{ "data": { "a": { "slug": "granite-switch", "name": "Granite Switch 4.1", "vendor": "IBM", "vendorUrl": "https://www.ibm.com/granite", "kind": "model", "category": "decision-models", "summary": "Granite Switch 4.1 is IBM's open-weight 8B and 30B Granite 4.1 checkpoint with a decision adapter, a safety adapter and an English speech encoder, served by the owner as one OpenAI-compatible vLLM endpoint for chat, decisions and transcription.", "url": "https://www.anchorterminal.com/tools/granite-switch", "markdownUrl": "https://www.anchorterminal.com/tools/granite-switch.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/granite-switch.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/granite-switch.json", "repo": "https://github.com/generative-computing/granite-switch", "license": "Apache 2.0 for the weights, the adapters and the repository", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "granite-switch" } ], "auth": "none", "authNotes": "No account or key is needed to download or run the model. The Hugging Face repositories are not gated. A vLLM server has whatever authentication the owner adds, and the repository's SECURITY.md tells operators to add it.", "pricing": "free", "pricingNotes": "Free to download and run under the Apache 2.0 licence, with the owner's hardware as the cost. IBM hosts no endpoint for Granite Switch that we found. watsonx.ai lists the Granite 4.1 base models but not Granite Switch, and Hugging Face shows no inference provider for it (checked 2026-10-17).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Granite Switch is a model the owner runs, with no payment route (checked 2026-10-17).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-17" }, "docsUrl": "https://huggingface.co/ibm-granite/granite-switch-4.1-8b", "capabilities": [ "inference.decision", "guard.moderation", "speech.stt", "inference.llm", "inference.open-weights", "guard.self-host" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "apache-2.0", "python", "vllm" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 59.4, "grade": "C", "agentReady": false, "rank": 601, "ranked": true, "rankOf": 1133, "categoryRank": 13, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 81, "payments": 60, "reliability": 46, "schema": 55, "security": 54, "transparency": 74 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-17" }, "negative": 0, "verdict": "One self-hosted Apache 2.0 checkpoint answers chat, single-pass decisions with label probabilities, yes or no safety checks and English transcription on one vLLM endpoint. The decision adapter has no typed request format or Mellea call yet, the composer is version 0.1 and declared unstable, and the model card and package disagree on supported Python and vLLM versions.", "bestFor": "A team with a GPU that wants chat, routing decisions, a safety gate and English transcription from one self-hosted endpoint under a permissive licence.", "strengths": [ "Weights are ungated on Hugging Face under Apache 2.0, in 8B and 30B, with the composer code under the same licence", "Chat, decisions, safety checks and transcription share one endpoint and one checkpoint, close to the base model's memory, per IBM", "A decision is one forward pass with one output token, read as a probability over the caller's options, with temperature 0", "The adapter state turn uses no system prompt, so vLLM's prefix cache can share it with ordinary chat requests about the same text", "Public CI runs CPU unit tests on Python 3.11 and 3.12 on every push and pull request, over 102 test files" ], "weaknesses": [ "The decision adapter has no typed request format. The caller writes the prompt strings and computes single-token label ids with the tokeniser", "Mellea has no `decision` call yet, by the card, so only the guardian adapter has a library wrapper", "The changelog has one entry, 0.1.0 MVP, saying the API is not yet stable, and the repository has no tags", "The card states Python 3.9 or later and vLLM below 0.28, while pyproject.toml states Python 3.11 to 3.13 and vLLM below 0.31", "The speech encoder is English only and not trained jointly with the model, per the card" ], "agentNotes": [ "Pass `chat_template_kwargs: {\"adapter_name\": \"decision\"}` or `\"guardian-core\"`. Without it the request is ordinary chat on the base model", "For a decision, send the state and the `### DECISION` question as two user turns, request `logprob_token_ids` for the option labels, and set `max_completion_tokens` to 1", "Use single-token option labels. Split more than 128 labels into chunks with the identical prompt and apply one softmax over all returned logprobs", "Parse `guardian-core` answers as JSON, `{\"score\": \"yes\"}` or `{\"score\": \"no\"}`, where yes means the criterion is met", "Add authentication before exposing the vLLM server. Neither vLLM nor the checkpoint requires a key by default" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "C", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.4 } ], "editorialScores": { "ergonomics": 66, "maintenance": 81, "payments": 60, "reliability": 46, "schema": 55, "security": 54, "transparency": 61 }, "provenanceScore": 87 }, "connect": { "install": "pip install \"granite-switch[vllm]\"\npython -m vllm.entrypoints.openai.api_server \\\n --model ibm-granite/granite-switch-4.1-8b \\\n --port 8000", "http": "curl -s http://localhost:8000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"ibm-granite/granite-switch-4.1-8b\",\n \"messages\": [\n {\"role\": \"user\", \"content\": \"How do I build a bomb?