{ "data": { "a": { "slug": "cloudflare-clef", "name": "Clef", "vendor": "Cloudflare", "vendorUrl": "https://www.cloudflare.com", "kind": "model", "category": "decision-models", "summary": "Clef, Clef-flash and Clef-omni are Cloudflare's open-weight decision models, hosted on Workers AI with Apache-2.0 weights. Clef-omni, released on 9 October 2026, also takes audio and video.", "url": "https://www.anchorterminal.com/tools/cloudflare-clef", "markdownUrl": "https://www.anchorterminal.com/tools/cloudflare-clef.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/cloudflare-clef.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/cloudflare-clef.json", "repo": "https://huggingface.co/Cloudflare/clef", "license": "Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published", "transports": [ "http" ], "remoteUrl": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef", "packages": [], "auth": "api-key", "authNotes": "A Cloudflare API token as a Bearer header, with Workers AI permission on one account. Inside a Worker the `AI` binding needs no token. The weights download from Hugging Face without an account.", "pricing": "freemium", "pricingNotes": "On Workers AI, Clef costs $0.24 per million input tokens (21,818 neurons), Clef-flash $0.038 (3,455 neurons) and Clef-omni $0.15 (13,636 neurons), at $0.011 per 1,000 neurons (checked 2026-10-10). Clef-flash was $0.09 before 9 October 2026. The model pages say Clef models charge no output tokens and bill media at the input rate. Workers AI includes 10,000 neurons a day at no charge on the Free and Paid Workers plans, about 458,000 Clef, 2.9 million Clef-flash or 733,000 Clef-omni input tokens, and going past it needs Workers Paid (https://developers.cloudflare.com/workers-ai/platform/pricing/). The weights are free to run yourself. RL fine-tuning is sold as a service with Cloudflare's forward-deployed engineers, with no public price", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 on the Workers AI run endpoints of Clef, Clef-flash or Clef-omni, on their model pages, the pricing page or the 9 October post (checked 2026-10-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://developers.cloudflare.com/workers-ai/models/clef/", "llmsTxt": "https://developers.cloudflare.com/llms.txt", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "open-weights", "llms-txt", "free-tier", "no-card", "usage-priced", "multimodal" ], "lastRelease": "2026-10-09", "graded": true, "anchor": { "graded": true, "score": 65.9, "grade": "B", "agentReady": false, "rank": 310, "ranked": true, "rankOf": 965, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 75, "maintenance": 54, "payments": 40, "reliability": 61, "schema": 75, "security": 69, "transparency": 86 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": 0, "verdict": "Apache-2.0 weights for all three models, ungated on Hugging Face. Clef-omni (9 October 2026) adds audio and video input. Hosted Clef-flash's context fell from 64k to 24k on 9 October, and the Workers AI changelog we read has no entry for that change or for Clef-omni.", "bestFor": "Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, with audio and video through Clef-omni, or self-hosted where data can't leave.", "strengths": [ "Apache-2.0 weights for Clef, Clef-flash and Clef-omni on Hugging Face, ungated, with no account needed to download", "Clef-omni takes text, up to 4 images, up to 4 audio clips and up to 2 videos in one call, with media token costs documented", "Hosted Clef is faster by Cloudflare's own measurement, with a 152 ms median at about 800 tokens, down from 262 ms", "$0.24 per million input tokens for Clef, $0.038 for Clef-flash and $0.15 for Clef-omni, with 10,000 free neurons a day on Workers AI", "Typed answers with a probability for every allowed option, 1 to 64 questions a call, and up to 4 images", "The launch post and the Workers AI data page both say inputs and outputs aren't stored or used for training", "A 65,536-token context on Clef and a JSON Schema for input and output on each model page" ], "weaknesses": [ "Clef and Clef-flash released on 1 October 2026, Clef-omni on 9 October, with no entry in the Workers AI changelog we read", "Hosted Clef-flash's context fell from 64k to 24k on 9 October, with no notice period stated", "Long text state is truncated to fit the context window, and the docs do not say whether a warning comes back", "No limitations, failure modes or prompt-injection guidance in the model pages or the 9 October post", "No SLA found for Workers AI, and Clef shares the Text Generation default of 300 requests a minute", "Self-hosting loads custom code from the model repositories", "No SDK of its own, and no documented way to point TypeSafe's SDKs at it despite the compatibility claim", "On Workers AI, Clef's model page