{ "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": 783, "ranked": true, "rankOf": 950, "categoryRank": 10, "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": "2026-10-09T16:55:07.207346386Z" }, { "registry": "pypi", "name": "gliclass", "version": "0.1.20", "released": "2026-07-21", "seenAt": "2026-10-09T16:55:07.014721965Z" } ], "githubStars": 556, "pypiWeekly": 12735, "securityTxt": { "url": "https://knowledgator.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-09T15:39:16.87234666Z" }, "updatedAt": "2026-10-09T16:55:07.207346386Z" } }, "answer": "pplx-decider scores 62.9 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on payments \u0026 pricing and transparency \u0026 trust.", "b": { "slug": "pplx-decider", "name": "pplx-decider", "vendor": "Perplexity", "vendorUrl": "https://www.perplexity.ai/", "kind": "model", "category": "decision-models", "summary": "pplx-decider is Perplexity's multimodal decision model, a fine-tune of Qwen3.8-27B. It answers yes or no, choice and score questions about text, JSON and images with probabilities, through Perplexity's hosted Decisions API or from open weights on Hugging Face.", "url": "https://www.anchorterminal.com/tools/pplx-decider", "markdownUrl": "https://www.anchorterminal.com/tools/pplx-decider.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pplx-decider.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pplx-decider.json", "repo": "https://huggingface.co/perplexity-ai/pplx-decider-v1.1-27b", "license": "Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service", "transports": [ "http" ], "remoteUrl": "https://api.perplexity.ai/v1/decisions", "packages": [], "auth": "api-key", "authNotes": "Hosted API. Bearer Perplexity API key in the `Authorization` header. A key sent in `x-api-key` returns 401. Keys are created in the API console after a project exists, are shown once, and can be generated and revoked through `/generate_auth_token` and `/revoke_auth_token`. No per-key scopes were found. Weights. The Hugging Face repository is public and not gated, and the bundled server takes an optional `AUTOJEV_API_KEY`.", "pricing": "usage", "pricingNotes": "$0.02 per million input tokens on Perplexity's Decisions API for both `pplx-decider-v1.1-27b` and `pplx-decider-v1-27b`. Output tokens are free and there is no per-request fee. The changelog says v1 launched at $0.04. Usage draws on prepaid credits, and the billing guide asks for a credit card. No free allowance was found. The weights are free to download and need a GPU with about 49 GiB for weights.", "priceSummary": "Pay per use", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the Decisions API guide, the reference, the pricing page or llms.txt, read on 9 October 2026.", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://docs.perplexity.ai/docs/decisions/quickstart", "llmsTxt": "https://docs.perplexity.ai/llms.txt", "openapi": "https://docs.perplexity.ai/openapi-gateway-preview.json", "capabilities": [ "inference.decision" ], "tags": [ "official", "hosted", "model", "open-weights", "multimodal", "openapi", "llms-txt", "usage-priced", "status-page" ], "lastRelease": "2026-10-05", "graded": true, "anchor": { "graded": true, "score": 62.9, "grade": "B", "agentReady": false, "rank": 417, "ranked": true, "rankOf": 950, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 76, "maintenance": 62, "payments": 25, "reliability": 61, "schema": 90, "security": 61, "transparency": 52 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": 0, "verdict": "The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.", "bestFor": "High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.", "strengths": [ "Weights for v1.1 and v1 are public on Hugging Face under Apache-2.0, with training code, config and a data manifest in the repository", "One request takes up to 128 questions about one `state`, mixing `noul`, `choice` and `score`, with under 262,144 input tokens", "$0.02 per million input tokens with free output and no per-request fee, published without a login", "OpenAPI 3.0.3 description, llms.txt and Markdown pages for the guide and reference", "Rate limit stated as 10 requests a second per organisation, with `Retry-After` on 429 and `x-ratelimit-*` headers" ], "weaknesses": [ "The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee", "The official Python SDK at 0.43.8 has no Decisions method. The guide uses a plain HTTP client", "An image over 2,048 tiles is not rejected. The request waits about a minute and returns 504", "The zero-retention statement on the Privacy and Security page names only the Chat Completions API", "The bundled server in the weights repository caps a question at 8,192 tokens and reads a `playground.html` the v1.1 repository does not include" ], "agentNotes": [ "Send `Authorization: Bearer`. A key in `x-api-key` returns 401 on this endpoint.", "Set `model` on every request. A missing or unknown model returns 400, and the guide shows a `-latest` name rejected.", "Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.", "Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and `error.code` changes type.", "For the weights, use the repository's `autojev` code. The card says default causal inference does not reproduce the evaluated setup." ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.9 } ], "editorialScores": { "ergonomics": 76, "maintenance": 62, "payments": 25, "reliability": 61, "schema": 90, "security": 61, "transparency": 54 }, "provenanceScore": 49 }, "connect": { "http": "curl -X POST https://api.perplexity.ai/v1/decisions \\\n -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"pplx-decider-v1.1-27b\",\"state\":\"The headphones sound great, but the battery stopped charging after two weeks.\",\"questions\":{\"defect\":{\"type\":\"noul\",\"instructions\":\"Does the review report a product defect?\"}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/pplx-decider" }, "area": "models", "unitPrices": [ { "item": "Decision input", "unit": "1m-tokens", "usd": 0.02, "note": "Same price for v1.1 and v1. State, questions and images count as input." }, { "item": "Decision output", "unit": "1m-tokens", "usd": 0, "note": "Output tokens are free. No per-request fee." } ], "provenance": { "legalEntity": "", "domain": "perplexity.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.perplexity.ai/hub/legal/terms-of-service", "privacy": "https://www.perplexity.ai/hub/legal/privacy-notice", "statusPage": "https://status.perplexity.com/", "changelog": "https://docs.perplexity.ai/docs/resources/changelog", "securityTxt": "unknown", "checked": "2026-10-09", "notes": [ "The terms of service and privacy notice linked here are the two the status page links. www.perplexity.ai answered our researcher with a bot check (403) on 9 October 2026, so neither was read.", "No legal entity was established. The pages read name the vendor only as Perplexity, and the Hugging Face organisation is marked as a verified company.", "The status page lists Website, App, Computer and API components, with no Decisions component.", "The changelog dates entries by month. The two Decisions entries are under October 2026.", "docs.perplexity.ai answered 404 for the well-known security.txt. The main site was not readable, so security.txt is unknown. Domain registration was not checked." ], "score": 49 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/pplx-decider.json", "live": { "slug": "pplx-decider", "probe": { "target": "https://api.perplexity.ai/v1/decisions", "method": "get", "lastAt": "2026-10-10T02:07:21.120432319Z", "lastOk": true, "lastStatus": 401, "lastMs": 168, "lastNote": "asks for credentials", "authRequired": true, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 220, "p95ms24h": 1251, "samples24h": 107, "samples30d": 107, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 22, "ok": 22 } ] }, "vendorStatus": { "page": "https://status.perplexity.com", "indicator": "none", "summary": "All Systems Operational", "checkedAt": "2026-10-10T02:06:24.469078521Z" }, "pages": [ { "url": "https://docs.perplexity.ai/docs/resources/changelog", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:38:00.707248662Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "ab545eed1660" }, { "url": "https://www.perplexity.ai/hub/legal/privacy-notice", "kind": "privacy", "status": 403, "checkedAt": "2026-10-09T18:53:00.205668839Z", "changedAt": "0001-01-01T00:00:00Z" }, { "url": "https://www.perplexity.ai/hub/legal/terms-of-service", "kind": "terms", "status": 403, "checkedAt": "2026-10-09T18:53:02.2245445Z", "changedAt": "0001-01-01T00:00:00Z" } ], "updatedAt": "2026-10-10T02:07:21.120432319Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Knowledgator", "b": "Perplexity", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.perplexity.ai/v1/decisions", "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": "free", "b": "free", "name": "Price for decision models" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (library and the model weights we checked)", "b": "Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-07-21", "b": "2026-10-05", "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": "none", "name": "Popularity" } ], "faq": [ { "answer": "pplx-decider scores 62.9 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on payments \u0026 pricing and transparency \u0026 trust.", "question": "Which is better for AI agents, GLiClass or pplx-decider?" }, { "answer": "GLiClass, at free against free for pplx-decider. These are the vendors' published prices for the job.", "question": "Which is cheaper for decision models, GLiClass or pplx-decider?" }, { "answer": "GLiClass needs no key. pplx-decider needs an API key.", "question": "Do GLiClass and pplx-decider need an API key?" }, { "answer": "No hosted endpoint is listed for GLiClass. pplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions.", "question": "Can an agent call GLiClass and pplx-decider 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 pplx-decider.", "question": "Are GLiClass and pplx-decider open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 25", "Transparency \u0026 trust, 64 against 52" ], "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": [ "Reliability, 61 against 43", "Schema \u0026 documentation, 90 against 49", "Agent ergonomics, 76 