{ "data": { "a": { "slug": "gliclass", "name": "GLiClass", "vendor": "Knowledgator", "vendorUrl": "https://www.knowledgator.com", "kind": "model", "category": "decision-models", "summary": "GLiClass is an open-source Python library and family of open-weight zero-shot text classifiers from Knowledgator. It scores every candidate label in one forward pass and runs locally through a pipeline or a Ray Serve endpoint.", "url": "https://www.anchorterminal.com/tools/gliclass", "markdownUrl": "https://www.anchorterminal.com/tools/gliclass.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/gliclass.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/gliclass.json", "repo": "https://github.com/Knowledgator/GLiClass", "license": "Apache-2.0 (library and the model weights we checked)", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "gliclass" } ], "auth": "none", "authNotes": "No account or key. The weights are public and ungated on Hugging Face. The bundled Ray Serve deployment has no authentication of any kind, and `python -m gliclass.serve` binds to 0.0.0.0 unless `--host` is passed, so the owner has to restrict the port.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy for the library or the weights. Hardware is the owner's cost. Knowledgator's site links a hosted platform with plans at platform.knowledgator.com, which we couldn't reach on 8 October 2026, so whether it serves GLiClass and at what price is unchecked.", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. GLiClass is software the owner runs, and its server has no payment route (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 555, "npmWeekly": null, "pypiWeekly": 13204, "asOf": "2026-10-08" }, "docsUrl": "https://docs.knowledgator.com/docs/frameworks/gliclass/", "capabilities": [ "inference.decision" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "no-auth" ], "lastRelease": "2026-07-21", "graded": true, "anchor": { "graded": true, "score": 49.9, "grade": "D", "agentReady": false, "rank": 848, "ranked": true, "rankOf": 1094, "categoryRank": 13, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 60, "maintenance": 44, "payments": 60, "reliability": 43, "schema": 49, "security": 38, "transparency": 64 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.", "bestFor": "Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.", "strengths": [ "Apache-2.0 code and weights, with `train.py`, the training datasets named on the model cards and an arXiv paper (2508.07662)", "One forward pass scores every label. The base v3.0 card reports 51.6 examples a second averaged over 1 to 128 labels on an A6000 (vendor figures)", "Single-label (softmax) and multi-label (sigmoid) modes, hierarchical label sets, task prompts and few-shot examples in one pipeline call", "A Ray Serve deployment with dynamic batching ships in the `gliclass[serve]` extra, with a documented request table for `POST /gliclass`", "31 public, ungated GLiClass checkpoints on Hugging Face, from 32.7M to 439M parameters, as safetensors" ], "weaknesses": [ "No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic", "The bundled server has no authentication, and `python -m gliclass.serve` binds to 0.0.0.0 by default", "The last three runs of the Tests workflow on main, all on 24 September 2026, failed", "Still 0.1.x with no changelog file. 0.1.18 raised the `transformers` floor to 5.0, and issue #44 on v5 loading has been open since 6 July 2026", "No OpenAPI file, no llms.txt, no SECURITY.md and no documented error responses" ], "agentNotes": [ "Pass `--host 127.0.0.1` to `python -m gliclass.serve`, or put the port behind your own gateway. The server checks no credential", "On a machine without a GPU add `--device cpu --dtype float32 --num-gpus-per-replica 0`. The default configuration expects CUDA", "Send one text a request to `POST /gliclass`. An array in `texts` is cut to its first item without an error", "Set `multi_label` to false for one label from a set. The default scores each label independently, so scores do not sum to 1", "Keep text plus labels under the pipeline's 1,024-token `max_length`, or use `ZeroShotClassificationWithChunkingPipeline`. Longer input is truncated silently" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 49.9 } ], "editorialScores": { "ergonomics": 60, "maintenance": 44, "payments": 60, "reliability": 43, "schema": 49, "security": 38, "transparency": 60 }, "provenanceScore": 68 }, "connect": { "install": "pip install gliclass", "http": "pip install \"gliclass[serve]\"\npython -m gliclass.serve --model knowledgator/gliclass-edge-v3.0 --port 8000\ncurl -X POST http://localhost:8000/gliclass \\\n -H \"Content-Type: application/json\" \\\n -d '{\"text\": \"This is a great product.