{ "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 ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on schema \u0026 documentation and agent ergonomics.", "b": { "slug": "scaledown", "name": "ScaleDown", "vendor": "Carbon ScaleDown, Inc.", "vendorUrl": "https://scaledown.ai", "kind": "model", "category": "decision-models", "summary": "ScaleDown's API serves three single-task Constrained Decoding Models (Classify, Extract and Summarize) and a Compress model, called with an API key at api.scaledown.xyz. Classify answers Jev-shaped decision requests with probabilities.", "url": "https://www.anchorterminal.com/tools/scaledown", "markdownUrl": "https://www.anchorterminal.com/tools/scaledown.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/scaledown.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scaledown.json", "repo": "https://github.com/scaledown-team/langchain-scaledown", "license": "Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT", "transports": [ "http" ], "remoteUrl": "https://api.scaledown.xyz", "packages": [ { "registry": "pypi", "name": "langchain-scaledown" } ], "auth": "api-key", "authNotes": "An API key in the `x-api-key` header. Extract and Summarize on `/v1/chat/completions` also accept `Authorization: Bearer`, so an unmodified OpenAI SDK works by changing the base URL. Keys are made in the dashboard after sign-up at scaledown.ai/auth. We found no documentation of key scopes, expiry or rotation. An unauthenticated request returns 401 with `{\"detail\":\"x-api-key header is required\"}`.", "pricing": "usage", "pricingNotes": "$0.05 per million input tokens for every model, with output tokens free (https://scaledown.ai, FAQ). Classify's optional one-sentence reasoning bills its extra input tokens at 2x. New accounts get 50 million free tokens with no card, per the homepage. The docs introduction instead says to contact sales for a key. OpenRouter lists Extract and Summarize at $0.04 per million input tokens. Enterprise and self-hosted plans are priced by sales.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI document, the site or the LiteLLM and OpenRouter entries (checked 2026-10-14). Running out of credit returns 402 Payment Required as an ordinary error.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 0, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-14" }, "docsUrl": "https://docs.scaledown.ai/introduction", "llmsTxt": "https://docs.scaledown.ai/llms.txt", "openapi": "https://docs.scaledown.ai/api-reference/openapi.json", "capabilities": [ "inference.decision", "docs.extract" ], "tags": [ "hosted", "model", "closed-source", "openapi", "llms-txt", "openai-compatible", "usage-priced", "free-tier", "no-card", "python" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 48.6, "grade": "D", "agentReady": false, "rank": 917, "ranked": true, "rankOf": 1133, "categoryRank": 18, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 56, "payments": 40, "reliability": 20, "schema": 69, "security": 48, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-14" }, "negative": -2, "negativeNotes": [ "Conflicting compliance claims on ScaleDown's own pages, read 14 October 2026. The DPA (20 July 2026) says ScaleDown maintains a SOC 2 Type II attestation and ISO 27001 certification, the homepage shows SOC 2 Type 1, HIPAA and ISO 27001 badges, and llms.txt says GDPR, HIPAA and SOC 2 compliance is in progress. At least one is wrong. No report or trust centre found to settle it (-2) (https://scaledown.ai/dpa, https://scaledown.ai/llms.txt)" ], "verdict": "Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.", "bestFor": "Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.", "strengths": [ "`POST /v1/scaledown` takes Jev's request shape, so a Jev integration can move by changing the base URL, per the docs", "$0.05 per million input tokens for every model, output free, and 50 million free tokens with no card, per the homepage", "Extract returns each value with a confidence, character offsets and surrounding context, and routes `enum` fields to the Classify model", "llms.txt with Markdown twins, an OpenAPI 3.1 document and OpenAI-compatible chat completions for Extract and Summarize", "The terms, DPA and FAQ agree that customer data isn't used for training, and the DPA lists four US subprocessors" ], "weaknesses": [ "No status page, no published rate limits and no SLA outside enterprise contracts", "No public changelog. The docs dropped the native /extract and /summarization endpoints from the reference on 13 October 2026", "Compliance claims disagree between the DPA (SOC 2 Type II, ISO 27001), the homepage badges (SOC 2 Type 1) and llms.txt (in progress)", "No security.txt, disclosure policy or bug bounty, and no guidance on hostile text in classified input", "The OpenAPI document covers /classify, /v1/scaledown and Compress only, without the documented limits" ], "agentNotes": [ "Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed", "Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases", "Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side", "Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x", "Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 48.6 } ], "editorialScores": { "ergonomics": 76, "maintenance": 56, "payments": 40, "reliability": 20, "schema": 69, "security": 48, "transparency": 56 }, "provenanceScore": 52 }, "connect": { "install": "pip install langchain-scaledown # LangChain middleware; any OpenAI SDK also works against /v1/chat/completions", "http": "curl https://api.scaledown.xyz/v1/scaledown \\\n -H \"x-api-key: $SCALEDOWN_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"classify-1\",\"state\":\"I was charged twice for my subscription this month.