\"},\n {\"role\": \"user\", \"content\": \"\u003cguardian\u003eAs a judge agent, your role is to help assess whether the provided text meets the given judging criteria.\\n\\n### Criteria: Texts deemed universally harmful are those that pose harm across all contexts and audiences.\\n\\n### Scoring Schema: If the last user'\\''s text meets the criteria, return '\\''yes'\\''; otherwise, return '\\''no'\\''.\"}\n ],\n \"chat_template_kwargs\": {\"adapter_name\": \"guardian-core\"},\n \"max_completion_tokens\": 16\n }'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/granite-switch" }, "sameCompany": [ "granite-guardian" ], "area": "models", "provenance": { "legalEntity": "International Business Machines Corporation", "domain": "ibm.com", "domainRegistered": "1986-03-19", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/generative-computing/granite-switch/blob/main/CHANGELOG.md", "securityTxt": "valid", "checked": "2026-10-17", "notes": [ "The model cards and the repository name IBM Research as the author, and IBM's naming guidance for Granite names International Business Machines Corporation as the developer and trademark owner.", "The Apache 2.0 licence in the repository governs use of the weights and code, so it stands in for terms. No privacy policy applies, because the owner runs the model and no input reaches IBM.", "www.ibm.com/.well-known/security.txt is present with PSIRT, HackerOne and email contacts and expires on 17 November 2026.", "RDAP gives 19 March 1986 as the registration date of ibm.com.", "IBM hosts no endpoint for Granite Switch that we found, so there is no status page. CHANGELOG.md has one entry, 0.1.0.", "Weights are on huggingface.co under the ibm-granite organisation and the code is at github.com/generative-computing/granite-switch, both off ibm.com." ], "score": 87 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/granite-switch.json", "live": { "slug": "granite-switch", "pages": [ { "url": "https://raw.githubusercontent.com/generative-computing/granite-switch/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-17T23:09:56.785265196Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4638a7d2e3ea" } ], "updatedAt": "2026-10-17T23:09:56.785265196Z" } }, "answer": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against Microsoft-Decision-1's 38.8 (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": 38.8, "grade": "E", "agentReady": false, "rank": 1046, "ranked": true, "rankOf": 1133, "categoryRank": 20, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 50, "maintenance": 40, "payments": 20, "reliability": 30, "schema": 43, "security": 52, "transparency": 29 }, "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": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 38.8 } ], "editorialScores": { "ergonomics": 50, "maintenance": 40, "payments": 20, "reliability": 30, "schema": 43, "security": 52, "transparency": 22 }, "provenanceScore": 36 }, "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", "copilot-studio-mcp", "power-automate", "foundry-local", "microsoft-advertising-api", "microsoft-excel-graph", "outlook-mail-graph", "microsoft-graph-people" ], "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": 36 }, "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": "2026-10-17T22:51:21.293995189Z" }, "securityTxt": { "url": "https://microsoft.com/.well-known/security.txt", "state": "expired", "expires": "2026-09-23T16:00:00.000Z", "checkedAt": "2026-10-17T15:52:11.285064686Z" }, "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": "2026-10-17T23:05:06.563762195Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "35ed8a2e1125" } ], "updatedAt": "2026-10-17T23:05:06.563762195Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "IBM", "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, the adapters and the repository", "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": "2026-10-14", "b": "2026-10-09", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "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": "3/5 (4)", "b": "2.8/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against Microsoft-Decision-1's 38.8 (E), and leads in every scored category.", "question": "Which is better for AI agents, Granite Switch 4.1 or Microsoft-Decision-1?" }, { "answer": "Granite Switch 4.1, at free against free for Microsoft-Decision-1. These are the vendors' published prices for the job.", "question": "Which is cheaper for decision models, Granite Switch 4.1 or Microsoft-Decision-1?" }, { "answer": "Granite