\", \"labels\": [\"positive\", \"negative\", \"neutral\"], \"threshold\": 0.3, \"multi_label\": true}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/gliclass" }, "area": "models", "provenance": { "legalEntity": "Knowledgator Engineering Ltd.", "domain": "knowledgator.com", "domainRegistered": "2021-06-25", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/Knowledgator/GLiClass/releases", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of use and privacy policy linked from knowledgator.com name Knowledgator Engineering Ltd., London, United Kingdom. Both are dated 21 September 2023.", "Those two documents govern the website and Knowledgator's hosted services, not the library, so `terms` and `privacy` are left out. The Apache-2.0 licence governs what an agent would run.", "Software the owner runs, so there is no hosted endpoint and no status page for it.", "www.knowledgator.com/.well-known/security.txt returns 404, and the repository has no SECURITY.md.", "RDAP for knowledgator.com gives a registration date of 2021-06-25.", "The code is on github.com under the Knowledgator organisation and the weights on huggingface.co under knowledgator." ], "score": 68 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/gliclass.json", "live": { "slug": "gliclass", "versions": [ { "registry": "github", "name": "Knowledgator/GLiClass", "version": "v0.1.20", "released": "2026-07-21", "seenAt": "2026-10-14T23:54:33.912165118Z" }, { "registry": "pypi", "name": "gliclass", "version": "0.1.20", "released": "2026-07-21", "seenAt": "2026-10-14T23:54:33.720749948Z" } ], "githubStars": 559, "pypiWeekly": 11061, "securityTxt": { "url": "https://knowledgator.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-14T15:46:55.370320351Z" }, "domain": { "domain": "knowledgator.com", "registered": "2021-06-25", "source": "https://rdap.verisign.com/com/v1/domain/knowledgator.com", "checkedAt": "2026-10-11T13:24:38.717810411Z" }, "updatedAt": "2026-10-14T23:54:33.912165118Z" } }, "answer": "GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and maintenance \u0026 community.", "b": { "slug": "scaledown", "name": "ScaleDown", "vendor": "Carbon ScaleDown, Inc.", "vendorUrl": "https://scaledown.ai", "kind": "model", "category": "decision-models", "summary": "ScaleDown's API serves three single-task Constrained Decoding Models (Classify, Extract and Summarize) and a Compress model, called with an API key at api.scaledown.xyz. Classify answers Jev-shaped decision requests with probabilities.", "url": "https://www.anchorterminal.com/tools/scaledown", "markdownUrl": "https://www.anchorterminal.com/tools/scaledown.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/scaledown.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/scaledown.json", "repo": "https://github.com/scaledown-team/langchain-scaledown", "license": "Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT", "transports": [ "http" ], "remoteUrl": "https://api.scaledown.xyz", "packages": [ { "registry": "pypi", "name": "langchain-scaledown" } ], "auth": "api-key", "authNotes": "An API key in the `x-api-key` header. Extract and Summarize on `/v1/chat/completions` also accept `Authorization: Bearer`, so an unmodified OpenAI SDK works by changing the base URL. Keys are made in the dashboard after sign-up at scaledown.ai/auth. We found no documentation of key scopes, expiry or rotation. An unauthenticated request returns 401 with `{\"detail\":\"x-api-key header is required\"}`.", "pricing": "usage", "pricingNotes": "$0.05 per million input tokens for every model, with output tokens free (https://scaledown.ai, FAQ). Classify's optional one-sentence reasoning bills its extra input tokens at 2x. New accounts get 50 million free tokens with no card, per the homepage. The docs introduction instead says to contact sales for a key. OpenRouter lists Extract and Summarize at $0.04 per million input tokens. Enterprise and self-hosted plans are priced by sales.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs, the OpenAPI document, the site or the LiteLLM and OpenRouter entries (checked 2026-10-14). Running out of credit returns 402 Payment Required as an ordinary error.