\",\"questions\":{\"category\":{\"type\":\"choice\",\"criteria\":{\"billing\":\"About a charge, invoice, refund, or payment problem.\",\"technical\":\"About a bug or something not working.\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/scaledown" }, "alsoIn": [ "document-extraction" ], "area": "models", "unitPrices": [ { "item": "Classify, Extract, Summarize and Compress input", "unit": "1m-tokens", "usd": 0.05, "note": "Output tokens free. Classify reasoning input billed at 2x. 50M free tokens for new accounts" } ], "provenance": { "legalEntity": "Carbon ScaleDown, Inc.", "domain": "scaledown.ai", "domainRegistered": "2025-03-28", "endpointOnVendorDomain": true, "terms": "https://scaledown.ai/terms", "privacy": "https://scaledown.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-14", "notes": [ "The terms (last updated 20 July 2026), privacy notice (3 June 2026) and DPA (20 July 2026) name Carbon ScaleDown, Inc., 22952 Stokes Rd, Ramona, CA 92065, and Delaware law. One sentence of the terms names ScaleDown, Inc.", "scaledown.ai is a single-page app. /terms, /privacy and /dpa answer HTTP 404 with the app shell, and their text is in the JavaScript bundle (https://scaledown.ai/assets/index-CIrIjse9.js), where we read it.", "The API host is api.scaledown.xyz. scaledown.xyz redirects to scaledown.ai, so we treat the endpoint as on the vendor's domain.", "scaledown.ai/.well-known/security.txt and docs.scaledown.ai/.well-known/security.txt return 404. status.scaledown.ai and status.scaledown.xyz don't resolve.", "No public changelog. The docs source at github.com/scaledown-team/docs has dated commits that record API changes.", "RDAP gives scaledown.ai a registration date of 28 March 2025." ], "score": 52 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/scaledown.json", "live": { "slug": "scaledown", "probe": { "target": "https://api.scaledown.xyz", "method": "get", "lastAt": "2026-10-18T00:31:06.203006924Z", "lastOk": true, "lastStatus": 403, "lastMs": 271, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 263, "p95ms24h": 325, "samples24h": 253, "samples30d": 811, "days": [ { "date": "2026-10-14", "probes": 47, "ok": 47 }, { "date": "2026-10-15", "probes": 253, "ok": 253 }, { "date": "2026-10-16", "probes": 252, "ok": 252 }, { "date": "2026-10-17", "probes": 253, "ok": 253 }, { "date": "2026-10-18", "probes": 6, "ok": 6 } ] }, "versions": [ { "registry": "pypi", "name": "langchain-scaledown", "version": "0.2.0", "released": "2026-10-12", "seenAt": "2026-10-17T02:15:43.866175969Z" } ], "githubStars": 0, "pypiWeekly": 292, "securityTxt": { "url": "https://scaledown.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-17T15:52:20.915283697Z" }, "llmsTxt": { "url": "https://docs.scaledown.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-17T14:23:10.857281738Z" }, "pages": [ { "url": "https://scaledown.ai/privacy", "kind": "privacy", "status": 404, "checkedAt": "2026-10-17T23:09:25.223499381Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://scaledown.ai/terms", "kind": "terms", "status": 404, "checkedAt": "2026-10-17T23:09:27.6171155Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-18T00:31:06.203006924Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "IBM", "b": "Carbon ScaleDown, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.scaledown.xyz", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache 2.0 for the weights, the adapters and the repository", "b": "Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-14", "b": "2026-10-14", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "0 stars", "name": "Popularity" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on schema \u0026 documentation and agent ergonomics.", "question": "Which is better for AI agents, Granite Switch 4.1 or ScaleDown?" }, { "answer": "Granite Switch 4.1 needs no key. ScaleDown needs an API key.", "question": "Do Granite Switch 4.1 and ScaleDown need an API key?" }, { "answer": "No hosted endpoint is listed for Granite Switch 4.1. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.", "question": "Can an agent call Granite Switch 4.1 and ScaleDown 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 ScaleDown.", "question": "Are Granite Switch 4.1 and ScaleDown open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 46 against 20", "Security \u0026 auth, 54 against 48", "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 81 against 56", "Transparency \u0026 trust, 74 against 54" ], "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": [ "Schema \u0026 documentation, 69 against 55", "Agent ergonomics, 76 against 66" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.", "slug": "scaledown", "watchFor": "No status page, no published rate limits and no SLA outside enterprise contracts" } ], "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-scaledown.json", "title": "Celeris-1 Decision vs ScaleDown", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown" }, { "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-scaledown.json", "title": "Clef vs