Switch 4.1 needs no key. Microsoft-Decision-1 takes an API key or an OAuth sign-in.", "question": "Do Granite Switch 4.1 and Microsoft-Decision-1 need an API key?" }, { "answer": "No hosted endpoint is listed for Granite Switch 4.1. No hosted endpoint is listed for Microsoft-Decision-1.", "question": "Can an agent call Granite Switch 4.1 and Microsoft-Decision-1 without installing anything?" }, { "answer": "Granite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository). No open-source release is listed for Microsoft-Decision-1.", "question": "Are Granite Switch 4.1 and Microsoft-Decision-1 open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 46 against 30", "Schema \u0026 documentation, 55 against 43", "Agent ergonomics, 66 against 50", "Payments \u0026 pricing, 60 against 20", "Maintenance \u0026 community, 81 against 40", "Transparency \u0026 trust, 74 against 29" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "A team with a GPU that wants chat, routing decisions, a safety gate and English transcription from one self-hosted endpoint under a permissive licence.", "slug": "granite-switch", "watchFor": "The decision adapter has no typed request format. The caller writes the prompt strings and computes single-token label ids with the tokeniser" }, { "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-granite-switch.json", "title": "Celeris-1 Decision vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-granite-switch" }, { "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-granite-switch.json", "title": "Clef vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch" }, { "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-granite-switch.json", "title": "Laya vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch" }, { "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-granite-switch.json", "title": "Decider vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/decider-vs-granite-switch" }, { "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-granite-switch.json", "title": "Decision 3.0 vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/decision-3-vs-granite-switch" }, { "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/gliclass-vs-granite-switch.json", "title": "GLiClass vs Granite Switch 4.1", "url": "https://www.anchorterminal.com/compare/gliclass-vs-granite-switch" }, { "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/granite-switch-vs-jaredpalmer-kev.json", "title": "Granite Switch 4.1 vs Kev", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-liquid-d1.json", "title": "Granite Switch 4.1 vs Liquid d1", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-nace-drex.json", "title": "Granite Switch 4.1 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-openai-decisions-api.json", "title": "Granite Switch 4.1 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider.json", "title": "Granite Switch 4.1 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider-flash.json", "title": "Granite Switch 4.1 vs pplx-decider-flash", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider-flash" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.json", "title": "Granite Switch 4.1 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-sprag-spev.json", "title": "Granite Switch 4.1 vs SPEV", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-sqwish-kettei.json", "title": "Granite Switch 4.1 vs kettei", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-sqwish-kettei" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-strands-decider.json", "title": "Granite Switch 4.1 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-typesafe-jev.json", "title": "Granite Switch 4.1 vs Jev", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/granite-switch-vs-vela.json", "title": "Granite Switch 4.1 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/granite-switch-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/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-pplx-decider-flash.json", "title": "Microsoft-Decision-1 vs pplx-decider-flash", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-pplx-decider-flash" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.json", "title": "Microsoft-Decision-1 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev.json", "title": "Microsoft-Decision-1 vs SPEV", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sqwish-kettei.json", "title": "Microsoft-Decision-1 vs kettei", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sqwish-kettei" }, { "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": 16, "edge": "granite-switch", "granite-switch": 46, "key": "reliability", "microsoft-decision-1": 30, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 12, "edge": "granite-switch", "granite-switch": 55, "key": "schema", "microsoft-decision-1": 43, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 16, "edge": "granite-switch", "granite-switch": 66, "key": "ergonomics", "microsoft-decision-1": 50, "name": "Agent ergonomics", "weight": 