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 0, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-14" }, "docsUrl": "https://docs.scaledown.ai/introduction", "llmsTxt": "https://docs.scaledown.ai/llms.txt", "openapi": "https://docs.scaledown.ai/api-reference/openapi.json", "capabilities": [ "inference.decision", "docs.extract" ], "tags": [ "hosted", "model", "closed-source", "openapi", "llms-txt", "openai-compatible", "usage-priced", "free-tier", "no-card", "python" ], "lastRelease": "2026-10-14", "graded": true, "anchor": { "graded": true, "score": 48.6, "grade": "D", "agentReady": false, "rank": 880, "ranked": true, "rankOf": 1094, "categoryRank": 15, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 56, "payments": 40, "reliability": 20, "schema": 69, "security": 48, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-14" }, "negative": -2, "negativeNotes": [ "Conflicting compliance claims on ScaleDown's own pages, read 14 October 2026. The DPA (20 July 2026) says ScaleDown maintains a SOC 2 Type II attestation and ISO 27001 certification, the homepage shows SOC 2 Type 1, HIPAA and ISO 27001 badges, and llms.txt says GDPR, HIPAA and SOC 2 compliance is in progress. At least one is wrong. No report or trust centre found to settle it (-2) (https://scaledown.ai/dpa, https://scaledown.ai/llms.txt)" ], "verdict": "Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.", "bestFor": "Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.", "strengths": [ "`POST /v1/scaledown` takes Jev's request shape, so a Jev integration can move by changing the base URL, per the docs", "$0.05 per million input tokens for every model, output free, and 50 million free tokens with no card, per the homepage", "Extract returns each value with a confidence, character offsets and surrounding context, and routes `enum` fields to the Classify model", "llms.txt with Markdown twins, an OpenAPI 3.1 document and OpenAI-compatible chat completions for Extract and Summarize", "The terms, DPA and FAQ agree that customer data isn't used for training, and the DPA lists four US subprocessors" ], "weaknesses": [ "No status page, no published rate limits and no SLA outside enterprise contracts", "No public changelog. The docs dropped the native /extract and /summarization endpoints from the reference on 13 October 2026", "Compliance claims disagree between the DPA (SOC 2 Type II, ISO 27001), the homepage badges (SOC 2 Type 1) and llms.txt (in progress)", "No security.txt, disclosure policy or bug bounty, and no guidance on hostile text in classified input", "The OpenAPI document covers /classify, /v1/scaledown and Compress only, without the documented limits" ], "agentNotes": [ "Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed", "Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases", "Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side", "Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x", "Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 48.6 } ], "editorialScores": { "ergonomics": 76, "maintenance": 56, "payments": 40, "reliability": 20, "schema": 69, "security": 48, "transparency": 56 }, "provenanceScore": 52 }, "connect": { "install": "pip install langchain-scaledown # LangChain middleware; any OpenAI SDK also works against /v1/chat/completions", "http": "curl https://api.scaledown.xyz/v1/scaledown \\\n -H \"x-api-key: $SCALEDOWN_API_KEY\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"classify-1\",\"state\":\"I was charged twice for my subscription this month.\",\"questions\":{\"category\":{\"type\":\"choice\",\"criteria\":{\"billing\":\"About a charge, invoice, refund, or payment problem.\",\"technical\":\"About a bug or something not working.\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/scaledown" }, "alsoIn": [ "document-extraction" ], "area": "models", "unitPrices": [ { "item": "Classify, Extract, Summarize and Compress input", "unit": "1m-tokens", "usd": 0.05, "note": "Output tokens free. Classify reasoning input billed at 2x. 50M free tokens for new accounts" } ], "provenance": { "legalEntity": "Carbon ScaleDown, Inc.", "domain": "scaledown.ai", "domainRegistered": "2025-03-28", "endpointOnVendorDomain": true, "terms": "https://scaledown.ai/terms", "privacy": "https://scaledown.ai/privacy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-14", "notes": [ "The terms (last updated 20 July 2026), privacy notice (3 June 2026) and DPA (20 July 2026) name Carbon ScaleDown, Inc., 22952 Stokes Rd, Ramona, CA 92065, and Delaware law. One sentence of the terms names ScaleDown, Inc.", "scaledown.ai is a single-page app. /terms, /privacy and /dpa answer HTTP 404 with the app shell, and their text is in the JavaScript bundle (https://scaledown.ai/assets/index-CIrIjse9.js), where we read it.", "The API host is api.scaledown.xyz. scaledown.xyz redirects to scaledown.ai, so we treat the endpoint as on the vendor's domain.", "scaledown.ai/.well-known/security.txt and docs.scaledown.ai/.well-known/security.txt return 404. status.scaledown.ai and status.scaledown.xyz don't resolve.", "No public changelog. The docs source at github.com/scaledown-team/docs has dated commits that record API changes.", "RDAP gives scaledown.ai a registration date of 28 March 2025." ], "score": 