ScaleDown", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown" }, { "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-scaledown.json", "title": "Laya vs ScaleDown", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-scaledown" }, { "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-scaledown.json", "title": "Decider vs ScaleDown", "url": "https://www.anchorterminal.com/compare/decider-vs-scaledown" }, { "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-scaledown.json", "title": "Decision 3.0 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/decision-3-vs-scaledown" }, { "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-scaledown.json", "title": "GLiClass vs ScaleDown", "url": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown" }, { "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-microsoft-decision-1.json", "title": "Granite Switch 4.1 vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1" }, { "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-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-scaledown.json", "title": "Kev vs ScaleDown", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown.json", "title": "Liquid d1 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown" }, { "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/nace-drex-vs-scaledown.json", "title": "Drex 1.5 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown.json", "title": "OpenAI Decisions API vs ScaleDown", "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-flash-vs-scaledown.json", "title": "pplx-decider-flash vs ScaleDown", "url": "https://www.anchorterminal.com/compare/pplx-decider-flash-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown.json", "title": "pplx-decider vs ScaleDown", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.json", "title": "ScaleDown vs SPEV", "url": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.json", "title": "ScaleDown vs kettei", "url": "https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-strands-decider.json", "title": "ScaleDown vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/scaledown-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev.json", "title": "ScaleDown vs Jev", "url": "https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-vela.json", "title": "ScaleDown vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/scaledown-vs-vela" } ], "scores": [ { "by": 26, "edge": "granite-switch", "granite-switch": 46, "key": "reliability", "name": "Reliability", "scaledown": 20, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 14, "edge": "scaledown", "granite-switch": 55, "key": "schema", "name": "Schema \u0026 documentation", "scaledown": 69, "weight": 13 }, { "by": 10, "edge": "scaledown", "granite-switch": 66, "key": "ergonomics", "name": "Agent ergonomics", "scaledown": 76, "weight": 13 }, { "by": 6, "edge": "granite-switch", "granite-switch": 54, "key": "security", "name": "Security \u0026 auth", "scaledown": 48, "weight": 14 }, { "by": 20, "edge": "granite-switch", "granite-switch": 60, "key": "payments", "name": "Payments \u0026 pricing", "scaledown": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 25, "edge": "granite-switch", "granite-switch": 81, "key": "maintenance", "name": "Maintenance \u0026 community", "scaledown": 56, "weight": 7 }, { "by": 20, "edge": "granite-switch", "granite-switch": 74, "key": "transparency", "name": "Transparency \u0026 trust", "scaledown": 54, "weight": 7 } ], "summary": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on schema \u0026 documentation and agent ergonomics. Both do decision models.", "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.", "scaledown": "Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown", "json": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.min.md" }, "markdown": "Granite Switch 4.1 scores 59.4 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on schema \u0026 documentation and agent ergonomics. Both do decision models.\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- ScaleDown: grade D, 48.6/100, rank #917 of 1133. Markdown https://www.anchorterminal.com/tools/scaledown.md · JSON https://www.anchorterminal.com/api/v1/tools/scaledown.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- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md\n- All 128 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/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 20\n- Security \u0026 auth, 54 against 48\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 81 against 56\n- Transparency \u0026 trust, 74 against 54\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### ScaleDown (D)\n\nGood for: Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.