{ "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "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" }, "tool": { "slug": "decision-3", "name": "Decision 3.0", "vendor": "vLLM Semantic Router Team", "vendorUrl": "https://vllm-sr.ai", "kind": "model", "category": "decision-models", "summary": "Decision 3.0 is a family of open-weight multimodal decision models from the vLLM Semantic Router team, 0.6B to 27B, under Apache-2.0. They answer choice, yes-or-no and score questions about text, images and video with a probability per option.", "url": "https://www.anchorterminal.com/tools/decision-3", "markdownUrl": "https://www.anchorterminal.com/tools/decision-3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/decision-3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/decision-3.json", "repo": "https://github.com/vllm-project/semantic-router", "license": "Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "vllm-sr" } ], "auth": "none", "authNotes": "No account. The weights are public and ungated on Hugging Face. The bundled `d3_server.py` binds to 127.0.0.1 and is open unless `DECISION_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` and answers 401 otherwise. `GET /health` stays open. The router's model runtime has no authentication.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy and no hosted API from the authors. Hardware is the owner's cost. The cards give speeds on one AMD Instinct MI325X GPU, and a third-party Core ML build runs the three smaller sizes on a Mac (checked 2026-10-12).", "priceSummary": "Free ยท OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Decision 3.0 is software the owner runs, and neither the bundled server nor the router's model runtime has a payment route (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://huggingface.co/collections/vllm-sr/decision-30", "openapi": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/vllm_srun/api/openapi.yaml", "capabilities": [ "inference.decision" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "multimodal", "openapi" ], "lastRelease": "2026-10-11", "graded": true, "anchor": { "graded": true, "score": 63.1, "grade": "B", "agentReady": false, "rank": 413, "ranked": true, "rankOf": 965, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 82, "payments": 60, "reliability": 58, "schema": 70, "security": 56, "transparency": 45 }, "pending": [ "performance", "tasks" ], "breakdown": [ { "key": "reliability", "name": "Reliability", "weight": 16, "effectiveWeight": 20, "score": 58, "points": 11.6, "reason": "Scored on the local-package checklist, since Decision 3.0 is a model the owner runs. The cards install with `pip install \"transformers==5.17.0\" torch ...` and load with `AutoModel.from_pretrained(..., trust_remote_code=True)`, and requirements.txt says the runtime was validated with transformers 5.17.0 on ROCm. No Python version is stated. The router's `vllm-sr` package states Python 3.10 or newer, but serving Decision 3.0 needs Engine mode, which is newer than the 0.4.0 stable release (12 of 20). The semantic-router repository runs public CI, and its model runtime has a `test_decision3_reference.py` suite and a parity record of byte-identical answers against the packages' own server on CPU and an MI325X, dated 11 October. Today's CI result on main was unread (15 of 25). The models are two days old and the Hub repositories have no discussions to read. We couldn't read issue reply times on the router repository (12 of 25). Each Hub repository carries tags v3.0.0 to v3.1.0, and the router pins a commit per size. There's no changelog in the model repositories, and five tagged releases in two days (9 of 15). Released as 3.0 with no beta label, though only two days old (10 of 15)." }, { "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": 70, "points": 11.38, "reason": "Read for a model the owner serves. The router's model runtime has an OpenAPI file, contract version 2.3.0, changed on 11 October, whose decision request carries `images` and `videos` for models with those modalities. The bundled `d3_server.py` has no specification file and documents its wire format in its docstring (22 of 25). vllm-sr.ai has no llms.txt (404). The cards and the server docstring are Markdown and plain text in each repository (5 of 10). The cards