{ "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": 59.5, "grade": "C", "agentReady": false, "rank": 639, "ranked": true, "rankOf": 1244, "categoryRank": 14, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 66, "maintenance": 81, "payments": 60, "reliability": 46, "schema": 55, "security": 54, "transparency": 75 }, "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": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 59.5 } ], "editorialScores": { "ergonomics": 66, "maintenance": 81, "payments": 60, "reliability": 46, "schema": 55, "security": 54, "transparency": 61 }, "provenanceScore": 88, "checked": { "categories": { "ergonomics": "2026-10-17", "maintenance": "2026-10-17", "payments": "2026-10-17", "reliability": "2026-10-17", "schema": "2026-10-17", "security": "2026-10-17", "transparency": "2026-10-17" }, "last": "2026-10-17", "lastMoved": "2026-10-28", "oldest": "2026-10-17", "stale": false, "staleAfterDays": 90 } }, "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-embedding-small-english-r2", "granite-guardian", "granite-4-2-3b" ], "family": { "lab": "IBM (Granite)", "family": "Granite Switch", "url": "https://www.anchorterminal.com/open-weights/#ibm", "others": [ { "name": "granite-switch-4.1-8b", "url": "https://huggingface.co/ibm-granite/granite-switch-4.1-8b", "params": "8B (Hub safetensors count 8.78B)", "listing": "https://www.anchorterminal.com/tools/granite-switch" }, { "name": "granite-switch-4.1-8b-preview", "url": "https://huggingface.co/ibm-granite/granite-switch-4.1-8b-preview", "params": "8B (Hub safetensors count 9.57B)" }, { "name": "granite-switch-4.1-3b-preview", "url": "https://huggingface.co/ibm-granite/granite-switch-4.1-3b-preview", "params": "3B (Hub safetensors count 4.15B)" }, { "name": "granite-switch-4.1-30b-preview", "url": "https://huggingface.co/ibm-granite/granite-switch-4.1-30b-preview", "params": "30B (Hub safetensors count 32.24B)" } ], "olderCount": 64 }, "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": 88 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/granite-switch.json", "live": { "slug": "granite-switch", "versions": [ { "registry": "pypi", "name": "granite-switch", "version": "0.1.1", "released": "2026-10-15", "seenAt": "2026-10-30T14:17:00.365045692Z" } ], "githubStars": 119, "pypiWeekly": 580, "securityTxt": { "url": "https://ibm.com/.well-known/security.txt", "state": "valid", "expires": "2026-11-30T00:00:00+00:00", "checkedAt": "2026-10-30T15:38:23.13721203Z" }, "domain": { "domain": "ibm.com", "registered": "1986-03-19", "source": "https://rdap.verisign.com/com/v1/domain/ibm.com", "checkedAt": "2026-10-25T14:03:33.422073312Z" }, "pages": [ { "url": "https://raw.githubusercontent.com/generative-computing/granite-switch/main/CHANGELOG.md", "kind": "changelog", "status": 304, "checkedAt": "2026-10-30T05:48:53.472146927Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4638a7d2e3ea" } ], "github": { "repo": "generative-computing/granite-switch", "checkedAt": "2026-10-26T07:29:14.825940483Z", "stars": 115, "archived": false, "issuesEnabled": true, "pushedAt": "2026-10-25T20:06:29Z", "openIssues": 23, "openPRs": 13, "issuesOpened90d": 10, "issuesClosed90d": 3, "prsMerged90d": 18, "ci": { "branch": "main", "runs": 15, "success": 14, "failure": 1, "other": 0, "latest": "success", "latestAt": "2026-10-25T14:01:04Z" }, "replies": { "sampled": 25, "unanswered": 13, "medianDays": 0.9 } }, "updatedAt": "2026-10-30T15:38:23.13721203Z" } }, "answer": "RightNow System Zero scores 66.8 (B) on agent readiness against Granite Switch 4.1's 59.5 (C), and leads in 4 of 7 scored categories. Granite Switch 4.1 leads on payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.", "b": { "slug": "rightnow-system-zero", "name": "RightNow System Zero", "vendor": "RightNow AI, Inc.", "vendorUrl": "https://www.rightnowai.co", "kind": "model", "category": "decision-models", "summary": "RightNow System Zero is a hosted, closed-weight decision model from RightNow AI, Inc. It answers boolean, choice and score questions about text, JSON, images, WAV audio and PDFs with per-option probabilities, over HTTP or a WebSocket stream.", "url": "https://www.anchorterminal.com/tools/rightnow-system-zero", "markdownUrl": "https://www.anchorterminal.com/tools/rightnow-system-zero.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/rightnow-system-zero.