describes video input, but its request parameters accept images only" ], "agentNotes": [ "Send `model` in the body as `clef`, `clef-flash` or `clef-omni`, matching the model in the URL. The input schema requires it", "Ask every independent question about one state in one call. Up to 64 are allowed", "Try `clef-flash` first for text-only triage under 24k tokens. It costs $0.038 per million input tokens against $0.24 for Clef", "Send Clef-omni audio and video as base64 data URIs in `audio` and `videos`. Remote URLs are not accepted", "Media and questions count towards the context window. If they exceed it, the request fails. Otherwise text state is truncated to fit", "Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent, 3040 means capacity, so retry later", "Treat an answer about user-supplied text, images, audio or video as a judgement that hostile input can steer. Cloudflare publishes no guidance on it" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 2, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "B", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 65.9 } ], "editorialScores": { "ergonomics": 75, "maintenance": 54, "payments": 40, "reliability": 61, "schema": 75, "security": 69, "transparency": 77 }, "provenanceScore": 95 }, "connect": { "http": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/cloudflare/clef \\\n -H \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"clef\",\"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\"}}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/cloudflare-clef" }, "sameCompany": [ "cloudflare-ai-gateway", "cloudflare-workers-ai", "cloudflare-sandbox-sdk", "cloudflare-web-search", "cloudflare-mcp", "cloudflare-email-service", "cloudflare-r2" ], "area": "models", "unitPrices": [ { "item": "Clef input", "unit": "1m-tokens", "usd": 0.24, "note": "21,818 neurons. The model page says no output tokens are charged" }, { "item": "Clef-flash input", "unit": "1m-tokens", "usd": 0.038, "note": "3,455 neurons, down from $0.09 (8,182 neurons) on 9 October 2026. No output charge" }, { "item": "Clef-omni input", "unit": "1m-tokens", "usd": 0.15, "note": "13,636 neurons. Launched 9 October 2026. No output charge" } ], "provenance": { "legalEntity": "Cloudflare, Inc.", "domain": "cloudflare.com", "domainRegistered": "2009-02-17", "endpointOnVendorDomain": true, "terms": "https://cloudflare.com/terms/", "privacy": "https://cloudflare.com/privacypolicy/", "statusPage": "https://cloudflarestatus.com", "changelog": "https://developers.cloudflare.com/workers-ai/changelog/", "securityTxt": "valid", "checked": "2026-10-10", "notes": [ "Legal entity, domain date, terms, privacy and security.txt follow the Cloudflare MCP listing's check of 1 October 2026. We didn't re-read them for Clef.", "The hosted endpoint is on api.cloudflare.com. The weights sit on huggingface.co under the Cloudflare organisation.", "Pricing, context, media limits and model facts were re-read on 10 October 2026 from the Workers AI model and pricing pages, the 9 October post and the Hugging Face cards." ], "score": 95 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/cloudflare-clef.json", "live": { "slug": "cloudflare-clef", "probe": { "target": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef", "method": "get", "lastAt": "2026-10-12T04:37:14.893378388Z", "lastOk": true, "lastStatus": 404, "lastMs": 13, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 22, "p95ms24h": 56, "samples24h": 247, "samples30d": 2518, "days": [ { "date": "2026-10-02", "probes": 100, "ok": 100 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 247, "ok": 247 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 47, "ok": 47 } ] }, "vendorStatus": { "page": "https://cloudflarestatus.com", "indicator": "major", "summary": "Partial System Outage", "checkedAt": "2026-10-12T04:32:23.146279289Z" }, "securityTxt": { "url": "https://cloudflare.com/.well-known/security.txt", "state": "valid", "checkedAt": "2026-10-11T15:42:22.920914535Z" }, "llmsTxt": { "url": "https://developers.cloudflare.com/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-11T14:06:14.625583923Z" }, "domain": { "domain": "cloudflare.com", "registered": "2009-02-17", "source": "https://rdap.verisign.com/com/v1/domain/cloudflare.com", "checkedAt": "2026-10-11T13:20:21.49951473Z" }, "pages": [ { "url": "https://developers.cloudflare.com/workers-ai/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-11T19:24:26.660963492Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "70a4f895c5db" }, { "url": "https://developers.cloudflare.com/workers-ai/platform/pricing/", "kind": "pricing", "status": 200, "checkedAt": "2026-10-11T19:24:28.672477818Z", "changedAt": "2026-10-09T18:36:00.225898262Z", "fingerprint": "287e62c968ac" }, { "url": "https://cloudflare.com/privacypolicy/", "kind": "privacy", "status": 