52 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/scaledown.json", "live": { "slug": "scaledown", "probe": { "target": "https://api.scaledown.xyz", "method": "get", "lastAt": "2026-10-15T14:03:43.707330463Z", "lastOk": true, "lastStatus": 403, "lastMs": 252, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 263, "p95ms24h": 308, "samples24h": 197, "samples30d": 197, "days": [ { "date": "2026-10-14", "probes": 47, "ok": 47 }, { "date": "2026-10-15", "probes": 150, "ok": 150 } ] }, "versions": [ { "registry": "pypi", "name": "langchain-scaledown", "version": "0.2.0", "released": "2026-10-12", "seenAt": "2026-10-15T00:19:27.075016002Z" } ], "githubStars": 0, "pypiWeekly": 229, "pages": [ { "url": "https://scaledown.ai/privacy", "kind": "privacy", "status": 404, "checkedAt": "2026-10-14T21:06:40.247126332Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://scaledown.ai/terms", "kind": "terms", "status": 404, "checkedAt": "2026-10-14T21:06:42.626164273Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-15T14:03:43.707330463Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Knowledgator", "b": "Carbon ScaleDown, Inc.", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.scaledown.xyz", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Pay per use", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (library and the model weights we checked)", "b": "Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-07-21", "b": "2026-10-14", "name": "Last release" }, { "a": "no document linked", "b": "couldn't be read", "name": "Terms last updated" }, { "a": "no document linked", "b": "couldn't be read", "name": "Privacy policy last updated" }, { "a": "", "b": "couldn't be read", "name": "Customer content may train models" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict automated access" }, { "a": "", "b": "couldn't be read", "name": "Terms restrict benchmarking" }, { "a": "", "b": "couldn't be read", "name": "Terms or service can change without notice" }, { "a": "", "b": "couldn't be read", "name": "Arbitration or class-action waiver" }, { "a": "555 stars, 13k PyPI/wk", "b": "0 stars", "name": "Popularity" } ], "faq": [ { "answer": "GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and maintenance \u0026 community.", "question": "Which is better for AI agents, GLiClass or ScaleDown?" }, { "answer": "GLiClass needs no key. ScaleDown needs an API key.", "question": "Do GLiClass and ScaleDown need an API key?" }, { "answer": "No hosted endpoint is listed for GLiClass. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.", "question": "Can an agent call GLiClass and ScaleDown without installing anything?" }, { "answer": "GLiClass is open source (Apache-2.0 (library and the model weights we checked)). No open-source release is listed for ScaleDown.", "question": "Are GLiClass and ScaleDown open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 43 against 20", "Payments \u0026 pricing, 60 against 40", "Transparency \u0026 trust, 64 against 54" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.", "slug": "gliclass", "watchFor": "No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic" }, { "aheadOn": [ "Schema \u0026 documentation, 69 against 49", "Agent ergonomics, 76 against 60", "Security \u0026 auth, 48 against 38", "Maintenance \u0026 community, 56 against 44" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.", "slug": "scaledown", "watchFor": "No status page, no published rate limits and no SLA outside enterprise contracts" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.json", "title": "Celeris-1 Decision vs GLiClass", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown.json", "title": "Celeris-1 Decision vs ScaleDown", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.json", "title": "Clef vs GLiClass", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown.json", "title": "Clef vs ScaleDown", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-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-scaledown.json", "title": "Laya vs ScaleDown", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/decider-vs-gliclass.json", "title": "Decider vs GLiClass", "url": "https://www.anchorterminal.com/compare/decider-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/decider-vs-scaledown.json", "title": "Decider vs ScaleDown", "url": "https://www.anchorterminal.com/compare/decider-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-gliclass.json", "title": "Decision 3.0 vs GLiClass", "url": "https://www.anchorterminal.com/compare/decision-3-vs-gliclass" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-scaledown.json", "title": "Decision 3.0 