state what each size is, its inputs and limits, and the authors' evaluation. They say nothing about when not to use it (13 of 20). Three question types, choice with up to 255 options, noul and score, and an `images` or `videos` list of data URLs with stated byte and pixel caps. State is free-form text or JSON (12 of 15). Three worked examples (text, an image, a video) with downloadable inputs, but no recorded outputs and no error table. The server docstring names 401, 422 and 503 (9 of 15). Hub tags and a versioned runtime contract. No changelog for the models (9 of 15)." }, { "key": "ergonomics", "name": "Agent ergonomics", "weight": 13, "effectiveWeight": 16.25, "score": 72, "points": 11.7, "reason": "Read as an API an agent calls for a decision, as with Vela, Decider and Kev. Answers are probabilities, no text is generated, and every question sees the same text, images and videos. Videos are capped at 16,384 tokens a request, and the package config sets no other input limit (20 of 25). The caller fixes the output with any mix of the three types, and `permutation_average` scores choice questions in both option orders. There's no threshold field and no set or span type (15 of 20). The server answers 422 with a message, or an `invalid_questions` map naming each bad question, and refuses an over-long request whole rather than truncating it. The runtime answers `{error: {code, message}}` (15 of 20). Calls are stateless and safe to retry. The bundled server takes one request at a time and has no 429 or retry guidance (13 of 20). Loading is one `AutoModel` call or a `pipeline(\"decision\")`, with no SDK of its own. It needs a GPU for the evaluated settings, `trust_remote_code`, or the router's development channel (9 of 15)." }, { "key": "security", "name": "Security \u0026 auth", "weight": 14, "effectiveWeight": 17.5, "score": 56, "points": 9.8, "reason": "Read as software the owner runs. No account. The bundled server binds to 127.0.0.1 and is open unless `DECISION_API_KEY` is set, after which it requires one bearer key, compared in constant time. The router's model runtime has no authentication (13 of 30). A decision model has no write actions (15 of 20). The server accepts images and videos only as base64 data URLs within byte, pixel and duration caps, and refuses paths and URLs, so it fetches nothing. The in-process Python API does fetch http(s) URLs it is given. Nothing documents how hostile text, images or video in the input can move an answer (8 of 15). The server sets `x-request-id` and `server-timing` headers and keeps no log of calls. The runtime exposes metrics and says request text is never logged (8 of 15). SECURITY.md in the router repository takes private reports through GitHub Security Advisories. Each package ships MODEL_MANIFEST.json with SHA-256 for every file, which the runtime checks at load (by default only files under its fast-hash size are hashed). The `transformers` route runs repository code. No bug bounty and no security.txt on vllm-sr.ai (12 of 20)." }, { "key": "payments", "name": "Payments \u0026 pricing", "weight": 10, "effectiveWeight": 12.5, "score": 60, "points": 7.5, "reason": "Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up. No payment protocol (0). There is no hosted API from the authors. Hardware is the owner's cost." }, { "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": 82, "points": 7.18, "reason": "Read for an open-weight model. Created on 10 October 2026, with v3.1.0 on 11 October (30). Five tagged releases of each model in two days, after the team's Decision 1.0 post on 22 September and Vela 2.0 on 6 October (20). The router repository merged Decision 3.0 image support (#4862) and video and d3-edge support (#4868) on 11 October, and the `vllm-sr` CLI had four development builds on 11 October. We didn't check reply times on issues (15 of 25). No SDK of its own, and the router serves it only on the development channel (10 of 15). The router repository runs CI, with today's result on main unread (7 of 10)." }, { "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7, "effectiveWeight": 8.75, "score": 45, "points": 3.94, "note": "editorial 62, provenance 27", "reason": "Apache-2.0 for the weights and runtime, on Apache-2.0 Qwen3.5 and Qwen3.8 bases, with a NOTICE in each