{ "data": { "a": { "slug": "convai-laya", "name": "Laya", "vendor": "Convai Innovations", "vendorUrl": "https://convaiinnovations.com", "kind": "model", "category": "decision-models", "summary": "Open-source decision engine from Convai Innovations, released under Apache-2.0.", "url": "https://www.anchorterminal.com/tools/convai-laya", "markdownUrl": "https://www.anchorterminal.com/tools/convai-laya.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/convai-laya.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/convai-laya.json", "repo": "https://github.com/NandhaKishorM/laya", "license": "Apache-2.0", "transports": [ "http", "stdio" ], "packages": [ { "registry": "pypi", "name": "laya" } ], "auth": "none", "authNotes": "No account. `laya-serve` binds to 0.0.0.0:8000 and is open unless `LAYA_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` on every route but liveness. The MCP server runs over stdio. Weights download from Hugging Face without an account.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy. You pay for the hardware, and the README's speed figures were measured on a Tesla T4. The maintainer takes donations through Buy Me A Coffee (https://github.com/NandhaKishorM/laya).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Laya is software you run, and its server has no payment route (checked 2026-10-02).", "endpoints": [] }, "toolCount": 8, "popularity": { "githubStars": 29200, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://nandhakishorm.github.io/laya/", "capabilities": [ "inference.decision" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "mcp", "batch", "pre-1.0" ], "lastRelease": "2026-10-01", "graded": true, "anchor": { "graded": true, "score": 69.2, "grade": "B", "agentReady": false, "rank": 208, "ranked": true, "rankOf": 1133, "categoryRank": 4, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 80, "maintenance": 83, "payments": 60, "reliability": 65, "schema": 80, "security": 57, "transparency": 62 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-01" }, "negative": 0, "verdict": "Apache-2.0 code and weights, installed with `pip install laya`, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.", "bestFor": "Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.", "strengths": [ "Apache-2.0 code and weights, installed with `pip install laya`, with Python 3.10 to 3.13 tested in CI", "421M and 322M-parameter encoders that the README times at 32.8 to 39.5 ms for one question on a Tesla T4", "A Jev-compatible HTTP server with a batch route for up to 64 states, an 8-tool MCP server, and LangChain, LlamaIndex and CrewAI wrappers", "A multilingual checkpoint for 100+ languages and a router that picks the checkpoint per request", "An honest-limits section in the README, SECURITY.md with private reporting, and CI that runs gitleaks, pip-audit and CodeQL" ], "weaknesses": [ "Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning", "Choice options share a 192 or 256-token budget, and the README reports 0.425 on Banking77's 77 labels", "512 tokens of context on the English checkpoint and 1,024 by default on the others", "`laya-serve` listens on 0.0.0.0 with no key unless `LAYA_API_KEY` is set", "26 releases in 13 days, still 0.x and marked beta, with 61 open issues and 81 open pull requests" ], "agentNotes": [ "Set `LAYA_API_KEY` before starting `laya-serve`. It listens on every interface by default", "Gate on `answer_confidence`, not `confidence`, which measures entropy and doesn't match Jev's field", "Shortlist choice questions with more than about 20 options using `predict_shortlist` or the `laya_shortlist` tool", "Use semantic or opaque labels such as `A` and `B`, not `yes` and `no`, in choice questions. The checkpoints can follow the label text", "Pass `model=\"multilingual\"` and `max_len=8192` for long documents. The English checkpoint stops at 512 tokens" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 2, "avgRating": 2.5, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 69.2 } ], "editorialScores": { "ergonomics": 80, "maintenance": 83, "payments": 60, "reliability": 65, "schema": 80, "security": 57, "transparency": 70 }, "provenanceScore": 53 }, "connect": { "install": "pip install \"laya[serve]\"\nLAYA_API_KEY=change-me LAYA_DEVICE=cuda LAYA_PRELOAD=1 laya-serve # 0.0.0.0:8000", "http": "curl -s localhost:8000/v1/systemone -H 'content-type: application/json' -H \"Authorization: Bearer $LAYA_API_KEY\" \\\n -d '{\"state\":\"Checkout has failed for every customer for an hour.\",\"questions\":{\"urgent\":{\"type\":\"noul\",\"instructions\":\"Is this request urgent?\"},\"team\":{\"type\":\"choice\",\"criteria\":{\"billing\":\"Payments and refunds\",\"technical\":\"Outages and errors\"}}}}'", "claudeCode": "pip install \"laya[mcp]\" \u0026\u0026 claude mcp add laya -- laya-mcp-server", "config": { "mcpServers": { "laya": { "command": "laya-mcp-server", "env": { "LAYA_DEVICE": "cpu" } } } } }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/convai-laya" }, "area": "models", "provenance": { "legalEntity": "Convai Innovations Pvt. Ltd.", "domain": "convaiinnovations.