\n\nAhead on:\n- Schema \u0026 documentation, 69 against 55\n- Agent ergonomics, 76 against 66\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: No status page, no published rate limits and no SLA outside enterprise contracts\n\n\n## Score by category\n\n| Category | Weight | Granite Switch 4.1 | ScaleDown | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 46 | 20 | Granite Switch 4.1 +26 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 69 | ScaleDown +14 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 76 | ScaleDown +10 |\n| Security \u0026 auth | 14% (17.5 this run) | 54 | 48 | Granite Switch 4.1 +6 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | Granite Switch 4.1 +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 81 | 56 | Granite Switch 4.1 +25 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 74 | 54 | Granite Switch 4.1 +20 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **59.4 · C** | **48.6 · D** | |\n\n## Facts side by side\n\n| Fact | Granite Switch 4.1 | ScaleDown |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | IBM | Carbon ScaleDown, Inc. |\n| Hosted endpoint | no (local only) | `https://api.scaledown.xyz` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Apache 2.0 for the weights, the adapters and the repository | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-14 | 2026-10-14 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | none | 0 stars |\n| Agent reviews | 3/5 (4) | none |\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**ScaleDown.** Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.\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### ScaleDown\n\n1. Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed\n2. Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases\n3. Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side\n4. Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x\n5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects\n\n## Questions\n\n### Which is better for AI agents, Granite Switch 4.1 or ScaleDown?\n\nGranite Switch 4.1 scores 59.4 (C) on agent readiness against ScaleDown's 48.6 (D), and leads in 5 of 7 scored categories. ScaleDown leads on schema \u0026 documentation and agent ergonomics.\n\n### Do Granite Switch 4.1 and ScaleDown need an API key?\n\nGranite Switch 4.1 needs no key. ScaleDown needs an API key.\n\n### Can an agent call Granite Switch 4.1 and ScaleDown without installing anything?\n\nNo hosted endpoint is listed for Granite Switch 4.1. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.\n\n### Are Granite Switch 4.1 and ScaleDown 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 ScaleDown.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-switch-vs-scaledown.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"granite-switch\", \"b\": \"scaledown\"}`. From a terminal: `anchor compare granite-switch scaledown`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-switch.json and https://www.anchorterminal.com/api/v1/tools/scaledown.json\n\n## Other comparisons with Granite Switch 4.1 or ScaleDown\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 ScaleDown](https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown.md)\n- [Clef vs Granite Switch 4.1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch.md)\n- [Clef vs ScaleDown](https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown.md)\n- [Laya vs Granite Switch 4.1](https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.md)\n- [Laya vs ScaleDown](https://www.anchorterminal.com/compare/convai-laya-vs-scaledown.md)\n- [Decider vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decider-vs-granite-switch.md)\n- [Decider vs ScaleDown](https://www.anchorterminal.com/compare/decider-vs-scaledown.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 ScaleDown](https://www.anchorterminal.com/compare/decision-3-vs-scaledown.md)\n- [GLiClass vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gliclass-vs-granite-switch.md)\n- [GLiClass vs ScaleDown](https://www.anchorterminal.com/compare/gliclass-vs-scaledown.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 Microsoft-Decision-1](https://www.anchorterminal.com/compare/granite-switch-vs-microsoft-decision-1.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 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 ScaleDown](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown.md)\n- [Liquid d1 vs ScaleDown](https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown.md)\n- [Microsoft-Decision-1 vs ScaleDown](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.md)\n- [Drex 1.5 vs ScaleDown](https://www.anchorterminal.com/compare/nace-drex-vs-scaledown.md)\n- [OpenAI Decisions API vs ScaleDown](https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown.md)\n- [pplx-decider-flash vs ScaleDown](https://www.anchorterminal.com/compare/pplx-decider-flash-vs-scaledown.md)\n- [pplx-decider vs ScaleDown](https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown.md)\n- [ScaleDown vs SPEV](https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.md)\n- [ScaleDown vs kettei](https://www.anchorterminal.com/compare/scaledown-vs-sqwish-kettei.md)\n- [ScaleDown vs Strands Decider 2B](https://www.anchorterminal.com/compare/scaledown-vs-strands-decider.md)\n- [ScaleDown vs Jev](https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev.md)\n- [ScaleDown vs Vela 2.0](https://www.anchorterminal.com/compare/scaledown-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 ScaleDown", "url": "" } ], "description": "Granite Switch 4.1 scores 59.4 (C) to ScaleDown's 48.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Granite Switch 4.1 C 59.4", "ScaleDown D 48.6", "scores" ], "h1": "Granite Switch 4.1 vs ScaleDown", "image": "https://www.anchorterminal.com/assets/og/compare-granite-switch-vs-scaledown.png", "path": "/compare/granite-switch-vs-scaledown", "published": "2026-10-01", "section": "tools", "title": "Granite Switch 4.1 vs ScaleDown for AI agents (2026) | Anchor Terminal", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-scaledown" }, "tokens": { "markdown": 3000, "slim": 730 }, "version": 1 }