{ "data": { "a": { "slug": "microsoft-decision-1", "name": "Microsoft-Decision-1", "vendor": "Microsoft", "vendorUrl": "https://www.microsoft.com", "kind": "model", "category": "decision-models", "summary": "Microsoft-Decision-1 is a Microsoft model, post-trained from Qwen3.5-9B, that scores fixed answer options with a calibrated probability for each. It is in public preview on Microsoft Foundry and OpenRouter, at $0.042 per million input tokens.", "url": "https://www.anchorterminal.com/tools/microsoft-decision-1", "markdownUrl": "https://www.anchorterminal.com/tools/microsoft-decision-1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/microsoft-decision-1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.json", "license": "Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found.", "transports": [ "http" ], "packages": [], "auth": "mixed", "authNotes": "Foundry route: a Microsoft Entra bearer token for https://cognitiveservices.azure.com/.default, against a deployment in a Foundry resource, so an Azure subscription and deployment come first. OpenRouter route: an OpenRouter API key, read from OPENROUTER_API_KEY in OpenRouter's SDK example. Signup and key creation on OpenRouter were not checked.", "pricing": "usage", "pricingNotes": "$0.042 per million input tokens, with output free, on Foundry US and EU Datazone deployments and on OpenRouter (checked 10 October 2026). Microsoft says usage charges apply. No free tier or trial without a card was found.", "priceSummary": "Pay per use", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in Microsoft's announcement, the Tech Community post, the Foundry sample or OpenRouter's model page, checked 10 October 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-10" }, "docsUrl": "https://commandline.microsoft.com/microsoft-decision-1-model-foundry/", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "usage-priced", "status-page", "beta" ], "lastRelease": "2026-10-09", "graded": true, "anchor": { "graded": true, "score": 39, "grade": "E", "agentReady": false, "rank": 921, "ranked": true, "rankOf": 954, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 50, "maintenance": 40, "payments": 20, "reliability": 30, "schema": 43, "security": 52, "transparency": 32 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": 0, "verdict": "Microsoft publishes $0.042 per million input tokens, with output free, and the model is callable through Microsoft Foundry and OpenRouter. It is in public preview. No licence, model-specific retention statement, rate limit or deprecation policy was found, and the Foundry route needs an Azure deployment and an Entra token. Latency and accuracy figures are Microsoft's claims.", "bestFor": "Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text.", "strengths": [ "Price published without a login: $0.042 per million input tokens, with output free, on the US and EU Datazone deployments and on OpenRouter", "Callable today through two routes, Microsoft Foundry and OpenRouter, both linked from Microsoft's 9 October 2026 announcement", "Each answer is a probability for one fixed option, which Microsoft describes as calibrated, so an application can send uncertain results to review", "OpenRouter lists a 32,768-token context window, text input and decisions as output", "OpenRouter's documentation lists a Decisions method in its Python, TypeScript and Go SDKs, marked alpha" ], "weaknesses": [ "Public preview only. Microsoft's post gives no general availability date and states no licence for the hosted model", "No model-specific rate limit, retention statement or deprecation policy was found. Microsoft's Foundry data page covers Models sold by Azure in general", "The Foundry route needs an Azure subscription, a deployment of the model and a Microsoft Entra token, all set up by a person", "Microsoft describes its Xbox Research result as competitive with GPT-5 or GPT-6 Sol on quality, not better, and the two Microsoft posts name different baselines for it", "Azure status history lists a Foundry Models incident on 29 September 2026 in Sweden Central, with intermittent failures and HTTP 5xx for about six hours" ], "agentNotes": [ "Use OpenRouter's Decisions method, not an OpenAI chat-completions SDK. OpenRouter says chat completions SDKs will not work with this model", "On Foundry, send the request to the deployment's /providers/microsoft/v1/systemone path with a Microsoft Entra token for https://cognitiveservices.azure.com/.default, not an API key", "Take the deployment name from the Foundry quickstart before the first call. Microsoft says to confirm the route and authentication header, and the pages reviewed do not give the name", "Keep each request within OpenRouter's 32,768-token context and send only fixed options, since the model is not intended for open-ended generation", "Measure latency and calibration on your own labelled cases before relying on Microsoft's latency and 'nine times out of 10' statements" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 39 } ], "editorialScores": { "ergonomics": 50, "maintenance": 40, "payments": 20, "reliability": 30, "schema": 43, "security": 52, "transparency": 22 }, "provenanceScore": 41 }, "connect": { "http": "curl -X POST \"$AZURE_ENDPOINT/providers/microsoft/v1/systemone\" \\\n -H \"Authorization: Bearer $ENTRA_TOKEN\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"\u003cdeployment-name\u003e\",\"state\":\"The customer requests a refund for a duplicate charge.\",\"questions\":{\"team\":{\"type\":\"choice\",\"instructions\":\"Which team should handle this request?