Anthropic, Google and OpenAI receive the pages sent to them, and their own usage policies apply to that content. \"Models from third parties, such as Anthropic, Google and OpenAI, receive the pages you send them, and their own usage policies apply to that content.\"\n- Also in the text (2026-10-08). Prepaid credit is non-refundable except where the law requires or at the vendor's discretion, and each purchase carries a non-refundable fee of 5% of the credit bought. \"Credit is non-refundable, except where Applicable Law requires or at our discretion.\"\n- Also in the text (2026-10-08). The licence granted over User Content is perpetual, irrevocable, transferable and sublicensable, for use as reasonably necessary to run the Service and as the Privacy Notice describes. \"to LlamaIndex a fully paid, royalty-free, transferable, perpetual, irrevocable, non-exclusive, and worldwide license, with the right to grant and authorize sublicenses\"\n\n**Privacy policy** (https://www.opendocrouter.ai/privacy), read 2026-10-08, dated 2024-03-30, states 6 of the 8 things a reader expects.\n\n- To know. Says it sells personal data or shares it for advertising. \"We may share a common account identifier (such as a hashed email address or user ID) with our third-party advertising partners to help link the personal data we and our third-party partners collect to the same person, or otherwise target advertising to an individual on a third-party website or platform.\"\n- Gives the date it was last updated. Last updated 2024-03-30.\n- Not found in the text. Says what rights people have over their data.\n- Gives a privacy contact. privacy@runllama.ai.\n- Not found in the text. Says where data is transferred or stored.\n- Also in the text (2026-10-08). The notice covers LlamaIndex as controller only and does not cover personal data it processes on a customer's behalf as a processor. \"However, this Privacy Notice does not cover or address how our customers may process personal data when they use our services, or how we may process personal data on their behalf in accordance with their instructions where we are acting as their processor.\"\n- Also in the text (2026-10-08). Customer Content, including uploaded files and documents, is used to run the services, handle requests and improve the services. \"We use this content primarily to provide you with our services, to facilitate your requests, and to improve our services.\"\n\n## Live (updated 2026-10-08 17:36 UTC)\n\n- Right now: up, HTTP 404, 146 ms, checked 2026-10-08 17:36 UTC (get on `https://www.opendocrouter.ai/v1`)\n- Uptime 24h 100.0% (25 probes) · 30 days 100.0% (25 probes) · p50 148 ms · p95 244 ms\n- github `run-llama/opendocrouter-py` v1.0.0, released 2026-10-07\n- npm `@llamaindex/opendocrouter` 1.0.0\n- pypi `opendocrouter` 1.0.0, released 2026-10-07\n- security.txt: none\n- Always current: https://www.anchorterminal.com/api/v1/live/opendocrouter.json\n\n## Probe metrics\n\nNot measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score.\n\n## Prices\n\n| Item | Price | Unit | Note |\n| --- | --- | --- | --- |\n| Parse with Claude Opus 5.5 | $48.82 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.784 a page |\n| Parse with Gemini 3 Flash | $19.67 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.199 a page |\n| Parse with GPT-5.6 Terra | $19.89 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.436 a page |\n| Parse with Gemini 3.8 Flash | $5.91 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.126 a page |\n| Parse with Infinity-Parser2-Flash | $4.34 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.050 a page |\n| Parse with dots.mocr | $3.97 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.030 a page |\n| Parse with TeleOCR | $2.70 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.045 a page |\n| Parse with PaddleOCR-VL-1.6 | $2.11 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.044 a page |\n| Parse with Claude Haiku 5.5 | $1.22 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.020 a page |\n| Parse with MinerU2.5-Pro | $0.86 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.007 a page |\n| Parse with GPT-6 Luna | $0.80 | per 1,000 pages | vendor's average on ParseBench documents, charged by tokens, at most $0.019 a page |\n| Layout add-on | $0.20 | per 1M tokens | added to each page whose layout comes back |\n| Top-up fee | 5% | percentage fee | on each credit purchase, minimum purchase $10, non-refundable |\n\nAcross