repository. Unlike Vela 2.0, the cards publish no training data or training stages, and we found no training code (24 of 30). Self-hosted, so inputs stay on the owner's hardware unless the Python API is given URLs to fetch. The runtime docs say request text is never logged. There's no privacy statement for the project (20 of 30). The router's support matrix has a Deprecated class, and Decision 1.0, 2.0 and Vela stay built in. No policy with notice periods (8 of 20). We found no telemetry statement either way and didn't audit the runtime code for it. Weights download from the Hugging Face Hub (10 of 20)." } ], "assessment": { "date": "2026-10-12", "basis": "public evidence", "confidence": "medium", "notes": { "ergonomics": "Read as an API an agent calls for a decision, as with Vela, Decider and Kev. Answers are probabilities, no text is generated, and every question sees the same text, images and videos. Videos are capped at 16,384 tokens a request, and the package config sets no other input limit (20 of 25). The caller fixes the output with any mix of the three types, and `permutation_average` scores choice questions in both option orders. There's no threshold field and no set or span type (15 of 20). The server answers 422 with a message, or an `invalid_questions` map naming each bad question, and refuses an over-long request whole rather than truncating it. The runtime answers `{error: {code, message}}` (15 of 20). Calls are stateless and safe to retry. The bundled server takes one request at a time and has no 429 or retry guidance (13 of 20). Loading is one `AutoModel` call or a `pipeline(\"decision\")`, with no SDK of its own. It needs a GPU for the evaluated settings, `trust_remote_code`, or the router's development channel (9 of 15).", "maintenance": "Read for an open-weight model. Created on 10 October 2026, with v3.1.0 on 11 October (30). Five tagged releases of each model in two days, after the team's Decision 1.0 post on 22 September and Vela 2.0 on 6 October (20). The router repository merged Decision 3.0 image support (#4862) and video and d3-edge support (#4868) on 11 October, and the `vllm-sr` CLI had four development builds on 11 October. We didn't check reply times on issues (15 of 25). No SDK of its own, and the router serves it only on the development channel (10 of 15). The router repository runs CI, with today's result on main unread (7 of 10).", "payments": "Free Apache-2.0 software with nothing to buy, so 20 + 20 + 20 for pricing, free use and no sign-up. No payment protocol (0). There is no hosted API from the authors. Hardware is the owner's cost.", "reliability": "Scored on the local-package checklist, since Decision 3.0 is a model the owner runs. The cards install with `pip install \"transformers==5.17.0\" torch ...` and load with `AutoModel.from_pretrained(..., trust_remote_code=True)`, and requirements.txt says the runtime was validated with transformers 5.17.0 on ROCm. No Python version is stated. The router's `vllm-sr` package states Python 3.10 or newer, but serving Decision 3.0 needs Engine mode, which is newer than the 0.4.0 stable release (12 of 20). The semantic-router repository runs public CI, and its model runtime has a `test_decision3_reference.py` suite and a parity record of byte-identical answers against the packages' own server on CPU and an MI325X, dated 11 October. Today's CI result on main was unread (15 of 25). The models are two days old and the Hub repositories have no discussions to read. We couldn't read issue reply times on the router repository (12 of 25). Each Hub repository carries tags v3.0.0 to v3.1.0, and the router pins a commit per size. There's no changelog in the model repositories, and five tagged releases in two days (9 of 15). Released as 3.0 with no beta label, though only two days old (10 of 15).", "schema": "Read for a model the owner serves. The router's model runtime has an OpenAPI file, contract version 2.3.0, changed on 11 October, whose decision request carries `images` and `videos` for models with those modalities. The bundled `d3_server.py` has no specification file and documents its wire format in its docstring (22 of 25). vllm-sr.ai has no llms.txt (404). The cards and the server docstring are Markdown and plain text in each repository (5 of 10). The cards state