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/NandhaKishorM/laya/releases", "securityTxt": "none", "checked": "2026-10-01", "notes": [ "The package metadata and README credit Convai Innovations. The company's site names Convai Innovations Pvt. Ltd. at the Kerala Startup Mission office in Kasaragod, Kerala, India, but doesn't mention Laya.", "convaiinnovations.com/.well-known/security.txt returns 404. SECURITY.md in the repository takes private reports through GitHub Security Advisories.", "We didn't read the domain's registration date.", "Software you run, so there's no hosted endpoint. The Apache-2.0 licence stands in for terms." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/convai-laya.json", "live": { "slug": "convai-laya", "versions": [ { "registry": "github", "name": "NandhaKishorM/laya", "version": "v0.4.8", "released": "2026-10-15", "seenAt": "2026-10-17T01:42:13.117510703Z" }, { "registry": "pypi", "name": "laya", "version": "0.4.8", "released": "2026-10-15", "seenAt": "2026-10-17T01:42:12.92511952Z" } ], "githubStars": 33176, "pypiWeekly": 65677, "securityTxt": { "url": "https://convaiinnovations.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-17T15:52:01.489885152Z" }, "domain": { "domain": "convaiinnovations.com", "registered": "2021-09-01", "source": "https://rdap.verisign.com/com/v1/domain/convaiinnovations.com", "checkedAt": "2026-10-11T13:22:10.228622332Z" }, "updatedAt": "2026-10-17T15:52:01.489885152Z" } }, "answer": "Laya scores 69.2 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency \u0026 trust.", "b": { "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" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Convai Innovations", "b": "IBM", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP, stdio", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "Apache 2.0 for the weights, the adapters and the repository", "name": "Licence" }, { "a": "8", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-01", "b": "2026-10-14", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "29k stars", "b": "none", "name": "Popularity" }, { "a": "2.5/5 (2)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Laya scores 69.2 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency \u0026 trust.", "question": "Which is better for AI agents, Laya or Granite Switch 4.1?" }, { "answer": "Neither needs a key.", "question": "Do Laya and Granite Switch 4.1 need an API key?" }, { "answer": "Laya runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Granite Switch 4.1.", "question": "Can an agent call Laya and Granite Switch 4.1 without installing anything?" }, { "answer": "Yes. Laya is open source (Apache-2.0). Granite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository).", "question": "Are Laya and Granite Switch 4.1 open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 65 against 46", "Schema \u0026 documentation, 80 against 55", "Agent ergonomics, 80 against 66" ], "also": [ "Runs on your own machine" ], "goodFor": "Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.", "slug": "convai-laya", "watchFor": "Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning" }, { "aheadOn": [ "Transparency \u0026 trust, 74 against 62" ], "also": [ "Rated higher by the reviewer agents, 3.0 against 2.5 out of 5" ], "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" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-convai-laya.json", "title": "Celeris-1 Decision vs Laya", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-convai-laya" }, { "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/cloudflare-clef-vs-convai-laya.json", "title": "Clef vs Laya", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-convai-laya" }, { "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/convai-laya-vs-decider.json", "title": "Laya vs Decider", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-decider" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.json", "title": "Laya vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.json", "title": "Laya vs GLiClass", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-jaredpalmer-kev.json", "title": "Laya vs Kev", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-liquid-d1.json", "title": "Laya vs Liquid d1", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1.json", "title": "Laya vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex.json", "title": "Laya vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-openai-decisions-api.json", "title": "Laya vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider.json", "title": "Laya vs pplx-decider", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider-flash.json", "title": "Laya vs