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/rightnow-system-zero.json", "repo": "https://github.com/RightNow-AI/system-zero-sdk", "license": "Proprietary hosted model under RightNow AI terms of use; the SDKs are Apache-2.0", "transports": [ "http", "websocket" ], "remoteUrl": "https://api.rightnowai.co/v1/system-zero/decide", "packages": [ { "registry": "npm", "name": "@rightnowai/system-zero" }, { "registry": "pypi", "name": "rightnow-system-zero" } ], "auth": "api-key", "authNotes": "Bearer workspace API key in the Authorization header, created in the console after signing in with Google, GitHub or email and passing a human check. Keys are shown once, revocable and unscoped. HTTPS and server side only, and the stream authenticates on the WebSocket upgrade. A call without a key returns 401 invalid_api_key.", "pricing": "usage", "pricingNotes": "Prepaid credit at USD 0.19 per million uncached text tokens (USD 0.019 cached), USD 0.00013 per answered question and USD 0.000055 per answered call, with output free and separate image, audio, PDF and preview video fees (price card G, 27 October 2026). USD 5 of starting credit per verified email, with eligibility checks and no card. Top-ups start at USD 5 and purchased credit expires after 12 months. Refused questions aren't charged.", "priceSummary": "$0.0001 / tx", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, OpenAPI file or SDKs read on 31 October 2026. HTTP 402 insufficient_credits means the workspace's prepaid balance doesn't cover the call.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-31" }, "docsUrl": "https://www.rightnowai.co/docs/system-zero", "llmsTxt": "https://www.rightnowai.co/llms.txt", "openapi": "https://raw.githubusercontent.com/RightNow-AI/system-zero-sdk/main/openapi.json", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "closed-source", "multimodal", "streaming", "websocket", "llms-txt", "openapi", "typescript", "python", "usage-priced", "prepaid", "no-card", "security-txt", "new" ], "lastRelease": "2026-10-27", "graded": true, "anchor": { "graded": true, "score": 66.8, "grade": "B", "agentReady": false, "rank": 320, "ranked": true, "rankOf": 1244, "categoryRank": 9, "methodology": "0.7", "run": "2026-10-01", "scores": { "ergonomics": 86, "maintenance": 68, "payments": 40, "reliability": 50, "schema": 83, "security": 70, "transparency": 70 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-31" }, "negative": 0, "verdict": "A well-documented decision API with an OpenAPI file, idempotent retries, a detailed error catalogue, streaming over WebSocket and published per-unit prices with USD 5 of starting credit. Standard context is 38,000 tokens; the 64k, 128k and 1M bands are held and video is a preview. The latency and benchmark figures are RightNow's own, and several of its pages disagree.", "bestFor": "Typed decisions with per-option probabilities over text, JSON, images, audio and PDFs, including on streaming state", "strengths": [ "Boolean, choice and score questions, up to 1,024 a call, answered with a probability per option and no output charge", "An OpenAPI 3.1.0 file, llms.txt, Markdown docs and an error catalogue with a retry flag on every code", "Idempotency keys with stored replays for up to 24 hours, used by default in the official TypeScript and Python SDKs", "A server-side WebSocket stream returns decisions tagged with the state version they cover", "Per-unit prices published without a login, and USD 5 of starting credit with no card" ], "weaknesses": [ "Standard context is 38,000 tokens. The 64k, 128k and 1M bands are held, and video is a preview", "The status page's robots.txt disallows every path, and no SLA applies without a signed agreement", "Answers carry calibrated false in this release, so the probabilities aren't calibrated", "RightNow's pages disagree on audio formats, option counts, input kinds, starting-credit expiry and whether billing is open", "Latency and benchmark figures are RightNow's own, and the benchmark row is labelled 3.0.0 while the served model is 2.0.0" ], "agentNotes": [ "Send audio only as inline 16,000 Hz WAV. The FLAC, MP3, OGG and MP4 audio named on the blog are refused with media_unsupported.", "Keep state under 38,000 tokens. Long-context requests return 404 long_context_not_available, which never succeeds on retry.", "Reuse the same Idempotency-Key and body on retries, and stop when error.retryable or x-should-retry is false.", "Check every entry in answers even on HTTP 200, since one question can be refused while the others are answered.", "Treat probabilities as uncalibrated while calibrated is false, and pin system-zero-2.0.0 when answers must not move with the alias." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 66.8 } ], "editorialScores": { "ergonomics": 86, "maintenance": 68, "payments": 40, "reliability": 50, "schema": 83, "security": 70, "transparency": 55 }, "provenanceScore": 84, "checked": { "categories": { "ergonomics": "2026-10-31", "maintenance": "2026-10-31", "payments": "2026-10-31", "reliability": "2026-10-31", "schema": "2026-10-31", "security": "2026-10-31", "transparency": "2026-10-31" }, "last": "2026-10-31", "oldest": "2026-10-31", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "npm install @rightnowai/system-zero@0.4.2", "http": "curl https://api.rightnowai.co/v1/system-zero/decide \\\n -H \"Authorization: Bearer $SYSTEM_ZERO_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"system-zero\",\"state\":\"The blender I ordered arrived with a cracked jar.