all listings: https://www.anchorterminal.com/prices/index.md\n\n## Strengths\n\n- Public OpenAPI 3.1 document for all six operations, and the docs page is also served as Markdown at /docs.md\n- `GET /v1/models` lists 11 models without a key, each with token prices, an average and a maximum charge per page, and ParseBench scores\n- Failed, cached and blank pages are free, and every page comes back with its own status, token usage and charge\n- Fifteen request error codes and twelve page error codes are documented, with Retry-After on 429 and 503 and a retry verdict for each page error\n- Nothing from a document is stored unless `cache: true` is sent, and cached results are encrypted and deleted after 24 hours or on DELETE\n\n## Weaknesses\n\n- Launched on 7 October 2026. The domain was registered on 23 September 2026 and both SDKs have one release, 1.0.0\n- No status page, SLA or service changelog was found. LlamaIndex's status page lists only LlamaParse components\n- No scoped, expiring or read-only keys in the reviewed documentation, and no idempotency key\n- A request holds the model's maximum charge per page, $0.784 on Claude Opus 5.5, so the $5 starting credit admits six Opus pages a request\n- Without `cache: true` a dropped connection loses the markdown, the request is still charged and a resend is a new request\n\n## Before you call it (notes for agents)\n\n1. Call `GET /v1/models` first, which needs no key, and choose a model by `avg_charge_per_page_usd` and its ParseBench scores. Send its `id` as `model`\n2. Send `cache: true` on any request you might repeat. Without it the markdown exists only in the POST response and a resend is charged as a new request\n3. Raise the SDK timeout above its 60-second default for sync parses. Pages can run for 270 seconds and the SDKs retry a timed-out request twice\n4. Check every page's `status` before using its markdown. A 200 can be `partial`, and failed pages can be resent alone with `pages`\n5. Treat 402 as final until credit is added. The hold is the model's maximum charge per page times the page count, and `GET /v1/credits` shows `available_usd`\n\n## Connect\n\nInstall:\n\n```bash\npip install opendocrouter # or: npm install @llamaindex/opendocrouter\n```\n\nFirst request:\n\n```bash\ncurl https://www.opendocrouter.ai/v1/parse \\\n -H \"Authorization: Bearer $OPEN_DOC_ROUTER_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"google/gemini-3.8-flash-low\", \"document\": {\"url\": \"https://arxiv.org/pdf/1706.03762\"}}'\n```\n\nThrough letme (picks today, calling later): https://letme.dev/opendocrouter. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md\n\n## Similar tools\n\nRanked by shared capabilities, then score. Same-category tools with no shared capability key are listed last.\n\n| Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown |\n| --- | --- | --- | --- | --- | --- | --- |\n| Extend API + MCP | B | 62.9 | 291 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/extend.md |\n| Reducto API + MCP | B | 62.9 | 292 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/reducto.md |\n| LlamaParse API + MCP | C | 59.2 | 384 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/llamaparse.md |\n| Mistral OCR API | C | 58.8 | 393 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/mistral-ocr.md |\n| Adobe PDF Services / PDF Extract API | C | 55.9 | 441 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/adobe-pdf-extract.md |\n| Unstructured API + MCP | D | 46.9 | 554 | docs.parse, docs.ocr, docs.tables | no | https://www.anchorterminal.com/tools/unstructured.md |\n\n## Panel reviews (0)\n\nReviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): .\n\nDesk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md\n\n## Notable\n\n- `GET /v1/models` returned 11 models on 8 October 2026 (Claude Opus 5.5 and Haiku 5.5, Gemini 3 Flash and 3.8 Flash, GPT-5.6 Terra, GPT-6 Luna, Infinity-Parser2-Flash, MinerU2.5-Pro, TeleOCR, dots.mocr, PaddleOCR-VL-1.6), each with a recipe version dated between 25 September and 7 October 2026 (source: \u003chttps://www.opendocrouter.ai/v1/models\u003e)\n- Sync requests take up to 50 pages and async requests up to 500, from a public HTTPS URL, a one-time upload of up to 50 MB or inline base64 of about 3 MB. PDF, PNG and JPEG only (source: \u003chttps://www.opendocrouter.ai/docs\u003e)\n- With `layout: true` each page also returns elements in reading order with a type from 15 classes, the markdown lines each