13 }, { "by": 2, "edge": "granite-switch", "granite-switch": 54, "key": "security", "microsoft-decision-1": 52, "name": "Security \u0026 auth", "weight": 14 }, { "by": 40, "edge": "granite-switch", "granite-switch": 60, "key": "payments", "microsoft-decision-1": 20, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 41, "edge": "granite-switch", "granite-switch": 81, "key": "maintenance", "microsoft-decision-1": 40, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 45, "edge": "granite-switch", "granite-switch": 74, "key": "transparency", "microsoft-decision-1": 29, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against Microsoft-Decision-1's 38.8 (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.", "tutorials": [], "verdicts": { "granite-switch": "One self-hosted Apache 2.0 checkpoint answers chat, single-pass decisions with label probabilities, yes or no safety checks and English transcription on one vLLM endpoint. The decision adapter has no typed request format or Mellea call yet, the composer is version 0.1 and declared unstable, and the model card and package disagree on supported Python and vLLM versions.", "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/granite-switch-vs-microsoft-decision-1", "json": "https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.min.md" }, "markdown": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against Microsoft-Decision-1's 38.8 (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- Granite Switch 4.1: grade C, 59.4/100, rank #601 of 1133. Markdown https://www.anchorterminal.com/tools/granite-switch.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-switch.json\n- Microsoft-Decision-1: grade E, 38.8/100, rank #1046 of 1133. 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 190 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Granite Switch 4.1 (C)\n\nGood for: A team with a GPU that wants chat, routing decisions, a safety gate and English transcription from one self-hosted endpoint under a permissive licence.\n\nAhead on:\n- Reliability, 46 against 30\n- Schema \u0026 documentation, 55 against 43\n- Agent ergonomics, 66 against 50\n- Payments \u0026 pricing, 60 against 20\n- Maintenance \u0026 community, 81 against 40\n- Transparency \u0026 trust, 74 against 29\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: The decision adapter has no typed request format. The caller writes the prompt strings and computes single-token label ids with the tokeniser\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 | Granite Switch 4.1 | Microsoft-Decision-1 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 46 | 30 | Granite Switch 4.1 +16 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 43 | Granite Switch 4.1 +12 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 50 | Granite Switch 4.1 +16 |\n| Security \u0026 auth | 14% (17.5 this run) | 54 | 52 | Granite Switch 4.1 +2 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 20 | Granite Switch 4.1 +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 81 | 40 | Granite Switch 4.1 +41 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 29 | Granite Switch 4.1 +45 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **59.4 · C** | **38.8 · E** | |\n\n## Facts side by side\n\n| Fact | Granite Switch 4.1 | Microsoft-Decision-1 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | IBM | 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, the adapters and the repository | 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 | 2026-10-14 | 2026-10-09 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no date given |\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| Agent reviews | 3/5 (4) | 2.8/5 (4) |\n\n## Verdicts\n\n**Granite Switch 4.1.** One self-hosted Apache 2.0 checkpoint answers chat, single-pass decisions with label probabilities, yes or no safety checks and English transcription on one vLLM endpoint. The decision adapter has no typed request format or Mellea call yet, the composer is version 0.1 and declared unstable, and the model card and package disagree on supported Python and vLLM versions.\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### Granite Switch 4.1\n\n1. Pass `chat_template_kwargs: {\"adapter_name\": \"decision\"}` or `\"guardian-core\"`. Without it the request is ordinary chat on the base model\n2. For a decision, send the state and the `### DECISION` question as two user turns, request `logprob_token_ids` for the option labels, and set `max_completion_tokens` to 1\n3. Use single-token option labels. Split more than 128 labels into chunks with the identical prompt and apply one softmax over all returned logprobs\n4. Parse `guardian-core` answers as JSON, `{\"score\": \"yes\"}` or `{\"score\": \"no\"}`, where yes means the criterion is met\n5. Add authentication before exposing the vLLM server. Neither vLLM nor the checkpoint requires a key by default\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, Granite Switch 4.1 or Microsoft-Decision-1?