{ "data": { "a": { "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 · 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" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "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" ], "area": "models", "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 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/decision-3.json" }, "answer": "Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories.", "b": { "slug": "vela", "name": "Vela 2.0", "vendor": "vLLM Semantic Router project and KR Labs", "vendorUrl": "https://vllm-sr.ai", "kind": "model", "category": "decision-models", "summary": "Vela 2.0 is a family of four open-weight decision models from the vLLM Semantic Router project and KR Labs, released on 6 October 2026 under Apache-2.0 for routing, safety checks, personal-data spans and hallucination checks.", "url": "https://www.anchorterminal.com/tools/vela", "markdownUrl": "https://www.anchorterminal.com/tools/vela.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vela.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vela.json", "repo": "https://github.com/vllm-project/semantic-router", "license": "Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "vllm-sr" } ], "auth": "none", "authNotes": "No account. The weights are public and ungated on Hugging Face. The bundled `vela2_serve.py` binds to 127.0.0.1 and ignores the Authorization header unless `VELA2_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` and answers 401 otherwise. The router's model runtime has no authentication and publishes on 127.0.0.1 unless `--host` is passed.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy and no hosted API. Hardware is the owner's cost. The 0.3B runs on a CPU, and the cards put GPU parameter memory at about 17 GB for the 4B. The router docs list about 32 GB for the 9B (checked 2026-10-08).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Vela 2.0 is software the owner runs, and neither server has a payment route (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 6054, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://huggingface.co/collections/vllm-sr/vela-20", "openapi": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/vllm_srun/api/openapi.yaml", "capabilities": [ "inference.decision", "guard.pii", "guard.injection", "guard.moderation", "guard.self-host" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "openapi" ], "lastRelease": "2026-10-06", "graded": true, "anchor": { "graded": true, "score": 66.5, "grade": "B", "agentReady": false, "rank": 294, "ranked": true, "rankOf": 965, "categoryRank": 6, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 79, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 78, "security": 60, "transparency": 48 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.", "bestFor": "Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.", "strengths": [ "Five question types in one request (choice, noul, score, set and span), with span answers as labelled character offsets and a probability each", "Apache-2.0 weights, code and documentation, ungated on Hugging Face, with safetensors files and a SHA256SUMS manifest in the three decoder repositories", "Two serving routes. A bundled FastAPI server on `POST /v1/systemone`, and the router's model runtime with an OpenAPI 3.0.3 contract and Prometheus metrics", "The model cards disclose evaluation protocol, including that the 0.3B release selection considered test results and that SQuAD v2 isn't zero-shot", "The router's release note lists where the 0.3B default is behind Vela 1.0, with numbers, and how to restore each Vela 1.0 model" ], "weaknesses": [ "No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026", "Loading with `transformers` needs `trust_remote_code=True`, which runs Python from the model repository", "The router's `vllm-sr serve MODEL` engine mode is newer than the 0.4.0 stable release and needs the development channel", "By the authors' figures the 4B scores 31.63 on the Jev Decision Index 0.2.1 against 42.55 for its Decision 2.0 base", "The model runtime has no authentication, and the bundled server is open unless `VELA2_API_KEY` is set" ], "agentNotes": [ "Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch", "Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name", "Name span questions `pii`, `halu` or `toxic`, or set `\"head\": \"router\"`, to get the trained router head. Other labels go to the broad head", "Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit", "Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network" ], "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": 66.5 } ], "editorialScores": { "ergonomics": 79, "maintenance": 84, "payments": 60, "reliability": 57, "schema": 78, "security": 60, "transparency": 68 }, "provenanceScore": 27 }, "connect": { "install": "pip install torch \"transformers\u003e=5.17\" safetensors tokenizers numpy fastapi uvicorn\n# from a local snapshot of vllm-sr/Vela-2.0-4B\npython vela2_serve.py --model . --device cuda --port 8001", "http": "curl -s localhost:8001/v1/systemone -H 'content-type: application/json' \\\n -d '{\"model\":\"vllm-sr/Vela-2.0-4B\",\"state\":\"My card was charged twice and the parcel never arrived.\",\"questions\":{\"issues\":{\"type\":\"set\",\"instructions\":\"Which issues does the customer report?\",\"criteria\":{\"billing\":\"payments, charges, refunds or invoices\",\"shipping\":\"delivery of an order or a parcel\",\"login\":\"signing in, passwords or account access\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/vela" }, "sameCompany": [ "decision-3" ], "area": "models", "provenance": { "legalEntity": "", "domain": "vllm-sr.ai", "domainRegistered": "2026-07-13", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "An open-source project with no company named as publisher. The site footer reads vLLM Semantic Router Team, and the model cards credit KR Labs and vLLM Semantic Router.", "RDAP gives 13 July 2026 as the registration date of vllm-sr.ai.", "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 returns 404. SECURITY.md in the repository takes private reports through GitHub Security Advisories.", "The weights are on huggingface.co under the vllm-sr organisation, and the code for the router and its model runtime is at github.com/vllm-project/semantic-router." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/vela.json", "live": { "slug": "vela", "versions": [ { "registry": "github", "name": "vllm-project/semantic-router", "version": "v0.4.0", "released": "2026-09-27", "seenAt": "2026-10-11T20:04:18.357886079Z" }, { "registry": "pypi", "name": "vllm-sr", "version": "0.4.0", "released": "2026-09-27", "seenAt": "2026-10-11T20:04:18.232031217Z" } ], "githubStars": 6087, "pypiWeekly": 12392, "securityTxt": { "url": "https://vllm-sr.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-11T15:42:30.539810509Z" }, "domain": { "domain": "vllm-sr.ai", "registered": "2026-07-13", "source": "https://rdap.identitydigital.services/rdap/domain/vllm-sr.ai", "checkedAt": "2026-10-11T13:22:35.430005385Z" }, "pages": [ { "url": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "kind": "changelog", "status": 404, "checkedAt": "2026-10-11T19:35:39.18631015Z", "changedAt": "2026-10-09T18:47:13.835337297Z", "fingerprint": "10ded21d9f13" } ], "updatedAt": "2026-10-11T20:04:18.357886079Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "vLLM Semantic Router Team", "b": "vLLM Semantic Router project and KR Labs", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases", "b": "Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-11", "b": "2026-10-06", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "6.1k stars", "name": "Popularity" } ], "faq": [ { "answer": "Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories.", "question": "Which is better for AI agents, Decision 3.0 or Vela 2.0?" }, { "answer": "Neither needs a key.", "question": "Do Decision 3.0 and Vela 2.0 need an API key?" }, { "answer": "No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Vela 2.0.", "question": "Can an agent call Decision 3.0 and Vela 2.0 without installing anything?" }, { "answer": "Yes. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases). Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).", "question": "Are Decision 3.0 and Vela 2.0 open source?" } ], "goodFor": [ { "aheadOn": null, "also": null, "goodFor": "Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.", "slug": "decision-3", "watchFor": "Released on 10 October 2026, with five tagged releases of each model by 11 October" }, { "aheadOn": [ "Schema \u0026 documentation, 78 against 70", "Agent ergonomics, 79 against 72" ], "also": null, "goodFor": "Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.", "slug": "vela", "watchFor": "No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.json", "title": "Celeris-1 Decision vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.json", "title": "Celeris-1 Decision vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.json", "title": "Clef vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.json", "title": "Clef vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.json", "title": "Laya vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-vela.json", "title": "Laya vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/decider-vs-decision-3.json", "title": "Decider vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/decider-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/decider-vs-vela.json", "title": "Decider vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/decider-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-gliclass.json", "title": "Decision 3.0 vs GLiClass", "url": "https://www.anchorterminal.com/compare/decision-3-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev.json", "title": "Decision 3.0 vs Kev", "url": "https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.json", "title": "Decision 3.0 vs Liquid d1", "url": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.json", "title": "Decision 3.0 vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.json", "title": "Decision 3.0 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.json", "title": "Decision 3.0 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.json", "title": "Decision 3.0 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.json", "title": "Decision 3.0 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/decision-3-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.json", "title": "Decision 3.0 vs Jev", "url": "https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-vela.json", "title": "GLiClass vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/gliclass-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.json", "title": "Kev vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-vela.json", "title": "Liquid d1 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.json", "title": "Microsoft-Decision-1 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-vela.json", "title": "Drex 1.5 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.json", "title": "OpenAI Decisions API vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela.json", "title": "pplx-decider vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/strands-decider-vs-vela.json", "title": "Strands Decider 2B vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/strands-decider-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.json", "title": "Jev vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/typesafe-jev-vs-vela" } ], "scores": [ { "by": 1, "decision-3": 58, "edge": "decision-3", "key": "reliability", "name": "Reliability", "vela": 57, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 8, "decision-3": 70, "edge": "vela", "key": "schema", "name": "Schema \u0026 documentation", "vela": 78, "weight": 13 }, { "by": 7, "decision-3": 72, "edge": "vela", "key": "ergonomics", "name": "Agent ergonomics", "vela": 79, "weight": 13 }, { "by": 4, "decision-3": 56, "edge": "vela", "key": "security", "name": "Security \u0026 auth", "vela": 60, "weight": 14 }, { "by": 0, "decision-3": 60, "edge": "", "key": "payments", "name": "Payments \u0026 pricing", "vela": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "decision-3": 82, "edge": "vela", "key": "maintenance", "name": "Maintenance \u0026 community", "vela": 84, "weight": 7 }, { "by": 3, "decision-3": 45, "edge": "vela", "key": "transparency", "name": "Transparency \u0026 trust", "vela": 48, "weight": 7 } ], "summary": "Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Both do decision models.", "verdicts": { "decision-3": "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.", "vela": "One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/decision-3-vs-vela", "json": "https://www.anchorterminal.com/compare/decision-3-vs-vela.