{ "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": "Decision 3.0 scores 63.1 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category.", "b": { "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": 931, "ranked": true, "rankOf": 965, "categoryRank": 15, "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": "2026-10-12T03:24:34.021691121Z" }, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "expired", "expires": "2026-09-23T16:00:00.000Z", "checkedAt": "2026-10-11T15:42:16.059753534Z" }, "domain": { "domain": "microsoft.com", "registered": "1991-05-02", "source": "https://rdap.verisign.com/com/v1/domain/microsoft.com", "checkedAt": "2026-10-11T13:11:44.704195317Z" }, "pages": [ { "url": "https://learn.microsoft.com/en-us/azure/ai-foundry/responsible-ai/openai/data-privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-11T19:29:31.570586454Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "35ed8a2e1125" } ], "updatedAt": "2026-10-12T03:24:34.021691121Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "vLLM Semantic Router Team", "b": "Microsoft", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "free", "b": "free", "name": "Price for decision models" }, { "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": "Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found.", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-11", "b": "2026-10-09", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "", "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" } ], "faq": [ { "answer": "Decision 3.0 scores 63.1 (B) on agent readiness against Microsoft-Decision-1's 39 (E), and leads in every scored category.", "question": "Which is better for AI agents, Decision 3.0 or Microsoft-Decision-1?" }, { "answer": "Decision 3.0, at free against free for Microsoft-Decision-1. These are the vendors' published prices for the job.", "question": "Which is cheaper for decision models, Decision 3.0 or Microsoft-Decision-1?" }, { "answer": "Decision 3.0 needs no key. Microsoft-Decision-1 takes an API key or an OAuth sign-in.", "question": "Do Decision 3.0 and Microsoft-Decision-1 need an API key?" }, { "answer": "No hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Microsoft-Decision-1.", "question": "Can an agent call Decision 3.0 and Microsoft-Decision-1 without installing anything?" }, { "answer": "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). No open-source release is listed for Microsoft-Decision-1.", "question": "Are Decision 3.0 and Microsoft-Decision-1 open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 58 against 30", "Schema \u0026 documentation, 70 against 43", "Agent ergonomics, 72 against 50", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 82 against 40", "Transparency \u0026 trust, 45 against 32" ], "also": [ "No key needed to call it", "Open source" ], "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": 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" } ], "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-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/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-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/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-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/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-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/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-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/decision-3-vs-vela.json", "title": "Decision 3.0 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/decision-3-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/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/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/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/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" } ], "scores": [ { "by": 28, "decision-3": 58, "edge": "decision-3", "key": "reliability", "microsoft-decision-1": 30, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 27, "decision-3": 70, "edge": "decision-3", "key": "schema", "microsoft-decision-1": 43, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 22, "decision-3": 72, "edge": "decision-3", "key": "ergonomics", "microsoft-decision-1": 50, "name": "Agent ergonomics", "weight": 13 }, { "by": 4, "decision-3": 56, "edge": "decision-3", "key": "security", "microsoft-decision-1": 52, "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "decision-3": 60, "edge": "decision-3", "key": "payments", "microsoft-decision-1": 20, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 42, "decision-3": 82, "edge": "decision-3", "key": "maintenance", "microsoft-decision-1": 40, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 13, "decision-3": 45, "edge": "decision-3", "key": "transparency", "microsoft-decision-1": 32, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Decision 3.0 scores 63.1 (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": { "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.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1", "json": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md", "slim": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.min.md" }, "markdown": "Decision 3.0 scores 63.1 (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- 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- Microsoft-Decision-1: grade E, 39/100, rank #931 of 965. Markdown https://www.anchorterminal.com/tools/microsoft-decision-1.md · JSON https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.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\nAhead on:\n- Reliability, 58 against 30\n- Schema \u0026 documentation, 70 against 43\n- Agent ergonomics, 72 against 50\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 82 against 40\n- Transparency \u0026 trust, 45 against 32\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Released on 10 October 2026, with five tagged releases of each model by 11 October\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\n## Score by category\n\n| Category | Weight | Decision 3.0 | Microsoft-Decision-1 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 58 | 30 | Decision 3.0 +28 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 43 | Decision 3.0 +27 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 50 | Decision 3.0 +22 |\n| Security \u0026 auth | 14% (17.5 this run) | 56 | 52 | Decision 3.0 +4 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Decision 3.0 +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 40 | Decision 3.0 +42 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 32 | Decision 3.0 +13 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **63.1 · B** | **39 · E** | |\n\n## Facts side by side\n\n| Fact | Decision 3.0 | Microsoft-Decision-1 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | vLLM Semantic Router Team | Microsoft |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Pay per use |\n| Price for decision models | 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 | Not stated. The announcement and OpenRouter's model page name no licence, and no weights repository was found. |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-11 | 2026-10-09 |\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\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**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## 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### 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## Questions\n\n### Which is better for AI agents, Decision 3.0 or Microsoft-Decision-1?\n\nDecision 3.0 scores 63.1 (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, Decision 3.0 or Microsoft-Decision-1?\n\nDecision 3.0, at free against free for Microsoft-Decision-1. These are the vendors' published prices for the job.\n\n### Do Decision 3.0 and Microsoft-Decision-1 need an API key?\n\nDecision 3.0 needs no key. Microsoft-Decision-1 takes an API key or an OAuth sign-in.\n\n### Can an agent call Decision 3.0 and Microsoft-Decision-1 without installing anything?\n\nNo hosted endpoint is listed for Decision 3.0. No hosted endpoint is listed for Microsoft-Decision-1.\n\n### Are Decision 3.0 and Microsoft-Decision-1 open source?\n\nDecision 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). No open-source release is listed for Microsoft-Decision-1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"decision-3\", \"b\": \"microsoft-decision-1\"}`. From a terminal: `anchor compare decision-3 microsoft-decision-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.json\n\n## Other comparisons with Decision 3.0 or Microsoft-Decision-1\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 Microsoft-Decision-1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-microsoft-decision-1.md)\n- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)\n- [Clef vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decider vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decider-vs-microsoft-decision-1.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 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- [Decision 3.0 vs Vela 2.0](https://www.anchorterminal.com/compare/decision-3-vs-vela.md)\n- [GLiClass vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.md)\n- [Kev vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-microsoft-decision-1.md)\n- [Liquid d1 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1.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- [Microsoft-Decision-1 vs Vela 2.0](https://www.anchorterminal.com/compare/microsoft-decision-1-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 Microsoft-Decision-1", "url": "" } ], "description": "Decision 3.0 scores 63.1 (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": [ "Decision 3.0 B 63.1", "Microsoft-Decision-1 E 39", "scores" ], "h1": "Decision 3.0 vs Microsoft-Decision-1", "image": "https://www.anchorterminal.com/assets/og/compare-decision-3-vs-microsoft-decision-1.png", "path": "/compare/decision-3-vs-microsoft-decision-1", "published": "2026-10-01", "section": "tools", "title": "Decision 3.0 vs Microsoft-Decision-1 for AI agents (2026)", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1" }, "tokens": { "markdown": 2750, "slim": 630 }, "version": 1 }