\",\"questions\":{\"damaged\":{\"type\":\"boolean\",\"instructions\":\"Did the item arrive damaged?\"}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/rightnow-system-zero" }, "area": "models", "unitPrices": [ { "item": "Uncached text input", "unit": "1m-tokens", "usd": 0.19, "note": "Price card G, 27 October 2026. Output tokens are free." }, { "item": "Cached text input", "unit": "1m-tokens", "usd": 0.019, "note": "Automatic caching, optional prompt_cache_key." }, { "item": "Answered question", "unit": "tx", "usd": 0.00013, "note": "Refused questions aren't charged." }, { "item": "Answered call fee", "unit": "call", "usd": 0.000055, "note": "Once per call with at least one answered question." }, { "item": "Image input", "unit": "image", "usd": 0.011, "note": "PNG or JPEG, up to 4 a call." }, { "item": "Audio input", "unit": "audio-minute", "usd": 0.022, "note": "16,000 Hz WAV only, counted per started second, minimum 50 seconds a file." }, { "item": "PDF input", "unit": "1k-pages", "usd": 11, "note": "USD 0.011 a page, minimum USD 0.0055 a file, up to 500 pages." }, { "item": "Video input (preview)", "unit": "video-second", "usd": 0.0018, "note": "Preview. Minimum USD 0.018 a file, up to 10 seconds." } ], "provenance": { "legalEntity": "RightNow AI, Inc.", "domain": "rightnowai.co", "domainRegistered": "2025-02-11", "endpointOnVendorDomain": true, "terms": "https://www.rightnowai.co/terms-of-use", "privacy": "https://www.rightnowai.co/privacy-policy", "statusPage": "https://status.rightnowai.co", "changelog": "https://www.rightnowai.co/docs/system-zero/release-notes", "securityTxt": "valid", "checked": "2026-10-31", "notes": [ "The terms (version terms-2026-10-28-free5) and privacy policy (privacy-2026-10-28-free5) name RightNow AI, Inc., registered in Delaware at 131 Continental Dr, Newark, DE 19713, under Delaware law.", "RDAP at rdap.registry.co gives a registration date of 2025-02-11 for rightnowai.co.", "status.rightnowai.co is linked from the docs and footer and named in the privacy policy, but its robots.txt disallows every path, so its components and incident history were not read.", "security.txt at https://www.rightnowai.co/.well-known/security.txt is valid until 2027-09-20 and points to the contact page.", "robots.txt on www.rightnowai.co carries Content-Signal search=yes, ai-input=yes, ai-train=yes." ], "score": 84 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/rightnow-system-zero.json", "live": { "slug": "rightnow-system-zero", "probe": { "target": "https://api.rightnowai.co/v1/system-zero/decide", "method": "get", "lastAt": "2026-10-31T05:26:14.484043664Z", "lastOk": true, "lastStatus": 405, "lastMs": 213, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 205, "p95ms24h": 244, "samples24h": 24, "samples30d": 24, "days": [ { "date": "2026-10-31", "probes": 24, "ok": 24 } ] }, "vendorStatus": { "page": "https://status.rightnowai.co", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-31T04:13:05.315091541Z" }, "updatedAt": "2026-10-31T05:26:14.484043664Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "IBM", "b": "RightNow AI, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.rightnowai.co/v1/system-zero/decide", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP, websocket", "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 model under RightNow AI terms of use; the SDKs are Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-14", "b": "2026-10-27", "name": "Last release" }, { "a": "no document linked", "b": "no date given", "name": "Terms last updated" }, { "a": "no document linked", "b": "no date given", "name": "Privacy policy last updated" }, { "a": "", "b": "yes", "name": "Customer content may train models" }, { "a": "", "b": "yes", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" }, { "a": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "RightNow System Zero scores 66.8 (B) on agent readiness against Granite Switch 4.1's 59.5 (C), and leads in 4 of 7 scored categories. Granite Switch 4.1 leads on payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.", "question": "Which is better for AI agents, Granite Switch 4.1 or RightNow System Zero?" }, { "answer": "Granite Switch 4.1 needs no key. RightNow System Zero needs an API key.", "question": "Do Granite Switch 4.1 and RightNow System Zero need an API key?" }, { "answer": "No hosted endpoint is listed for Granite Switch 4.1. RightNow System Zero has a hosted endpoint at https://api.rightnowai.co/v1/system-zero/decide.", "question": "Can an agent call Granite Switch 4.1 and RightNow System Zero 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 RightNow System Zero.", "question": "Are Granite Switch 