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/decision-3-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-jaredpalmer-kev.json", "title": "GLiClass vs Kev", "url": "https://www.anchorterminal.com/compare/gliclass-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-liquid-d1.json", "title": "GLiClass vs Liquid d1", "url": "https://www.anchorterminal.com/compare/gliclass-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.json", "title": "GLiClass vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-nace-drex.json", "title": "GLiClass vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/gliclass-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api.json", "title": "GLiClass vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.json", "title": "GLiClass vs pplx-decider", "url": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev.json", "title": "GLiClass vs SPEV", "url": "https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-strands-decider.json", "title": "GLiClass vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/gliclass-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-typesafe-jev.json", "title": "GLiClass vs Jev", "url": "https://www.anchorterminal.com/compare/gliclass-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/gliclass-vs-vela.json", "title": "GLiClass vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/gliclass-vs-vela" }, { "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown.json", "title": "Kev vs ScaleDown", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown.json", "title": "Liquid d1 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.json", "title": "Microsoft-Decision-1 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-scaledown.json", "title": "Drex 1.5 vs ScaleDown", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown.json", "title": "OpenAI Decisions API vs ScaleDown", "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown.json", "title": "pplx-decider vs ScaleDown", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.json", "title": "ScaleDown vs SPEV", "url": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-strands-decider.json", "title": "ScaleDown vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/scaledown-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev.json", "title": "ScaleDown vs Jev", "url": "https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/scaledown-vs-vela.json", "title": "ScaleDown vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/scaledown-vs-vela" } ], "scores": [ { "by": 23, "edge": "gliclass", "gliclass": 43, "key": "reliability", "name": "Reliability", "scaledown": 20, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 20, "edge": "scaledown", "gliclass": 49, "key": "schema", "name": "Schema \u0026 documentation", "scaledown": 69, "weight": 13 }, { "by": 16, "edge": "scaledown", "gliclass": 60, "key": "ergonomics", "name": "Agent ergonomics", "scaledown": 76, "weight": 13 }, { "by": 10, "edge": "scaledown", "gliclass": 38, "key": "security", "name": "Security \u0026 auth", "scaledown": 48, "weight": 14 }, { "by": 20, "edge": "gliclass", "gliclass": 60, "key": "payments", "name": "Payments \u0026 pricing", "scaledown": 40, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 12, "edge": "scaledown", "gliclass": 44, "key": "maintenance", "name": "Maintenance \u0026 community", "scaledown": 56, "weight": 7 }, { "by": 10, "edge": "gliclass", "gliclass": 64, "key": "transparency", "name": "Transparency \u0026 trust", "scaledown": 54, "weight": 7 } ], "summary": "GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and maintenance \u0026 community. Both do decision models.", "verdicts": { "gliclass": "An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.", "scaledown": "Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown", "json": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown.md", "slim": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown.min.md" }, "markdown": "GLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and maintenance \u0026 community. Both do decision models.\n\n- GLiClass: grade D, 49.9/100, rank #848 of 1094. Markdown https://www.anchorterminal.com/tools/gliclass.md · JSON https://www.anchorterminal.com/api/v1/tools/gliclass.json\n- ScaleDown: grade D, 48.6/100, rank #880 of 1094. Markdown https://www.anchorterminal.com/tools/scaledown.md · JSON https://www.anchorterminal.com/api/v1/tools/scaledown.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 136 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n- Best document parsing, OCR and extraction APIs for AI agents: https://www.anchorterminal.com/best/document-extraction/index.md\n- All 125 documents comparisons: https://www.anchorterminal.com/compare/document-extraction/index.md\n\n## Which one, for what\n\n### GLiClass (D)\n\nGood for: Topic, intent and sentiment routing over a known label set on the owner's own CPU or GPU, where many labels must be scored at once.