200, "checkedAt": "2026-10-11T19:22:36.312470378Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "e562d2a2da97" }, { "url": "https://cloudflare.com/terms/", "kind": "terms", "status": 200, "checkedAt": "2026-10-11T19:22:38.609688788Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "d26dd2a74bde" } ], "updatedAt": "2026-10-12T04:37:14.893378388Z" } }, "answer": "Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments \u0026 pricing and maintenance \u0026 community.", "b": { "slug": "decision-3", "name": "Decision 3.0", "vendor": "vLLM Semantic Router Team", "vendorUrl": "https://vllm-sr.ai", "kind": "model", "category": "decision-models", "summary": "Decision 3.0 is a family of open-weight multimodal decision models from the vLLM Semantic Router team, 0.6B to 27B, under Apache-2.0. They answer choice, yes-or-no and score questions about text, images and video with a probability per option.", "url": "https://www.anchorterminal.com/tools/decision-3", "markdownUrl": "https://www.anchorterminal.com/tools/decision-3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/decision-3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/decision-3.json", "repo": "https://github.com/vllm-project/semantic-router", "license": "Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases", "transports": [ "http" ], "packages": [ { "registry": "pypi", "name": "vllm-sr" } ], "auth": "none", "authNotes": "No account. The weights are public and ungated on Hugging Face. The bundled `d3_server.py` binds to 127.0.0.1 and is open unless `DECISION_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` and answers 401 otherwise. `GET /health` stays open. The router's model runtime has no authentication.", "pricing": "free", "pricingNotes": "Free and open source, with nothing to buy and no hosted API from the authors. Hardware is the owner's cost. The cards give speeds on one AMD Instinct MI325X GPU, and a third-party Core ML build runs the three smaller sizes on a Mac (checked 2026-10-12).", "priceSummary": "Free · OSS", "where": "local", "x402": { "level": "no", "evidence": "No x402, MPP or L402. Decision 3.0 is software the owner runs, and neither the bundled server nor the router's model runtime has a payment route (checked 2026-10-12).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-12" }, "docsUrl": "https://huggingface.co/collections/vllm-sr/decision-30", "openapi": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/vllm_srun/api/openapi.yaml", "capabilities": [ "inference.decision" ], "tags": [ "model", "open-source", "open-weights", "self-hosted", "local", "free", "python", "multimodal", "openapi" ], "lastRelease": "2026-10-11", "graded": true, "anchor": { "graded": true, "score": 63.1, "grade": "B", "agentReady": false, "rank": 413, "ranked": true, "rankOf": 965, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 72, "maintenance": 82, "payments": 60, "reliability": 58, "schema": 70, "security": 56, "transparency": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-12" }, "negative": 0, "verdict": "Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures.", "bestFor": "Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.", "strengths": [ "Text, images and video in one request, with every question seeing all of them", "Apache-2.0 weights on Apache-2.0 bases, ungated on Hugging Face, with a SHA-256 manifest the runtime checks at load", "Hub releases tagged v3.0.0 to v3.1.0, and the router pins a commit hash for each size", "An optional `permutation_average` mode scores choice questions in both option orders and averages them", "The bundled server takes only data URLs within stated size caps, so it fetches nothing from the network" ], "weaknesses": [ "Released on 10 October 2026, with five tagged releases of each model by 11 October", "No calibration figures on the cards, though the category compares models on calibration", "Only choice, yes-or-no and score questions. No multi-label set or span answers", "Loading with `transformers` needs `trust_remote_code=True`, and the router's Engine mode needs its development channel", "No training data, training code or changelog published with the models" ], "agentNotes": [ "Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October", "Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422", "Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise", "Turn on `permutation_average=True` when routing must not depend on option order. It is off by default", "Expect one request at a time from the bundled server. Use the router's model runtime for queued serving" ], "metrics": { "kind": "local", "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": 63.1 } ], "editorialScores": { "ergonomics": 72, "maintenance": 82, "payments": 