against 60", "Security \u0026 auth, 61 against 38", "Maintenance \u0026 community, 62 against 44" ], "also": [ "Cheaper for decision models, $0 against $0 per 1M tokens", "A hosted endpoint, with nothing to install" ], "goodFor": "High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.", "slug": "pplx-decider", "watchFor": "The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee" } ], "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-pplx-decider.json", "title": "Celeris-1 Decision vs pplx-decider", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-pplx-decider" }, { "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-pplx-decider.json", "title": "Clef vs pplx-decider", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider" }, { "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-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/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-pplx-decider.json", "title": "Decider vs pplx-decider", "url": "https://www.anchorterminal.com/compare/decider-vs-pplx-decider" }, { "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-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-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-pplx-decider.json", "title": "Kev vs pplx-decider", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-pplx-decider.json", "title": "Liquid d1 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider.json", "title": "OpenAI Decisions API vs pplx-decider", "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider.json", "title": "pplx-decider vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev.json", "title": "pplx-decider vs Jev", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela.json", "title": "pplx-decider vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela" } ], "scores": [ { "by": 18, "edge": "pplx-decider", "gliclass": 43, "key": "reliability", "name": "Reliability", "pplx-decider": 61, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 41, "edge": "pplx-decider", "gliclass": 49, "key": "schema", "name": "Schema \u0026 documentation", "pplx-decider": 90, "weight": 13 }, { "by": 16, "edge": "pplx-decider", "gliclass": 60, "key": "ergonomics", "name": "Agent ergonomics", "pplx-decider": 76, "weight": 13 }, { "by": 23, "edge": "pplx-decider", "gliclass": 38, "key": "security", "name": "Security \u0026 auth", "pplx-decider": 61, "weight": 14 }, { "by": 35, "edge": "gliclass", "gliclass": 60, "key": "payments", "name": "Payments \u0026 pricing", "pplx-decider": 25, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 18, "edge": "pplx-decider", "gliclass": 44, "key": "maintenance", "name": "Maintenance \u0026 community", "pplx-decider": 62, "weight": 7 }, { "by": 12, "edge": "gliclass", "gliclass": 64, "key": "transparency", "name": "Transparency \u0026 trust", "pplx-decider": 52, "weight": 7 } ], "summary": "pplx-decider scores 62.9 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on payments \u0026 pricing and transparency \u0026 trust. Both do decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens.", "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.", "pplx-decider": "The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider", "json": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.md", "slim": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.min.md" }, "markdown": "pplx-decider scores 62.9 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on payments \u0026 pricing and transparency \u0026 trust. Both do decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens.\n\n- GLiClass: grade D, 49.9/100, rank #783 of 950. Markdown https://www.anchorterminal.com/tools/gliclass.md · JSON https://www.anchorterminal.com/api/v1/tools/gliclass.json\n- pplx-decider: grade B, 62.9/100, rank #417 of 950. Markdown https://www.anchorterminal.com/tools/pplx-decider.md · JSON https://www.anchorterminal.com/api/v1/tools/pplx-decider.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 66 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/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- Payments \u0026 pricing, 60 against 25\n- Transparency \u0026 trust, 64 against 52\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### pplx-decider (B)\n\nGood for: High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.\n\nAhead on:\n- Reliability, 61 against 43\n- Schema \u0026 documentation, 90 against 49\n- Agent ergonomics, 76 against 60\n- Security \u0026 auth, 61 against 38\n- Maintenance \u0026 community, 62 against 44\n\nAlso in its favour:\n- Cheaper for decision models, $0 against $0 per 1M tokens\n- A hosted endpoint, with nothing to install\n\nWatch for: The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee\n\n\n## Score by category\n\n| Category | Weight | GLiClass | pplx-decider | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 43 | 61 | pplx-decider +18 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 49 | 90 | pplx-decider +41 |\n| Agent ergonomics | 13% (16.2 this run) | 60 | 76 | pplx-decider +16 |\n| Security \u0026 auth | 14% (17.5 this run) | 38 | 61 | pplx-decider +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 