what each size is, its inputs and limits, and the authors' evaluation. They say nothing about when not to use it (13 of 20). Three question types, choice with up to 255 options, noul and score, and an `images` or `videos` list of data URLs with stated byte and pixel caps. State is free-form text or JSON (12 of 15). Three worked examples (text, an image, a video) with downloadable inputs, but no recorded outputs and no error table. The server docstring names 401, 422 and 503 (9 of 15). Hub tags and a versioned runtime contract. No changelog for the models (9 of 15).", "security": "Read as software the owner runs. No account. The bundled server binds to 127.0.0.1 and is open unless `DECISION_API_KEY` is set, after which it requires one bearer key, compared in constant time. The router's model runtime has no authentication (13 of 30). A decision model has no write actions (15 of 20). The server accepts images and videos only as base64 data URLs within byte, pixel and duration caps, and refuses paths and URLs, so it fetches nothing. The in-process Python API does fetch http(s) URLs it is given. Nothing documents how hostile text, images or video in the input can move an answer (8 of 15). The server sets `x-request-id` and `server-timing` headers and keeps no log of calls. The runtime exposes metrics and says request text is never logged (8 of 15). SECURITY.md in the router repository takes private reports through GitHub Security Advisories. Each package ships MODEL_MANIFEST.json with SHA-256 for every file, which the runtime checks at load (by default only files under its fast-hash size are hashed). The `transformers` route runs repository code. No bug bounty and no security.txt on vllm-sr.ai (12 of 20).", "transparency": "Apache-2.0 for the weights and runtime, on Apache-2.0 Qwen3.5 and Qwen3.8 bases, with a NOTICE in each repository. Unlike Vela 2.0, the cards publish no training data or training stages, and we found no training code (24 of 30). Self-hosted, so inputs stay on the owner's hardware unless the Python API is given URLs to fetch. The runtime docs say request text is never logged. There's no privacy statement for the project (20 of 30). The router's support matrix has a Deprecated class, and Decision 1.0, 2.0 and Vela stay built in. No policy with notice periods (8 of 20). We found no telemetry statement either way and didn't audit the runtime code for it. Weights download from the Hugging Face Hub (10 of 20)." }, "sources": [ { "what": "Decision 3.0 collection", "url": "https://huggingface.co/collections/vllm-sr/decision-30", "seen": "2026-10-12" }, { "what": "d3 model card (27B)", "url": "https://huggingface.co/vllm-sr/d3", "seen": "2026-10-12" }, { "what": "d3-mini model card", "url": "https://huggingface.co/vllm-sr/d3-mini", "seen": "2026-10-12" }, { "what": "d3-flash, d3-nano and d3-lite model cards", "url": "https://huggingface.co/vllm-sr/d3-lite", "seen": "2026-10-12" }, { "what": "repository metadata, files, tags and commits for the six models", "url": "https://huggingface.co/api/models/vllm-sr/d3-mini/refs", "seen": "2026-10-12" }, { "what": "bundled server source", "url": "https://huggingface.co/vllm-sr/d3-mini/blob/main/d3_server.py", "seen": "2026-10-12" }, { "what": "bundled runtime source, manifest checks and input handling", "url": "https://huggingface.co/vllm-sr/d3-mini/blob/main/d3_runtime.py", "seen": "2026-10-12" }, { "what": "decision config with readout temperature", "url": "https://huggingface.co/vllm-sr/d3-mini/blob/main/decision_config.json", "seen": "2026-10-12" }, { "what": "router docs, choosing a model (Decision 3.0 sizes and Engine mode)", "url": "https://github.com/vllm-project/semantic-router/blob/main/website/docs/model-runtime/choose-a-model.md", "seen": "2026-10-12" }, { "what": "Decision 3.0 parity record", "url": "https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/docs/records/decision3-parity.md", "seen": "2026-10-12" }, { "what": "model runtime OpenAPI file, contract 2.3.0", "url": "https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/vllm_srun/api/openapi.yaml", "seen": "2026-10-12" }, { "what": "Core ML port post by Fluid Inference, 11 October 2026", "url": "https://vllm-sr.ai/blog/decision-3-0-on-apple-silicon", "seen": "2026-10-12" }, { "what": "vllm-sr package