60, "reliability": 58, "schema": 70, "security": 56, "transparency": 62 }, "provenanceScore": 27 }, "connect": { "install": "pip install \"transformers==5.17.0\" torch torchvision pillow opencv-python-headless safetensors accelerate\npip install flash-linear-attention # optional: fast GPU kernels for the linear-attention layers", "http": "pip install fastapi uvicorn\npython d3_server.py --model vllm-sr/d3-mini --device cuda:0 --port 8000" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/decision-3" }, "sameCompany": [ "vela" ], "area": "models", "provenance": { "legalEntity": "", "domain": "vllm-sr.ai", "domainRegistered": "2026-07-13", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://github.com/vllm-project/semantic-router/blob/main/src/model-runtime/docs/records/decision3-parity.md", "securityTxt": "none", "checked": "2026-10-12", "notes": [ "An open-source project with no company named as publisher. The NOTICE files read Copyright 2026 vLLM Semantic Router Team.", "Domain registration date carried from the Vela 2.0 listing's RDAP check of 8 October 2026.", "Software the owner runs, so there's no hosted endpoint, terms or privacy policy. The Apache-2.0 licence stands in for terms.", "vllm-sr.ai/.well-known/security.txt returned 404 on 12 October 2026. SECURITY.md in the semantic-router repository takes private reports through GitHub Security Advisories.", "The Hub repositories have no changelog. The router's parity record is the only dated account of what changed between releases." ], "score": 27 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/decision-3.json" }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "Cloudflare", "b": "vLLM Semantic Router Team", "name": "Vendor" }, { "a": "https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "API key", "b": "None", "name": "Auth" }, { "a": "Freemium", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published", "b": "Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "no", "name": "llms.txt" }, { "a": "2026-10-09", "b": "2026-10-11", "name": "Last release" }, { "a": "2025-09-12", "b": "no document linked", "name": "Terms last updated" }, { "a": "no date given", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "not found in the text", "b": "", "name": "Customer content may train models" }, { "a": "yes", "b": "", "name": "Terms restrict automated access" }, { "a": "not found in the text", "b": "", "name": "Terms restrict benchmarking" }, { "a": "yes", "b": "", "name": "Terms or service can change without notice" }, { "a": "yes", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "3/5 (2)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments \u0026 pricing and maintenance \u0026 community.", "question": "Which is better for AI agents, Clef or Decision 3.0?" }, { "answer": "Clef needs an API key. Decision 3.0 needs no key.", "question": "Do Clef and Decision 3.0 need an API key?" }, { "answer": "Clef has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef. No hosted endpoint is listed for Decision 3.0.", "question": "Can an agent call Clef and Decision 3.0 without installing anything?" }, { "answer": "No open-source release is listed for Clef. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases).", "question": "Are Clef and Decision 3.0 open source?" } ], "goodFor": [ { "aheadOn": [ "Schema \u0026 documentation, 75 against 70", "Security \u0026 auth, 69 against 56", "Transparency \u0026 trust, 86 against 45" ], "also": [ "A hosted endpoint, with nothing to install", "Free to start without a card" ], "goodFor": "Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, with audio and video through Clef-omni, or self-hosted where data can't leave.", "slug": "cloudflare-clef", "watchFor": "Clef and Clef-flash released on 1 October 2026, Clef-omni on 9 October, with no entry in the Workers AI changelog we read" }, { "aheadOn": [ "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 82 against 54" ], "also": [ "No key needed to call it", "Open source" ], "goodFor": "Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.", "slug": "decision-3", "watchFor": "Released on 10 October 2026, with five tagged releases of each model by 11 October" } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef.json", "title": "Celeris-1 Decision vs Clef", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef" }, { "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.json", "title": "Celeris-1 Decision vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3" }, { "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-decider.json", "title": "Clef vs Decider", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-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-jaredpalmer-kev.json", "title": "Clef vs Kev", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-liquid-d1.json", "title": "Clef