\n\nAhead on:\n- Reliability, 43 against 20\n- Payments \u0026 pricing, 60 against 40\n- Transparency \u0026 trust, 64 against 54\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No calibration evidence. The cards report F1 only, and the docs tell users to calibrate thresholds on their own traffic\n\n### ScaleDown (D)\n\nGood for: Cheap, high-volume labelling, routing and yes or no checks where a probability is more useful than prose, and for pulling described fields with offsets from text, images or PDFs.\n\nAhead on:\n- Schema \u0026 documentation, 69 against 49\n- Agent ergonomics, 76 against 60\n- Security \u0026 auth, 48 against 38\n- Maintenance \u0026 community, 56 against 44\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: No status page, no published rate limits and no SLA outside enterprise contracts\n\n\n## Score by category\n\n| Category | Weight | GLiClass | ScaleDown | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 43 | 20 | GLiClass +23 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 49 | 69 | ScaleDown +20 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 76 | ScaleDown +16 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 48 | ScaleDown +10 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | GLiClass +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 44 | 56 | ScaleDown +12 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 54 | GLiClass +10 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **49.9 · D** | **48.6 · D** | |\n\n## Facts side by side\n\n| Fact | GLiClass | ScaleDown |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Knowledgator | Carbon ScaleDown, Inc. |\n| Hosted endpoint | no (local only) | `https://api.scaledown.xyz` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| x402 | no | no |\n| Licence | Apache-2.0 (library and the model weights we checked) | Proprietary hosted models under ScaleDown's Terms of Service. The langchain-scaledown integration is MIT |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-07-21 | 2026-10-14 |\n| Terms last updated | no document linked | couldn't be read |\n| Privacy policy last updated | no document linked | couldn't be read |\n| Customer content may train models | | couldn't be read |\n| Terms restrict automated access | | couldn't be read |\n| Terms restrict benchmarking | | couldn't be read |\n| Terms or service can change without notice | | couldn't be read |\n| Arbitration or class-action waiver | | couldn't be read |\n| Popularity | 555 stars, 13k PyPI/wk | 0 stars |\n\n## Verdicts\n\n**GLiClass.** An Apache-2.0 classifier that scores a whole label set in one encoder pass on the owner's hardware, with single-label, multi-label, hierarchical and few-shot modes. It returns label scores with no calibration claim, the bundled server has no authentication, and the last three test runs on the main branch, on 24 September 2026, failed.\n\n**ScaleDown.** Classify answers Jev-shaped `choice`, `noul` and `score` questions with probabilities, and Extract returns values with confidences and character offsets, at $0.05 per million input tokens with output free. There is no status page, no published rate limit and no public changelog, and the site's compliance claims contradict each other.\n\n## Before you call either\n\n### GLiClass\n\n1. Pass `--host 127.0.0.1` to `python -m gliclass.serve`, or put the port behind your own gateway. The server checks no credential\n2. On a machine without a GPU add `--device cpu --dtype float32 --num-gpus-per-replica 0`. The default configuration expects CUDA\n3. Send one text a request to `POST /gliclass`. An array in `texts` is cut to its first item without an error\n4. Set `multi_label` to false for one label from a set. The default scores each label independently, so scores do not sum to 1\n5. Keep text plus labels under the pipeline's 1,024-token `max_length`, or use `ZeroShotClassificationWithChunkingPipeline`. Longer input is truncated silently\n\n### ScaleDown\n\n1. Send several questions about one item in one `/v1/scaledown` call. Each becomes its own Classify call and the usage is summed\n2. Pin `classify-1`, `extract-1` or `summarize-1` once you've tuned thresholds on your own labelled cases\n3. Set `context_chars` to 0 and use `top_n` on Extract unless you need the 500 characters of context each side\n4. Set `reasoning: false` on /classify when you only need the label. The reasoning call bills its input at 2x\n5. Back off and retry on 429, 502 and 504. No limits are published and calls have no side effects\n\n## Questions\n\n### Which is better for AI agents, GLiClass or ScaleDown?