25 | GLiClass +35 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 44 | 62 | pplx-decider +18 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 64 | 52 | GLiClass +12 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **49.9 · D** | **62.9 · B** | |\n\n## Facts side by side\n\n| Fact | GLiClass | pplx-decider |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Knowledgator | Perplexity |\n| Hosted endpoint | no (local only) | `https://api.perplexity.ai/v1/decisions` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\n| Price for decision models | free | free |\n| x402 | no | no |\n| Licence | Apache-2.0 (library and the model weights we checked) | Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-07-21 | 2026-10-05 |\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 | none |\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**pplx-decider.** The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.\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### pplx-decider\n\n1. Send `Authorization: Bearer`. A key in `x-api-key` returns 401 on this endpoint.\n2. Set `model` on every request. A missing or unknown model returns 400, and the guide shows a `-latest` name rejected.\n3. Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.\n4. Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and `error.code` changes type.\n5. For the weights, use the repository's `autojev` code. The card says default causal inference does not reproduce the evaluated setup.\n\n## Questions\n\n### Which is better for AI agents, GLiClass or pplx-decider?\n\npplx-decider scores 62.9 (B) on agent readiness against GLiClass's 49.9 (D), and leads in 5 of 7 scored categories. GLiClass leads on payments \u0026 pricing and transparency \u0026 trust.\n\n### Which is cheaper for decision models, GLiClass or pplx-decider?\n\nGLiClass, at free against free for pplx-decider. These are the vendors' published prices for the job.\n\n### Do GLiClass and pplx-decider need an API key?\n\nGLiClass needs no key. pplx-decider needs an API key.\n\n### Can an agent call GLiClass and pplx-decider without installing anything?\n\nNo hosted endpoint is listed for GLiClass. pplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions.\n\n### Are GLiClass and pplx-decider open source?\n\nGLiClass is open source (Apache-2.0 (library and the model weights we checked)). No open-source release is listed for pplx-decider.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.json, and with the fewest tokens: https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"gliclass\", \"b\": \"pplx-decider\"}`. From a terminal: `anchor compare gliclass pplx-decider`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/gliclass.json and https://www.anchorterminal.com/api/v1/tools/pplx-decider.json\n\n## Other comparisons with GLiClass or pplx-decider\n\n- [Celeris-1 Decision vs GLiClass](https://www.anchorterminal.com/compare/celeris-1-decision-vs-gliclass.md)\n- [Celeris-1 Decision vs pplx-decider](https://www.anchorterminal.com/compare/celeris-1-decision-vs-pplx-decider.md)\n- [Clef vs GLiClass](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.md)\n- [Clef vs pplx-decider](https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider.md)\n- [Laya vs GLiClass](https://www.anchorterminal.com/compare/convai-laya-vs-gliclass.md)\n- [Laya vs pplx-decider](https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider.md)\n- [Decider vs GLiClass](https://www.anchorterminal.com/compare/decider-vs-gliclass.md)\n- [Decider vs pplx-decider](https://www.anchorterminal.com/compare/decider-vs-pplx-decider.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 OpenAI Decisions API](https://www.anchorterminal.com/compare/gliclass-vs-openai-decisions-api.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 pplx-decider](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-pplx-decider.md)\n- [Liquid d1 vs pplx-decider](https://www.anchorterminal.com/compare/liquid-d1-vs-pplx-decider.md)\n- [OpenAI Decisions API vs pplx-decider](https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider.md)\n- [pplx-decider vs Strands Decider 2B](https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider.md)\n- [pplx-decider vs Jev](https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev.md)\n- [pplx-decider vs Vela 2.0](https://www.anchorterminal.com/compare/pplx-decider-vs-vela.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "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" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "GLiClass vs pplx-decider", "url": "" } ], "description": "pplx-decider scores 62.9 (B) to GLiClass's 49.9 (D) for decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "GLiClass D 49.9", "pplx-decider B 62.9", "scores" ], "h1": "GLiClass vs pplx-decider", "image": "https://www.anchorterminal.com/assets/og/compare-gliclass-vs-pplx-decider.png", "path": "/compare/gliclass-vs-pplx-decider", "published": "2026-10-01", "section": "tools", "title": "GLiClass vs pplx-decider for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider" }, "tokens": { "markdown": 2550, "slim": 780 }, "version": 1 }