4.1 and RightNow System Zero open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 81 against 68", "Transparency \u0026 trust, 75 against 70" ], "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, 83 against 55", "Agent ergonomics, 86 against 66", "Security \u0026 auth, 70 against 54" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Typed decisions with per-option probabilities over text, JSON, images, audio and PDFs, including on streaming state", "slug": "rightnow-system-zero", "watchFor": "Standard context is 38,000 tokens. The 64k, 128k and 1M bands are held, and video is a preview" } ], "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-rightnow-system-zero.json", "title": "Celeris-1 Decision vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-rightnow-system-zero" }, { "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-rightnow-system-zero.json", "title": "Clef vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-rightnow-system-zero" }, { "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-rightnow-system-zero.json", "title": "Laya vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-rightnow-system-zero" }, { "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-rightnow-system-zero.json", "title": "Decider vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/decider-vs-rightnow-system-zero" }, { "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-rightnow-system-zero.json", "title": "Decision 3.0 vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/decision-3-vs-rightnow-system-zero" }, { "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-rightnow-system-zero.json", "title": "GLiClass vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/gliclass-vs-rightnow-system-zero" }, { "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-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-rightnow-system-zero.json", "title": "Kev vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-rightnow-system-zero.json", "title": "Liquid d1 vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-rightnow-system-zero.json", "title": "Microsoft-Decision-1 vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-rightnow-system-zero.json", "title": "Drex 1.5 vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-rightnow-system-zero.json", "title": "OpenAI Decisions API vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-flash-vs-rightnow-system-zero.json", "title": "pplx-decider-flash vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/pplx-decider-flash-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-rightnow-system-zero.json", "title": "pplx-decider vs RightNow System Zero", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-rightnow-system-zero" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-scaledown.json", "title": "RightNow System Zero vs ScaleDown", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sprag-spev.json", "title": "RightNow System Zero vs SPEV", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sqwish-kettei.json", "title": "RightNow System Zero vs kettei", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sqwish-kettei" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-strands-decider.json", "title": "RightNow System Zero vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-typesafe-jev.json", "title": "RightNow System Zero vs Jev", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-vela.json", "title": "RightNow System Zero vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/rightnow-system-zero-vs-vela" } ], "scores": [ { "by": 4, "edge": "rightnow-system-zero", "granite-switch": 46, "key": "reliability", "name": "Reliability", "rightnow-system-zero": 50, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 28, "edge": "rightnow-system-zero", "granite-switch": 55, "key": "schema", "name": "Schema \u0026 documentation", "rightnow-system-zero": 83, "weight": 13 }, { "by": 20, "edge": "rightnow-system-zero", "granite-switch": 66, "key": "ergonomics", "name": "Agent ergonomics", "rightnow-system-zero": 86, "weight": 13 }, { "by": 16, "edge": "rightnow-system-zero", "granite-switch": 54, "key": "security", "name": "Security \u0026 auth", "rightnow-system-zero": 70, "weight": 14 }, { "by": 20, "edge": "granite-switch", "granite-switch": 60, "key": "payments", "name": "Payments \u0026 pricing", "rightnow-system-zero": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 13, "edge": "granite-switch", "granite-switch": 81, "key": "maintenance", "name": "Maintenance \u0026 community", "rightnow-system-zero": 68, "weight": 7 }, { "by": 5, "edge": "granite-switch", "granite-switch": 75, "key": "transparency", "name": "Transparency \u0026 trust", "rightnow-system-zero": 70, "weight": 7 } ], "summary": "RightNow System Zero scores 66.8 (B) on agent readiness against Granite Switch 4.1's 59.5 (C), and leads in 4 of 7 scored categories. Granite Switch 4.1 leads on payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust. 