metadata and release list", "url": "https://pypi.org/pypi/vllm-sr/json", "seen": "2026-10-12" }, { "what": "security.txt (404)", "url": "https://vllm-sr.ai/.well-known/security.txt", "seen": "2026-10-12" } ], "openQuestions": [ "unchecked: today's CI result on the semantic-router main branch, and issue reply times. The GitHub API wasn't available to this session", "unchecked: GitHub stars for vllm-project/semantic-router on 12 October. The Vela 2.0 listing recorded 6,054 on 8 October", "The accuracy, vision, video and latency figures are the authors', on their own harness. We haven't run them, and no calibration figures were published", "The lead described the probabilities as calibrated. Neither the cards nor the runtime make that claim, and the readout temperature is 1.0", "d3-edge (0.59B) is built into the router and public on the Hub but missing from the collection and has no card figures we read", "The Hub API lists tag v3.1.0 on d3-mini at commit b5598a4 while main and the router pin a475367. We didn't establish why", "Decision 2.0 and Decision 1.0 sit in the same Hugging Face organisation and aren't graded here" ] }, "negative": 0, "verdict": "Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures.", "bestFor": "Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.", "strengths": [ "Text, images and video in one request, with every question seeing all of them", "Apache-2.0 weights on Apache-2.0 bases, ungated on Hugging Face, with a SHA-256 manifest the runtime checks at load", "Hub releases tagged v3.0.0 to v3.1.0, and the router pins a commit hash for each size", "An optional `permutation_average` mode scores choice questions in both option orders and averages them", "The bundled server takes only data URLs within stated size caps, so it fetches nothing from the network" ], "weaknesses": [ "Released on 10 October 2026, with five tagged releases of each model by 11 October", "No calibration figures on the cards, though the category compares models on calibration", "Only choice, yes-or-no and score questions. No multi-label set or span answers", "Loading with `transformers` needs `trust_remote_code=True`, and the router's Engine mode needs its development channel", "No training data, training code or changelog published with the models" ], "agentNotes": [ "Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October", "Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422", "Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise", "Turn on `permutation_average=True` when routing must not depend on option order. It is off by default", "Expect one request at a time from the bundled server. Use the router's model runtime for queued serving" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 63.1 } ], "editorialScores": { "ergonomics": 72, "maintenance": 82, "payments": 60, "reliability": 58, "schema": 70, "security": 56, "transparency": 62 }, "provenanceScore": 27 }, "connect": { "install": "pip install \"transformers==5.17.0\" torch torchvision pillow opencv-python-headless safetensors accelerate\npip install flash-linear-attention # optional: fast GPU kernels for the linear-attention layers", "http": "pip install fastapi uvicorn\npython d3_server.py --model vllm-sr/d3-mini --device cuda:0 --port 8000" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/decision-3" }, "sameCompany": [ "vela" ], "notable": [ "Five sizes in the Hugging Face collection, d3 (26.09B, on Qwen3.8-27B), d3-flash (8.39B), d3-mini (4.54B), d3-nano (2.21B) and d3-lite (0.85B), the last four on Qwen3.5. A sixth, d3-edge (0.59B, a pruned d3-lite), is on the Hub and built into the router but not in the collection (https://huggingface.co/api/models/vllm-sr/d3-edge)", "The model repositories were created on 10 October 2026 and tagged v3.0.0 to v3.1.0, five releases, the last on 11 October (https://huggingface.co/api/models/vllm-sr/d3-mini/refs)", "Three question types, choice (up to 255 options), noul (yes or no) and score. Vela 2.0's set and span types are not supported (https://huggingface.co/vllm-sr/d3-mini/blob/main/d3_server.py)", "By the authors' figures d3 scores 64.7 on the Jev Decision Index 0.3.1 against 62.8 for Perplexity Decider v1.1 (27B) and 60.1 for Jev, and d3-mini 54.2 against 45.0 for its Decision 2.0 predecessor. These are the