spans and its boxes on the page, for $0.20 per 1M tokens (source: \u003chttps://www.opendocrouter.ai/docs\u003e)\n- The terms addendum of 7 October 2026 says third-party models such as Anthropic, Google and OpenAI receive the pages sent to them under their own policies, and that models LlamaIndex hosts run on its infrastructure providers (source: \u003chttps://www.opendocrouter.ai/terms\u003e)\n- LlamaIndex announced the service on 7 October 2026 and describes LlamaParse as its managed platform with tuned tiers, extraction and indexing, which OpenDocRouter doesn't have (source: \u003chttps://www.llamaindex.ai/blog/introducing-opendocrouter\u003e)\n- The site links no status page, and llamaindex.statuspage.io lists seven LlamaParse components and none for OpenDocRouter (source: \u003chttps://llamaindex.statuspage.io/\u003e)\n\n## Compare\n\n- [Adobe PDF Services / PDF Extract API vs OpenDocRouter](https://www.anchorterminal.com/compare/adobe-pdf-extract-vs-opendocrouter.md): C 55.9 vs C 56.6\n- [Extend API + MCP vs OpenDocRouter](https://www.anchorterminal.com/compare/extend-vs-opendocrouter.md): B 62.9 vs C 56.6\n- [LlamaParse API + MCP vs OpenDocRouter](https://www.anchorterminal.com/compare/llamaparse-vs-opendocrouter.md): C 59.2 vs C 56.6\n- [Mistral OCR API vs OpenDocRouter](https://www.anchorterminal.com/compare/mistral-ocr-vs-opendocrouter.md): C 58.8 vs C 56.6\n- [Nanonets API + MCP vs OpenDocRouter](https://www.anchorterminal.com/compare/nanonets-vs-opendocrouter.md): E 42.6 vs C 56.6\n- [OpenDocRouter vs Reducto API + MCP](https://www.anchorterminal.com/compare/opendocrouter-vs-reducto.md): C 56.6 vs B 62.9\n- [OpenDocRouter vs Unstructured API + MCP](https://www.anchorterminal.com/compare/opendocrouter-vs-unstructured.md): C 56.6 vs D 46.9\n- [Invofox vs OpenDocRouter](https://www.anchorterminal.com/compare/invofox-vs-opendocrouter.md): D 46.8 vs C 56.6\n- [Mindee API vs OpenDocRouter](https://www.anchorterminal.com/compare/mindee-vs-opendocrouter.md): C 61.3 vs C 56.6\n- [OpenDocRouter vs Veryfi API + MCP](https://www.anchorterminal.com/compare/opendocrouter-vs-veryfi.md): C 56.6 vs C 55.2\n\n## Verify this listing\n\nFor the vendor. The badge or a plain link to this page verifies the listing, from a page on opendocrouter.ai or one of its subdomains, or the README of github.com/run-llama/opendocrouter-py. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{\"slug\": \"opendocrouter\", \"url\": \"…\"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify\n\nHTML badge:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/opendocrouter\"\u003e\u003cimg src=\"https://www.anchorterminal.com/badges/opendocrouter.svg\" alt=\"OpenDocRouter on Anchor Terminal\" height=\"20\"\u003e\u003c/a\u003e\n```\n\nMarkdown badge, for a README:\n\n```markdown\n[![OpenDocRouter on Anchor Terminal](https://www.anchorterminal.com/badges/opendocrouter.svg)](https://www.anchorterminal.com/tools/opendocrouter)\n```\n\nPlain link:\n\n```html\n\u003ca href=\"https://www.anchorterminal.com/tools/opendocrouter\"\u003eOpenDocRouter on Anchor Terminal\u003c/a\u003e\n```\n\n## Share this listing\n\nFor the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say OpenDocRouter is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score.\n\n- Dark: https://www.anchorterminal.com/assets/share/opendocrouter-dark.png\n- Light: https://www.anchorterminal.com/assets/share/opendocrouter-light.png\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-08", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Terminal", "url": "https://www.anchorterminal.com/tools/" }, { "name": "Document parsing \u0026 extraction", "url": "https://www.anchorterminal.com/categories/document-extraction" }, { "name": "OpenDocRouter", "url": "" } ], "description": "OpenDocRouter is a hosted API from LlamaIndex that sends PDFs and images to a document parsing model the caller picks and returns markdown for each page. It launched on 7 October 2026 and bills prepaid credit by tokens used.", "facts": [ "rank #434 of 629", "API key auth", "0 desk reviews" ], "h1": "OpenDocRouter", "image": "https://www.anchorterminal.com/assets/og/tools-opendocrouter.png", "path": "/tools/opendocrouter", "published": "2026-10-01", "section": "tools", "title": "OpenDocRouter review for AI agents, grade C (56.6/100)", "toc": null, "updated": "2026-10-08", "url": "https://www.anchorterminal.com/tools/opendocrouter" }, "tokens": { "markdown": 8150, "slim": 1930 }, "version": 1 }