\",\"criteria\":{\"billing\":\"Charges, invoices, refunds or subscription payments\",\"technical\":\"Software errors or integration failures\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/microsoft-decision-1" }, "sameCompany": [ "azure-foundry-fine-tuning", "azure-ai-content-safety", "azure-speech-to-text", "azure-text-to-speech", "microsoft-agent-framework", "microsoft-execution-containers", "microsoft-entra-agent-id", "azure-key-vault", "azure-document-intelligence", "azure-devops-mcp", "microsoft-learn-mcp", "playwright-mcp", "azure-mcp", "azure-maps", "azure-translator", "microsoft-graph-calendar", "azure-blob-storage", "onedrive-sharepoint", "microsoft-teams", "dynamics-365-sales", "power-automate", "foundry-local", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph" ], "area": "models", "unitPrices": [ { "item": "Decision input", "unit": "1m-tokens", "usd": 0.042, "note": "US and EU Datazone on Foundry and OpenRouter. Microsoft's post says usage charges apply." }, { "item": "Decision output", "unit": "1m-tokens", "usd": 0, "note": "Free per Microsoft's post and OpenRouter. The Foundry price table shows N/A." } ], "provenance": { "legalEntity": "", "domain": "microsoft.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy", "statusPage": "https://azure.status.microsoft/en-us/status/history/", "changelog": "", "securityTxt": "expired", "checked": "2026-10-10", "notes": [ "The Foundry endpoint is account-specific, given as AZURE_ENDPOINT in Microsoft's sample, so endpointOnVendorDomain is not set.", "The legal entity name and Microsoft's product terms were not read, so terms is empty.", "Microsoft's security.txt at www.microsoft.com/.well-known/security.txt gives an Expires date of 2026-09-23, which has passed.", "The Azure status history page shows a Foundry Models component and dated incidents. It is shared by all Foundry models, not specific to this one.", "The Foundry model catalogue page at ai.azure.com is rendered by script and returned no model content when read." ], "score": 41 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/microsoft-decision-1.json", "live": { "slug": "microsoft-decision-1", "vendorStatus": { "page": "https://azure.status.microsoft/en-us/status/history", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T11:53:10.031474948Z" }, "updatedAt": "2026-10-10T11:53:10.031474948Z" } }, "answer": "Vela 2.0 scores 66.5 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category.", "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": 291, "ranked": true, "rankOf": 954, "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" }, "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": "2026-10-09T17:26:43.396072974Z" }, { "registry": "pypi", "name": "vllm-sr", "version": "0.4.0", "released": "2026-09-27", "seenAt": "2026-10-09T17:26:43.275825559Z" } ], "githubStars": 6069, "pypiWeekly": 15068, "securityTxt": { "url": "https://vllm-sr.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:13.1700609Z" }, "pages": [ { "url": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:47:13.835337297Z", "changedAt": "2026-10-09T18:47:13.835337297Z", "fingerprint": "10ded21d9f13" } ], "updatedAt": "2026-10-09T18:47:13.835337297Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Microsoft", "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": "OAuth or key", "b": "None", "name": "Auth" }, { "a": "Pay per use", "b": "Free", "name": "Pricing" }, { "a": "free", "b": "free", "name": "Price for decision models" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found.", "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": "2026-10-09", "b": "2026-10-06", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "", "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 Microsoft-Decision-1's 39 (E), and leads in every scored category.", "question": "Which is better for AI agents, Microsoft-Decision-1 or Vela 2.0?" }, { "answer": "Microsoft-Decision-1, at free against free for Vela 2.0. These are the vendors' published prices for the job.", "question": "Which is cheaper for decision models, Microsoft-Decision-1 or Vela 2.0?" }, { "answer": "Microsoft-Decision-1 takes an API key or an OAuth sign-in. Vela 2.0 needs no key.", "question": "Do Microsoft-Decision-1 and Vela 2.0 need an API key?" }, { "answer": "No hosted endpoint is listed for Microsoft-Decision-1. No hosted endpoint is listed for Vela 2.0.", "question": "Can an agent call Microsoft-Decision-1 and Vela 2.0 without installing anything?" }, { "answer": "No open-source release is listed for Microsoft-Decision-1. 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 Microsoft-Decision-1 and Vela 2.0 open source?" } ], "goodFor": [ { "aheadOn": null, "also": [ "Cheaper for decision models, $0 against $0 per 1M tokens" ], "goodFor": "Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text.", "slug": "microsoft-decision-1", "watchFor": "Public preview only. Microsoft's post gives no general availability date and states no licence for the hosted model" }, { "aheadOn": [ "Reliability, 57 against 30", "Schema \u0026 documentation, 78 against 43", "Agent ergonomics, 79 against 50", "Security \u0026 auth, 60 against 52", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 84 against 40", "Transparency \u0026 trust, 48 against 32" ], "also": [ "No key needed to call it", "Open source" ], "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-microsoft-decision-1.json", "title": "Celeris-1 Decision vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-microsoft-decision-1" }, { "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-microsoft-decision-1.json", "title": "Clef vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1" }, { "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-microsoft-decision-1.json", "title": "Laya vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1" }, { "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-microsoft-decision-1.json", "title": "Decider vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/decider-vs-microsoft-decision-1" }, { "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/gliclass-vs-microsoft-decision-1.json", "title": "GLiClass vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1" }, { "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-microsoft-decision-1.json", "title": "Kev vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-microsoft-decision-1" }, { "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-microsoft-decision-1.json", "title": "Liquid d1 vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1" }, { "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-nace-drex.json", "title": "Microsoft-Decision-1 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-openai-decisions-api.json", "title": "Microsoft-Decision-1 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-pplx-decider.json", "title": "Microsoft-Decision-1 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-strands-decider.json", "title": "Microsoft-Decision-1 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-typesafe-jev.json", "title": "Microsoft-Decision-1 vs Jev", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-typesafe-jev" }, { "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": 27, "edge": "vela", "key": "reliability", "microsoft-decision-1": 30, "name": "Reliability", "vela": 57, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 35, "edge": "vela", "key": "schema", "microsoft-decision-1": 43, "name": "Schema \u0026 documentation", "vela": 78, "weight": 13 }, { "by": 29, "edge": "vela", "key": "ergonomics", "microsoft-decision-1": 50, "name": "Agent ergonomics", "vela": 79, "weight": 13 }, { "by": 8, "edge": "vela", "key": "security", "microsoft-decision-1": 52, "name": "Security \u0026 auth", "vela": 60, "weight": 14 }, { "by": 40, "edge": "vela", "key": "payments", "microsoft-decision-1": 20, "name": "Payments \u0026 pricing", "vela": 60, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 44, "edge": "vela", "key": "maintenance", "microsoft-decision-1": 40, "name": "Maintenance \u0026 community", "vela": 84, "weight": 7 }, { "by": 16, "edge": "vela", "key": "transparency", "microsoft-decision-1": 32, "name": "Transparency \u0026 trust", "vela": 48, "weight": 7 } ], "summary": "Vela 2.0 scores 66.5 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category. Both do decision models. Microsoft-Decision-1 is cheaper for decision models, $0 against $0 per 1M tokens.", "verdicts": { "microsoft-decision-1": "Microsoft publishes $0.042 per million input tokens, with output free, and the model is callable through Microsoft Foundry and OpenRouter. It is in public preview. No licence, model-specific retention statement, rate limit or deprecation policy was found, and the Foundry route needs an Azure deployment and an Entra token. Latency and accuracy figures are Microsoft's claims.", "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/microsoft-decision-1-vs-vela", "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.md", "slim": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.min.md" }, "markdown": "Vela 2.0 scores 66.5 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category. Both do decision models. Microsoft-Decision-1 is cheaper for decision models, $0 against $0 per 1M tokens.\n\n- Microsoft-Decision-1: grade E, 39/100, rank #921 of 954. Markdown https://www.anchorterminal.com/tools/microsoft-decision-1.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.json\n- Vela 2.0: grade B, 66.5/100, rank #291 of 954. 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 91 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Microsoft-Decision-1 (E)\n\nGood for: Routing, classification, prioritisation and rubric checks over text, where a fixed set of options and a low price per token matter more than generated text.\n\nAlso in its favour:\n- Cheaper for decision models, $0 against $0 per 1M tokens\n\nWatch for: Public preview only. Microsoft's post gives no general availability date and states no licence for the hosted model\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- Reliability, 57 against 30\n- Schema \u0026 documentation, 78 against 43\n- Agent ergonomics, 79 against 50\n- Security \u0026 auth, 60 against 52\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 84 against 40\n- Transparency \u0026 trust, 48 against 32\n\nAlso in its favour:\n- No key needed to call it\n- Open source\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 | Microsoft-Decision-1 | Vela 2.0 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 30 | 57 | Vela 2.0 +27 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 43 | 78 | Vela 2.0 +35 |\n| Agent ergonomics | 13% (16.2 this run) | 50 | 79 | Vela 2.0 +29 |\n| Security \u0026 auth | 14% (17.5 this run) | 52 | 60 | Vela 2.0 +8 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 20 | 60 | Vela 2.0 +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 40 | 84 | Vela 2.0 +44 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 32 | 48 | Vela 2.0 +16 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **39 · E** | **66.5 · B** | |\n\n## Facts side by side\n\n| Fact | Microsoft-Decision-1 | Vela 2.0 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Microsoft | vLLM Semantic Router project and KR Labs |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | OAuth or key | None |\n| Pricing | Pay per use | Free |\n| Price for decision models | free | free |\n| x402 | no | no |\n| Licence | Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found. | 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 | 2026-10-09 | 2026-10-06 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | | 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**Microsoft-Decision-1.