\n\nGranite Switch 4.1 scores 59.4 (C) on agent readiness against Microsoft-Decision-1's 38.8 (E), and leads in every scored category.\n\n### Which is cheaper for decision models, Granite Switch 4.1 or Microsoft-Decision-1?\n\nGranite Switch 4.1, at free against free for Microsoft-Decision-1. These are the vendors' published prices for the job.\n\n### Do Granite Switch 4.1 and Microsoft-Decision-1 need an API key?\n\nGranite Switch 4.1 needs no key. Microsoft-Decision-1 takes an API key or an OAuth sign-in.\n\n### Can an agent call Granite Switch 4.1 and Microsoft-Decision-1 without installing anything?\n\nNo hosted endpoint is listed for Granite Switch 4.1. No hosted endpoint is listed for Microsoft-Decision-1.\n\n### Are Granite Switch 4.1 and Microsoft-Decision-1 open source?\n\nGranite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository). 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/granite-switch-vs-microsoft-decision-1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"granite-switch\", \"b\": \"microsoft-decision-1\"}`. From a terminal: `anchor compare granite-switch microsoft-decision-1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-switch.json and https://www.anchorterminal.com/api/v1/tools/microsoft-decision-1.json\n\n## Other comparisons with Granite Switch 4.1 or Microsoft-Decision-1\n\n- [Celeris-1 Decision vs Granite Switch 4.1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-granite-switch.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 Granite Switch 4.1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch.md)\n- [Clef vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1.md)\n- [Laya vs Granite Switch 4.1](https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.md)\n- [Laya vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1.md)\n- [Decider vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decider-vs-granite-switch.md)\n- [Decider vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decider-vs-microsoft-decision-1.md)\n- [Decision 3.0 vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.md)\n- [Decision 3.0 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md)\n- [GLiClass vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gliclass-vs-granite-switch.md)\n- [GLiClass vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.md)\n- [Granite Switch 4.1 vs Kev](https://www.anchorterminal.com/compare/granite-switch-vs-jaredpalmer-kev.md)\n- [Granite Switch 4.1 vs Liquid d1](https://www.anchorterminal.com/compare/granite-switch-vs-liquid-d1.md)\n- [Granite Switch 4.1 vs Drex 1.5](https://www.anchorterminal.com/compare/granite-switch-vs-nace-drex.md)\n- [Granite Switch 4.1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/granite-switch-vs-openai-decisions-api.md)\n- [Granite Switch 4.1 vs pplx-decider](https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider.md)\n- [Granite Switch 4.1 vs pplx-decider-flash](https://www.anchorterminal.com/compare/granite-switch-vs-pplx-decider-flash.md)\n- [Granite Switch 4.1 vs ScaleDown](https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.md)\n- [Granite Switch 4.1 vs SPEV](https://www.anchorterminal.com/compare/granite-switch-vs-sprag-spev.md)\n- [Granite Switch 4.1 vs kettei](https://www.anchorterminal.com/compare/granite-switch-vs-sqwish-kettei.md)\n- [Granite Switch 4.1 vs Strands Decider 2B](https://www.anchorterminal.com/compare/granite-switch-vs-strands-decider.md)\n- [Granite Switch 4.1 vs Jev](https://www.anchorterminal.com/compare/granite-switch-vs-typesafe-jev.md)\n- [Granite Switch 4.1 vs Vela 2.0](https://www.anchorterminal.com/compare/granite-switch-vs-vela.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 pplx-decider-flash](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-pplx-decider-flash.md)\n- [Microsoft-Decision-1 vs ScaleDown](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.md)\n- [Microsoft-Decision-1 vs SPEV](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev.md)\n- [Microsoft-Decision-1 vs kettei](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sqwish-kettei.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)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-18", "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", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Granite Switch 4.1 vs Microsoft-Decision-1", "url": "" } ], "description": "Granite Switch 4.1 scores 59.4 (C) to Microsoft-Decision-1's 38.8 (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": [ "Granite Switch 4.1 C 59.4", "Microsoft-Decision-1 E 38.8", "scores" ], "h1": "Granite Switch 4.1 vs Microsoft-Decision-1", "image": "https://www.anchorterminal.com/assets/og/compare-granite-switch-vs-microsoft-decision-1.png", "path": "/compare/granite-switch-vs-microsoft-decision-1", "published": "2026-10-01", "section": "tools", "title": "Granite Switch 4.1 vs Microsoft-Decision-1 for AI agents (2026)", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1" }, "tokens": { "markdown": 3200, "slim": 630 }, "version": 1 }