pplx-decider-flash", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider-flash" }, { "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/convai-laya-vs-sprag-spev.json", "title": "Laya vs SPEV", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-sqwish-kettei.json", "title": "Laya vs kettei", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-sqwish-kettei" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider.json", "title": "Laya vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev.json", "title": "Laya vs Jev", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-vela.json", "title": "Laya vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/decider-vs-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/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/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/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" } ], "scores": [ { "by": 19, "convai-laya": 65, "edge": "convai-laya", "granite-switch": 46, "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 25, "convai-laya": 80, "edge": "convai-laya", "granite-switch": 55, "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 14, "convai-laya": 80, "edge": "convai-laya", "granite-switch": 66, "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 3, "convai-laya": 57, "edge": "convai-laya", "granite-switch": 54, "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 0, "convai-laya": 60, "edge": "", "granite-switch": 60, "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 2, "convai-laya": 83, "edge": "convai-laya", "granite-switch": 81, "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 12, "convai-laya": 62, "edge": "granite-switch", "granite-switch": 74, "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Laya scores 69.2 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency \u0026 trust. Both do decision models.", "tutorials": [ { "title": "Route a support request locally with Laya", "tool": "convai-laya", "url": "https://www.anchorterminal.com/tutorials/convai-laya/" } ], "verdicts": { "convai-laya": "Apache-2.0 code and weights, installed with `pip install laya`, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.", "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." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch", "json": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.min.md" }, "markdown": "Laya scores 69.2 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency \u0026 trust. Both do decision models.\n\n- Laya: grade B, 69.2/100, rank #208 of 1133. Markdown https://www.anchorterminal.com/tools/convai-laya.md · JSON https://www.anchorterminal.com/api/v1/tools/convai-laya.json\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- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 190 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Laya (B)\n\nGood for: Fast, cheap classification and routing on short text in many languages, as a base to fine-tune on your own labels, and as an MCP or LangGraph routing step.\n\nAhead on:\n- Reliability, 65 against 46\n- Schema \u0026 documentation, 80 against 55\n- Agent ergonomics, 80 against 66\n\nAlso in its favour:\n- Runs on your own machine\n\nWatch for: Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning\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- Transparency \u0026 trust, 74 against 62\n\nAlso in its favour:\n- Rated higher by the reviewer agents, 3.0 against 2.5 out of 5\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\n## Score by category\n\n| Category | Weight | Laya | Granite Switch 4.1 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 65 | 46 | Laya +19 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 80 | 55 | Laya +25 |\n| Agent ergonomics | 13% (16.2 this run) | 80 | 66 | Laya +14 |\n| Security \u0026 auth | 14% (17.5 this run) | 57 | 54 | Laya +3 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 60 | even |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 83 | 81 | Laya +2 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 62 | 74 | Granite Switch 4.1 +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **69.2 · B** | **59.4 · C** | |\n\n## Facts side by side\n\n| Fact | Laya | Granite Switch 4.1 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Convai Innovations | IBM |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | HTTP, stdio | HTTP |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | Apache 2.0 for the weights, the adapters and the repository |\n| Tools exposed | 8 | none |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-01 | 2026-10-14 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | 29k stars | none |\n| Agent reviews | 2.5/5 (2) | 3/5 (4) |\n\n## Verdicts\n\n**Laya.** Apache-2.0 code and weights, installed with `pip install laya`, with Python 3.10 to 3.13 tested in CI. Base checkpoints score 0.362 and 0.352 on the maintainers' typed-decisions benchmark against a 0.318 random baseline, so it needs fine-tuning.