** Microsoft publishes $0.042 per million input tokens, with output free, and the model is callable through Microsoft Foundry and OpenRouter. It is in public preview. No licence, model-specific retention statement, rate limit or deprecation policy was found, and the Foundry route needs an Azure deployment and an Entra token. Latency and accuracy figures are Microsoft's claims.\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### Microsoft-Decision-1\n\n1. Use OpenRouter's Decisions method, not an OpenAI chat-completions SDK. OpenRouter says chat completions SDKs will not work with this model\n2. On Foundry, send the request to the deployment's /providers/microsoft/v1/systemone path with a Microsoft Entra token for https://cognitiveservices.azure.com/.default, not an API key\n3. Take the deployment name from the Foundry quickstart before the first call. Microsoft says to confirm the route and authentication header, and the pages reviewed do not give the name\n4. Keep each request within OpenRouter's 32,768-token context and send only fixed options, since the model is not intended for open-ended generation\n5. Measure latency and calibration on your own labelled cases before relying on Microsoft's latency and 'nine times out of 10' statements\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, Microsoft-Decision-1 or Vela 2.0?\n\nVela 2.0 scores 66.5 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category.\n\n### Which is cheaper for decision models, Microsoft-Decision-1 or Vela 2.0?\n\nMicrosoft-Decision-1, at free against free for Vela 2.0. These are the vendors' published prices for the job.\n\n### Do Microsoft-Decision-1 and Vela 2.0 need an API key?\n\nMicrosoft-Decision-1 takes an API key or an OAuth sign-in. Vela 2.0 needs no key.\n\n### Can an agent call Microsoft-Decision-1 and Vela 2.0 without installing anything?\n\nNo hosted endpoint is listed for Microsoft-Decision-1. No hosted endpoint is listed for Vela 2.0.\n\n### Are Microsoft-Decision-1 and Vela 2.0 open source?\n\nNo open-source release is listed for Microsoft-Decision-1. 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/microsoft-decision-1-vs-vela.json, and with the fewest tokens: https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"microsoft-decision-1\", \"b\": \"vela\"}`. From a terminal: `anchor compare microsoft-decision-1 vela`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.json and https://www.anchorterminal.com/api/v1/tools/vela.json\n\n## Other comparisons with Microsoft-Decision-1 or Vela 2.0\n\n- [Celeris-1 Decision vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-microsoft-decision-1.md)\n- [Celeris-1 Decision vs Vela 2.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.md)\n- [Clef vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1.md)\n- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)\n- [Laya vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1.md)\n- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)\n- [Decider vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decider-vs-microsoft-decision-1.md)\n- [Decider vs Vela 2.0](https://www.anchorterminal.com/compare/decider-vs-vela.md)\n- [GLiClass vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.md)\n- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)\n- [Kev vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-microsoft-decision-1.md)\n- [Kev vs Vela 2.0](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.md)\n- [Liquid d1 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1.md)\n- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-vs-vela.md)\n- [Microsoft-Decision-1 vs Drex 1.5](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex.md)\n- [Microsoft-Decision-1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-openai-decisions-api.md)\n- [Microsoft-Decision-1 vs pplx-decider](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-pplx-decider.md)\n- [Microsoft-Decision-1 vs Strands Decider 2B](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-strands-decider.md)\n- [Microsoft-Decision-1 vs Jev](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-typesafe-jev.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": "2026-10-10", "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": "Microsoft-Decision-1 vs Vela 2.0", "url": "" } ], "description": "Vela 2.0 scores 66.5 (B) to Microsoft-Decision-1's 39 (E) for decision models. Microsoft-Decision-1 is cheaper for decision models, $0 against $0 per 1M tokens. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Microsoft-Decision-1 E 39", "Vela 2.0 B 66.5", "scores" ], "h1": "Microsoft-Decision-1 vs Vela 2.0", "image": "https://www.anchorterminal.com/assets/og/compare-microsoft-decision-1-vs-vela.png", "path": "/compare/microsoft-decision-1-vs-vela", "published": "2026-10-01", "section": "tools", "title": "Microsoft-Decision-1 vs Vela 2.0 for AI agents (2026)", "toc": null, "updated": "2026-10-10", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-vela" }, "tokens": { "markdown": 2750, "slim": 630 }, "version": 1 }