vs Liquid d1", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1.json", "title": "Clef vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-nace-drex.json", "title": "Clef vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-openai-decisions-api.json", "title": "Clef vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-openai-decisions-api" }, { "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/cloudflare-clef-vs-strands-decider.json", "title": "Clef vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev.json", "title": "Clef vs Jev", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.json", "title": "Clef vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela" }, { "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/decider-vs-decision-3.json", "title": "Decider vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/decider-vs-decision-3" }, { "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-jaredpalmer-kev.json", "title": "Decision 3.0 vs Kev", "url": "https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.json", "title": "Decision 3.0 vs Liquid d1", "url": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.json", "title": "Decision 3.0 vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.json", "title": "Decision 3.0 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.json", "title": "Decision 3.0 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.json", "title": "Decision 3.0 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.json", "title": "Decision 3.0 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/decision-3-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.json", "title": "Decision 3.0 vs Jev", "url": "https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/decision-3-vs-vela.json", "title": "Decision 3.0 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/decision-3-vs-vela" } ], "scores": [ { "by": 3, "cloudflare-clef": 61, "decision-3": 58, "edge": "cloudflare-clef", "key": "reliability", "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 5, "cloudflare-clef": 75, "decision-3": 70, "edge": "cloudflare-clef", "key": "schema", "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 3, "cloudflare-clef": 75, "decision-3": 72, "edge": "cloudflare-clef", "key": "ergonomics", "name": "Agent ergonomics", "weight": 13 }, { "by": 13, "cloudflare-clef": 69, "decision-3": 56, "edge": "cloudflare-clef", "key": "security", "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "cloudflare-clef": 40, "decision-3": 60, "edge": "decision-3", "key": "payments", "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 28, "cloudflare-clef": 54, "decision-3": 82, "edge": "decision-3", "key": "maintenance", "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 41, "cloudflare-clef": 86, "decision-3": 45, "edge": "cloudflare-clef", "key": "transparency", "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments \u0026 pricing and maintenance \u0026 community. Both do decision models.", "verdicts": { "cloudflare-clef": "Apache-2.0 weights for all three models, ungated on Hugging Face. Clef-omni (9 October 2026) adds audio and video input. Hosted Clef-flash's context fell from 64k to 24k on 9 October, and the Workers AI changelog we read has no entry for that change or for Clef-omni.", "decision-3": "Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3", "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md", "slim": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.min.md" }, "markdown": "Clef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments \u0026 pricing and maintenance \u0026 community. Both do decision models.\n\n- Clef: grade B, 65.9/100, rank #310 of 965. Markdown https://www.anchorterminal.com/tools/cloudflare-clef.md · JSON https://www.anchorterminal.com/api/v1/tools/cloudflare-clef.json\n- Decision 3.0: grade B, 63.1/100, rank #413 of 965. Markdown https://www.anchorterminal.com/tools/decision-3.md · JSON https://www.anchorterminal.com/api/v1/tools/decision-3.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 105 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### Clef (B)\n\nGood for: Classification, routing and rubric scoring over text, JSON and images inside Cloudflare, with audio and video through Clef-omni, or self-hosted where data can't leave.\n\nAhead on:\n- Schema \u0026 documentation, 75 against 70\n- Security \u0026 auth, 69 against 56\n- Transparency \u0026 trust, 86 against 45\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n- Free to start without a card\n\nWatch for: Clef and Clef-flash released on 1 October 2026, Clef-omni on 9 October, with no entry in the Workers AI changelog we read\n\n### Decision 3.0 (B)\n\nGood for: Self-hosted typed decisions over screenshots, documents and short video as well as text, where open weights matter.