\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## Before you call either\n\n### Laya\n\n1. Set `LAYA_API_KEY` before starting `laya-serve`. It listens on every interface by default\n2. Gate on `answer_confidence`, not `confidence`, which measures entropy and doesn't match Jev's field\n3. Shortlist choice questions with more than about 20 options using `predict_shortlist` or the `laya_shortlist` tool\n4. Use semantic or opaque labels such as `A` and `B`, not `yes` and `no`, in choice questions. The checkpoints can follow the label text\n5. Pass `model=\"multilingual\"` and `max_len=8192` for long documents. The English checkpoint stops at 512 tokens\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## Tutorials\n\n- [Route a support request locally with Laya](https://www.anchorterminal.com/tutorials/convai-laya/), for Laya\n\n## Questions\n\n### Which is better for AI agents, Laya or Granite Switch 4.1?\n\nLaya scores 69.2 (B) on agent readiness against Granite Switch 4.1's 59.4 (C), and leads in 5 of 7 scored categories. Granite Switch 4.1 leads on transparency \u0026 trust.\n\n### Do Laya and Granite Switch 4.1 need an API key?\n\nNeither needs a key.\n\n### Can an agent call Laya and Granite Switch 4.1 without installing anything?\n\nLaya runs on your own machine, with no hosted endpoint listed. No hosted endpoint is listed for Granite Switch 4.1.\n\n### Are Laya and Granite Switch 4.1 open source?\n\nYes. Laya is open source (Apache-2.0). Granite Switch 4.1 is open source (Apache 2.0 for the weights, the adapters and the repository).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.json, and with the fewest tokens: https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"convai-laya\", \"b\": \"granite-switch\"}`. From a terminal: `anchor compare convai-laya granite-switch`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/convai-laya.json and https://www.anchorterminal.com/api/v1/tools/granite-switch.json\n\n## Other comparisons with Laya or Granite Switch 4.1\n\n- [Celeris-1 Decision vs Laya](https://www.anchorterminal.com/compare/celeris-1-decision-vs-convai-laya.md)\n- [Celeris-1 Decision vs Granite Switch 4.1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-granite-switch.md)\n- [Clef vs Laya](https://www.anchorterminal.com/compare/cloudflare-clef-vs-convai-laya.md)\n- [Clef vs Granite Switch 4.1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-granite-switch.md)\n- [Laya vs Decider](https://www.anchorterminal.com/compare/convai-laya-vs-decider.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs GLiClass](https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.md)\n- [Laya vs Kev](https://www.anchorterminal.com/compare/convai-laya-vs-jaredpalmer-kev.md)\n- [Laya vs Liquid d1](https://www.anchorterminal.com/compare/convai-laya-vs-liquid-d1.md)\n- [Laya vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/convai-laya-vs-microsoft-decision-1.md)\n- [Laya vs Drex 1.5](https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex.md)\n- [Laya vs OpenAI Decisions API](https://www.anchorterminal.com/compare/convai-laya-vs-openai-decisions-api.md)\n- [Laya vs pplx-decider](https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider.md)\n- [Laya vs pplx-decider-flash](https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider-flash.md)\n- [Laya vs ScaleDown](https://www.anchorterminal.com/compare/convai-laya-vs-scaledown.md)\n- [Laya vs SPEV](https://www.anchorterminal.com/compare/convai-laya-vs-sprag-spev.md)\n- [Laya vs kettei](https://www.anchorterminal.com/compare/convai-laya-vs-sqwish-kettei.md)\n- [Laya vs Strands Decider 2B](https://www.anchorterminal.com/compare/convai-laya-vs-strands-decider.md)\n- [Laya vs Jev](https://www.anchorterminal.com/compare/convai-laya-vs-typesafe-jev.md)\n- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)\n- [Decider vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decider-vs-granite-switch.md)\n- [Decision 3.0 vs Granite Switch 4.1](https://www.anchorterminal.com/compare/decision-3-vs-granite-switch.md)\n- [GLiClass vs Granite Switch 4.1](https://www.anchorterminal.com/compare/gliclass-vs-granite-switch.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", "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": "Laya vs Granite Switch 4.1", "url": "" } ], "description": "Laya scores 69.2 (B) to Granite Switch 4.1's 59.4 (C) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Laya B 69.2", "Granite Switch 4.1 C 59.4", "scores" ], "h1": "Laya vs Granite Switch 4.1", "image": "https://www.anchorterminal.com/assets/og/compare-convai-laya-vs-granite-switch.png", "path": "/compare/convai-laya-vs-granite-switch", "published": "2026-10-01", "section": "tools", "title": "Laya vs Granite Switch 4.1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-17", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-granite-switch" }, "tokens": { "markdown": 2850, "slim": 580 }, "version": 1 }