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/decision-3-vs-vela.md", "slim": "https://www.anchorterminal.com/compare/decision-3-vs-vela.min.md" }, "markdown": "Vela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Both do decision models.\n\n- Decision 3.0: grade B, 63.1/100, rank #413 of 965. Markdown https://www.anchorterminal.com/tools/decision-3.md · JSON https://www.anchorterminal.com/api/v1/tools/decision-3.json\n- Vela 2.0: grade B, 66.5/100, rank #294 of 965. Markdown https://www.anchorterminal.com/tools/vela.md · JSON https://www.anchorterminal.com/api/v1/tools/vela.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 105 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Decision 3.0 (B)\n\nGood for: Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.\n\nWatch for: Released on 10 October 2026, with five tagged releases of each model by 11 October\n\n### Vela 2.0 (B)\n\nGood for: Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.\n\nAhead on:\n- Schema \u0026 documentation, 78 against 70\n- Agent ergonomics, 79 against 72\n\nWatch for: No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026\n\n\n## Score by category\n\n| Category | Weight | Decision 3.0 | Vela 2.0 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 58 | 57 | Decision 3.0 +1 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 78 | Vela 2.0 +8 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 79 | Vela 2.0 +7 |\n| Security \u0026 auth | 14% (17.5 this run) | 56 | 60 | Vela 2.0 +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 84 | Vela 2.0 +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 48 | Vela 2.0 +3 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **63.1 · B** | **66.5 · B** | |\n\n## Facts side by side\n\n| Fact | Decision 3.0 | Vela 2.0 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | vLLM Semantic Router Team | vLLM Semantic Router project and KR Labs |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-11 | 2026-10-06 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | none | 6.1k stars |\n\n## Verdicts\n\n**Decision 3.0.** 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.\n\n**Vela 2.0.** One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.\n\n## Before you call either\n\n### Decision 3.0\n\n1. Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October\n2. Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422\n3. Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise\n4. Turn on `permutation_average=True` when routing must not depend on option order. It is off by default\n5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving\n\n### Vela 2.0\n\n1. Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch\n2. Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name\n3. Name span questions `pii`, `halu` or `toxic`, or set `\"head\": \"router\"`, to get the trained router head. Other labels go to the broad head\n4. Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit\n5. Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network\n\n## Questions\n\n### Which is better for AI agents, Decision 3.0 or Vela 2.0?\n\nVela 2.0 scores 66.5 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories.\n\n### Do Decision 3.0 and Vela 2.0 need an API key?\n\nNeither needs a key.\n\n### Can an agent call Decision 3.0 and Vela 2.0 without installing anything?\n\nNo hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Vela 2.0.\n\n### Are Decision 3.0 and Vela 2.0 open source?\n\nYes. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases). Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-vela.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-vela.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"decision-3\", \"b\": \"vela\"}`. From a terminal: `anchor compare decision-3 vela`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/vela.json\n\n## Other comparisons with Decision 3.0 or Vela 2.0\n\n- [Celeris-1 Decision vs Decision 3.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.md)\n- [Celeris-1 Decision vs Vela 2.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.md)\n- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)\n- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decider vs Vela 2.0](https://www.anchorterminal.com/compare/decider-vs-vela.md)\n- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)\n- [Decision 3.0 vs Kev](https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev.md)\n- [Decision 3.0 vs Liquid d1](https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.md)\n- [Decision 3.0 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md)\n- [Decision 3.0 vs Drex 1.5](https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md)\n- [Decision 3.0 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.md)\n- [Decision 3.0 vs pplx-decider](https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.md)\n- [Decision 3.0 vs Strands Decider 2B](https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.md)\n- [Decision 3.0 vs Jev](https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.md)\n- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)\n- [Kev vs Vela 2.0](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.md)\n- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-vs-vela.md)\n- [Microsoft-Decision-1 vs Vela 2.0](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.md)\n- [Drex 1.5 vs Vela 2.0](https://www.anchorterminal.com/compare/nace-drex-vs-vela.md)\n- [OpenAI Decisions API vs Vela 2.0](https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.md)\n- [pplx-decider vs Vela 2.0](https://www.anchorterminal.com/compare/pplx-decider-vs-vela.md)\n- [Strands Decider 2B vs Vela 2.0](https://www.anchorterminal.com/compare/strands-decider-vs-vela.md)\n- [Jev vs Vela 2.0](https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.md)\n", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Decision 3.0 vs Vela 2.0", "url": "" } ], "description": "Vela 2.0 scores 66.5 (B) to Decision 3.0's 63.1 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Decision 3.0 B 63.1", "Vela 2.0 B 66.5", "scores" ], "h1": "Decision 3.0 vs Vela 2.0", "image": "https://www.anchorterminal.com/assets/og/compare-decision-3-vs-vela.png", "path": "/compare/decision-3-vs-vela", "published": "2026-10-01", "section": "tools", "title": "Decision 3.0 vs Vela 2.0 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/decision-3-vs-vela" }, "tokens": { "markdown": 2450, "slim": 480 }, "version": 1 }