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.", "rightnow-system-zero": "A well-documented decision API with an OpenAPI file, idempotent retries, a detailed error catalogue, streaming over WebSocket and published per-unit prices with USD 5 of starting credit. Standard context is 38,000 tokens; the 64k, 128k and 1M bands are held and video is a preview. The latency and benchmark figures are RightNow's own, and several of its pages disagree." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero", "json": "https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero.min.md" }, "markdown": "RightNow System Zero scores 66.8 (B) on agent readiness against Granite Switch 4.1's 59.5 (C), and leads in 4 of 7 scored categories. Granite Switch 4.1 leads on payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust. Both do decision models.\n\n- Granite Switch 4.1: grade C, 59.5/100, rank #639 of 1244. Markdown https://www.anchorterminal.com/tools/granite-switch.md · JSON https://www.anchorterminal.com/api/v1/tools/granite-switch.json\n- RightNow System Zero: grade B, 66.8/100, rank #320 of 1244. Markdown https://www.anchorterminal.com/tools/rightnow-system-zero.md · JSON https://www.anchorterminal.com/api/v1/tools/rightnow-system-zero.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 220 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- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 81 against 68\n- Transparency \u0026 trust, 75 against 70\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### RightNow System Zero (B)\n\nGood for: Typed decisions with per-option probabilities over text, JSON, images, audio and PDFs, including on streaming state\n\nAhead on:\n- Schema \u0026 documentation, 83 against 55\n- Agent ergonomics, 86 against 66\n- Security \u0026 auth, 70 against 54\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: Standard context is 38,000 tokens. The 64k, 128k and 1M bands are held, and video is a preview\n\n\n## Score by category\n\n| Category | Weight | Granite Switch 4.1 | RightNow System Zero | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 46 | 50 | RightNow System Zero +4 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 55 | 83 | RightNow System Zero +28 |\n| Agent ergonomics | 13% (16.2 this run) | 66 | 86 | RightNow System Zero +20 |\n| Security \u0026 auth | 14% (17.5 this run) | 54 | 70 | RightNow System Zero +16 |\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 | 68 | Granite Switch 4.1 +13 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 75 | 70 | Granite Switch 4.1 +5 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **59.5 · C** | **66.8 · B** | |\n\n## Facts side by side\n\n| Fact | Granite Switch 4.1 | RightNow System Zero |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | IBM | RightNow AI, Inc. |\n| Hosted endpoint | no (local only) | `https://api.rightnowai.co/v1/system-zero/decide` |\n| Transports | HTTP | HTTP, websocket |\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 model under RightNow AI terms of use; the SDKs are Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-14 | 2026-10-27 |\n| Terms last updated | no document linked | no date given |\n| Privacy policy last updated | no document linked | no date given |\n| Customer content may train models | | yes |\n| Terms restrict automated access | | yes |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\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**RightNow System Zero.** A well-documented decision API with an OpenAPI file, idempotent retries, a detailed error catalogue, streaming over WebSocket and published per-unit prices with USD 5 of starting credit. Standard context is 38,000 tokens; the 64k, 128k and 1M bands are held and video is a preview. The latency and benchmark figures are RightNow's own, and several of its pages disagree.\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### RightNow System Zero\n\n1. Send audio only as inline 16,000 Hz WAV. The FLAC, MP3, OGG and MP4 audio named on the blog are refused with media_unsupported.\n2. Keep state under 38,000 tokens. Long-context requests return 404 long_context_not_available, which never succeeds on retry.\n3. Reuse the same Idempotency-Key and body on retries, and stop when error.retryable or x-should-retry is false.\n4. Check every entry in answers even on HTTP 200, since one question can be refused while the others are answered.\n5. Treat probabilities as uncalibrated while calibrated is false, and pin system-zero-2.0.0 when answers must not move with the alias.\n\n## Questions\n\n### Which is better for AI agents, Granite Switch 4.1 or RightNow System Zero?