\n\nGLiClass scores 49.9 (D) on agent readiness against ScaleDown's 48.6 (D), and leads in 3 of 7 scored categories. ScaleDown leads on schema \u0026 documentation, agent ergonomics, security \u0026 auth and maintenance \u0026 community.\n\n### Do GLiClass and ScaleDown need an API key?\n\nGLiClass needs no key. ScaleDown needs an API key.\n\n### Can an agent call GLiClass and ScaleDown without installing anything?\n\nNo hosted endpoint is listed for GLiClass. ScaleDown has a hosted endpoint at https://api.scaledown.xyz.\n\n### Are GLiClass and ScaleDown open source?\n\nGLiClass is open source (Apache-2.0 (library and the model weights we checked)). No open-source release is listed for ScaleDown.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gliclass-vs-scaledown.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gliclass\", \"b\": \"scaledown\"}`. From a terminal: `anchor compare gliclass scaledown`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gliclass.json and https://www.anchorterminal.com/api/v1/tools/scaledown.json\n\n## Other comparisons with GLiClass or ScaleDown\n\n- [Celeris-1 Decision vs GLiClass](https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.md)\n- [Celeris-1 Decision vs ScaleDown](https://www.anchorterminal.com/compare/celeris-1-decision-vs-scaledown.md)\n- [Clef vs GLiClass](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.md)\n- [Clef vs ScaleDown](https://www.anchorterminal.com/compare/cloudflare-clef-vs-scaledown.md)\n- [Laya vs GLiClass](https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.md)\n- [Laya vs ScaleDown](https://www.anchorterminal.com/compare/convai-laya-vs-scaledown.md)\n- [Decider vs GLiClass](https://www.anchorterminal.com/compare/decider-vs-gliclass.md)\n- [Decider vs ScaleDown](https://www.anchorterminal.com/compare/decider-vs-scaledown.md)\n- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)\n- [Decision 3.0 vs ScaleDown](https://www.anchorterminal.com/compare/decision-3-vs-scaledown.md)\n- [GLiClass vs Kev](https://www.anchorterminal.com/compare/gliclass-vs-jaredpalmer-kev.md)\n- [GLiClass vs Liquid d1](https://www.anchorterminal.com/compare/gliclass-vs-liquid-d1.md)\n- [GLiClass vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/gliclass-vs-microsoft-decision-1.md)\n- [GLiClass vs Drex 1.5](https://www.anchorterminal.com/compare/gliclass-vs-nace-drex.md)\n- [GLiClass vs OpenAI Decisions API](https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api.md)\n- [GLiClass vs pplx-decider](https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.md)\n- [GLiClass vs SPEV](https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev.md)\n- [GLiClass vs Strands Decider 2B](https://www.anchorterminal.com/compare/gliclass-vs-strands-decider.md)\n- [GLiClass vs Jev](https://www.anchorterminal.com/compare/gliclass-vs-typesafe-jev.md)\n- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)\n- [Kev vs ScaleDown](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-scaledown.md)\n- [Liquid d1 vs ScaleDown](https://www.anchorterminal.com/compare/liquid-d1-vs-scaledown.md)\n- [Microsoft-Decision-1 vs ScaleDown](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-scaledown.md)\n- [Drex 1.5 vs ScaleDown](https://www.anchorterminal.com/compare/nace-drex-vs-scaledown.md)\n- [OpenAI Decisions API vs ScaleDown](https://www.anchorterminal.com/compare/openai-decisions-api-vs-scaledown.md)\n- [pplx-decider vs ScaleDown](https://www.anchorterminal.com/compare/pplx-decider-vs-scaledown.md)\n- [ScaleDown vs SPEV](https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.md)\n- [ScaleDown vs Strands Decider 2B](https://www.anchorterminal.com/compare/scaledown-vs-strands-decider.md)\n- [ScaleDown vs Jev](https://www.anchorterminal.com/compare/scaledown-vs-typesafe-jev.md)\n- [ScaleDown vs Vela 2.0](https://www.anchorterminal.com/compare/scaledown-vs-vela.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-15", "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": "GLiClass vs ScaleDown", "url": "" } ], "description": "GLiClass scores 49.9 (D) to ScaleDown's 48.6 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "GLiClass D 49.9", "ScaleDown D 48.6", "scores" ], "h1": "GLiClass vs ScaleDown", "image": "https://www.anchorterminal.com/assets/og/compare-gliclass-vs-scaledown.png", "path": "/compare/gliclass-vs-scaledown", "published": "2026-10-01", "section": "tools", "title": "GLiClass vs ScaleDown for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-15", "url": "https://www.anchorterminal.com/compare/gliclass-vs-scaledown" }, "tokens": { "markdown": 2750, "slim": 730 }, "version": 1 }