authors' numbers, not ours (https://huggingface.co/vllm-sr/d3)", "The cards report probabilities for every option but make no calibration claim and publish no calibration figures. The shipped config sets the readout temperature to 1.0 (https://huggingface.co/vllm-sr/d3-mini/blob/main/decision_config.json)", "The vllm-sr.ai blog has no launch post of its own. Its first Decision 3.0 post, on 11 October 2026, is a Core ML port by Alex Weng of Fluid Inference, written with early access (https://vllm-sr.ai/blog/decision-3-0-on-apple-silicon)", "The router added Decision 3.0 with images on 11 October 2026 and video inputs and d3-edge the same day, with a parity record of byte-identical answers against the packages' own server (https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/docs/records/decision3-parity.md)" ], "area": "models", "details": [ { "label": "Models", "value": "d3 (26.09B with a 0.46B vision encoder, on Qwen3.8-27B), d3-flash (8.39B, Qwen3.5-9B), d3-mini (4.54B, Qwen3.5-4B), d3-nano (2.21B, Qwen3.5-2B), d3-lite (0.85B, Qwen3.5-0.8B) and d3-edge (0.59B, a pruned d3-lite, outside the collection)" }, { "label": "Question types", "value": "choice (up to 255 options), noul (yes or no) and score (ordered levels), any mix in one request, one forward pass per question, a probability for every option and no generated text" }, { "label": "Inputs", "value": "Text or JSON, plus any number of images (PNG, JPEG or WebP, read at up to 1.6 MP) and videos (MP4, WebM, MOV or MKV, 2 frames a second, at most 32 frames and 16,384 video tokens a request)" }, { "label": "Serving", "value": "`AutoModel.from_pretrained(..., trust_remote_code=True)` and `model.system_one(...)`, the bundled `d3_server.py` on `POST /v1/systemone`, or the router's model runtime on `POST /v1/decisions` (Engine mode, development channel)" }, { "label": "Server limits", "value": "Data URLs only, each image at most 8,000,000 bytes and 16,000,000 pixels, each video at most 32,000,000 bytes and 300 seconds. Requests are served one at a time" }, { "label": "Errors", "value": "Bundled server 401, 422 (malformed body, unknown fields, invalid questions or over the input limit) and 503 while loading. Model runtime `{error: {code, message}}`" }, { "label": "Licence", "value": "Apache-2.0 with a NOTICE naming the Qwen base, which is also Apache-2.0" }, { "label": "Hosted option", "value": "None from the authors" } ], "provenance": { "legalEntity": "", "domain": "vllm-sr.ai", "domainRegistered": "2026-07-13", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/docs/records/decision3-parity.md", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "An open-source project with no company named as publisher. The NOTICE files read Copyright 2026 vLLM Semantic Router Team.", "Domain registration date carried from the Vela 2.0 listing's RDAP check of 8 October 2026.", "Software the owner runs, so there's no hosted endpoint, terms or privacy policy. The Apache-2.0 licence stands in for terms.", "vllm-sr.ai/.well-known/security.txt returned 404 on 12 October 2026. SECURITY.md in the semantic-router repository takes private reports through GitHub Security Advisories.", "The Hub repositories have no changelog. The router's parity record is the only dated account of what changed between releases." ], "score": 27, "checks": [ { "check": "Legal entity named", "value": "not found", "points": 0, "max": 20, "state": "no" }, { "check": "Domain age", "value": "vllm-sr.ai, registered 2026-07-13 (under a year)", "points": 0, "max": 15, "state": "no" }, { "check": "Endpoint on the vendor's domain", "value": "no hosted endpoint", "points": 0, "max": 0, "state": "na" }, { "check": "Terms of service", "value": "nothing hosted, so the Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases licence stands in", "points": 10, "max": 10, "state": "ok" }, { "check": "Privacy policy", "value": "nothing hosted, not scored", "points": 0, "max": 0, "state": "na" }, { "check": "Status page", "value": "not found", "points": 0, "max": 10, "state": "no" }, { "check": "Changelog", "value": "published", "points": 10, "max": 10, "state": "ok" }, { "check": "security.txt", "value": "not found", "points": 0, "max": 10, "state": "no" } ] }, "pageJsonUrl": "https://www.anchorterminal.com/tools/decision-3.json" } }