\n\nRightNow System Zero scores 66.8 (B) on agent readiness against Granite Switch 4.1's 59.5 (C), and leads in 4 of 7 scored categories. Granite Switch 4.1 leads on payments \u0026 pricing, maintenance \u0026 community and transparency \u0026 trust.\n\n### Do Granite Switch 4.1 and RightNow System Zero need an API key?\n\nGranite Switch 4.1 needs no key. RightNow System Zero needs an API key.\n\n### Can an agent call Granite Switch 4.1 and RightNow System Zero without installing anything?\n\nNo hosted endpoint is listed for Granite Switch 4.1. RightNow System Zero has a hosted endpoint at https://api.rightnowai.co/v1/system-zero/decide.\n\n### Are Granite Switch 4.1 and RightNow System Zero 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 RightNow System Zero.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero.json, and with the fewest tokens: https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"granite-switch\", \"b\": \"rightnow-system-zero\"}`. From a terminal: `anchor compare granite-switch rightnow-system-zero`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/granite-switch.json and https://www.anchorterminal.com/api/v1/tools/rightnow-system-zero.json\n\n## Other comparisons with Granite Switch 4.1 or RightNow System Zero\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 RightNow System Zero](https://www.anchorterminal.com/compare/celeris-1-decision-vs-rightnow-system-zero.md)\n- [Clef vs Granite Switch 4.1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch.md)\n- [Clef vs RightNow System Zero](https://www.anchorterminal.com/compare/cloudflare-clef-vs-rightnow-system-zero.md)\n- [Laya vs Granite Switch 4.1](https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.md)\n- [Laya vs RightNow System Zero](https://www.anchorterminal.com/compare/convai-laya-vs-rightnow-system-zero.md)\n- [Decider vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decider-vs-granite-switch.md)\n- [Decider vs RightNow System Zero](https://www.anchorterminal.com/compare/decider-vs-rightnow-system-zero.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 RightNow System Zero](https://www.anchorterminal.com/compare/decision-3-vs-rightnow-system-zero.md)\n- [GLiClass vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gliclass-vs-granite-switch.md)\n- [GLiClass vs RightNow System Zero](https://www.anchorterminal.com/compare/gliclass-vs-rightnow-system-zero.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 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 RightNow System Zero](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-rightnow-system-zero.md)\n- [Liquid d1 vs RightNow System Zero](https://www.anchorterminal.com/compare/liquid-d1-vs-rightnow-system-zero.md)\n- [Microsoft-Decision-1 vs RightNow System Zero](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-rightnow-system-zero.md)\n- [Drex 1.5 vs RightNow System Zero](https://www.anchorterminal.com/compare/nace-drex-vs-rightnow-system-zero.md)\n- [OpenAI Decisions API vs RightNow System Zero](https://www.anchorterminal.com/compare/openai-decisions-api-vs-rightnow-system-zero.md)\n- [pplx-decider-flash vs RightNow System Zero](https://www.anchorterminal.com/compare/pplx-decider-flash-vs-rightnow-system-zero.md)\n- [pplx-decider vs RightNow System Zero](https://www.anchorterminal.com/compare/pplx-decider-vs-rightnow-system-zero.md)\n- [RightNow System Zero vs ScaleDown](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-scaledown.md)\n- [RightNow System Zero vs SPEV](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sprag-spev.md)\n- [RightNow System Zero vs kettei](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-sqwish-kettei.md)\n- [RightNow System Zero vs Strands Decider 2B](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-strands-decider.md)\n- [RightNow System Zero vs Jev](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-typesafe-jev.md)\n- [RightNow System Zero vs Vela 2.0](https://www.anchorterminal.com/compare/rightnow-system-zero-vs-vela.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-31", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "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 RightNow System Zero", "url": "" } ], "description": "RightNow System Zero scores 66.8 (B) to Granite Switch 4.1's 59.5 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Granite Switch 4.1 C 59.5", "RightNow System Zero B 66.8", "scores" ], "h1": "Granite Switch 4.1 vs RightNow System Zero", "image": "https://www.anchorterminal.com/assets/og/compare-granite-switch-vs-rightnow-system-zero.png", "path": "/compare/granite-switch-vs-rightnow-system-zero", "published": "2026-10-01", "section": "tools", "title": "Granite Switch 4.1 vs RightNow System Zero for AI agents (2026)", "toc": null, "updated": "2026-10-31", "url": "https://www.anchorterminal.com/compare/granite-switch-vs-rightnow-system-zero" }, "tokens": { "markdown": 3200, "slim": 780 }, "version": 1 }