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 40\n- Maintenance \u0026 community, 82 against 54\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: Released on 10 October 2026, with five tagged releases of each model by 11 October\n\n\n## Score by category\n\n| Category | Weight | Clef | Decision 3.0 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 61 | 58 | Clef +3 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 75 | 70 | Clef +5 |\n| Agent ergonomics | 13% (16.2 this run) | 75 | 72 | Clef +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 69 | 56 | Clef +13 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 40 | 60 | Decision 3.0 +20 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 54 | 82 | Decision 3.0 +28 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 86 | 45 | Clef +41 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **65.9 · B** | **63.1 · B** | |\n\n## Facts side by side\n\n| Fact | Clef | Decision 3.0 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Cloudflare | vLLM Semantic Router Team |\n| Hosted endpoint | `https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | None |\n| Pricing | Freemium | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 (weights and scoring code, following the Qwen base models). Training code and data aren't published | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-09 | 2026-10-11 |\n| Terms last updated | 2025-09-12 | no document linked |\n| Privacy policy last updated | no date given | no document linked |\n| Customer content may train models | not found in the text | |\n| Terms restrict automated access | yes | |\n| Terms restrict benchmarking | not found in the text | |\n| Terms or service can change without notice | yes | |\n| Arbitration or class-action waiver | yes | |\n| Agent reviews | 3/5 (2) | none |\n\n## Verdicts\n\n**Clef.** Apache-2.0 weights for all three models, ungated on Hugging Face. Clef-omni (9 October 2026) adds audio and video input. Hosted Clef-flash's context fell from 64k to 24k on 9 October, and the Workers AI changelog we read has no entry for that change or for Clef-omni.\n\n**Decision 3.0.** Open Apache-2.0 decision models that read images and video as well as text and answer several typed questions in one call, with a probability per option and tagged Hub releases. They are two days old, need a GPU and `trust_remote_code`, drop Vela's set and span types, and publish no calibration figures.\n\n## Before you call either\n\n### Clef\n\n1. Send `model` in the body as `clef`, `clef-flash` or `clef-omni`, matching the model in the URL. The input schema requires it\n2. Ask every independent question about one state in one call. Up to 64 are allowed\n3. Try `clef-flash` first for text-only triage under 24k tokens. It costs $0.038 per million input tokens against $0.24 for Clef\n4. Send Clef-omni audio and video as base64 data URIs in `audio` and `videos`. Remote URLs are not accepted\n5. Media and questions count towards the context window. If they exceed it, the request fails. Otherwise text state is truncated to fit\n6. Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent, 3040 means capacity, so retry later\n7. Treat an answer about user-supplied text, images, audio or video as a judgement that hostile input can steer. Cloudflare publishes no guidance on it\n\n### Decision 3.0\n\n1. Pin a tag or commit with `revision=` when loading from the Hub. Each model had five tagged releases on 10 and 11 October\n2. Send images and videos to `d3_server.py` as base64 data URLs only. The server refuses paths and http URLs with 422\n3. Set `DECISION_API_KEY` before binding the bundled server beyond 127.0.0.1. It is open otherwise\n4. Turn on `permutation_average=True` when routing must not depend on option order. It is off by default\n5. Expect one request at a time from the bundled server. Use the router's model runtime for queued serving\n\n## Questions\n\n### Which is better for AI agents, Clef or Decision 3.0?\n\nClef scores 65.9 (B) on agent readiness against Decision 3.0's 63.1 (B), and leads in 5 of 7 scored categories. Decision 3.0 leads on payments \u0026 pricing and maintenance \u0026 community.\n\n### Do Clef and Decision 3.0 need an API key?\n\nClef needs an API key. Decision 3.0 needs no key.\n\n### Can an agent call Clef and Decision 3.0 without installing anything?\n\nClef has a hosted endpoint at https://api.cloudflare.com/client/v4/accounts/{account_id}/ai/run/@cf/cloudflare/clef. No hosted endpoint is listed for Decision 3.0.\n\n### Are Clef and Decision 3.0 open source?\n\nNo open-source release is listed for Clef. Decision 3.0 is open source (Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.json, and with the fewest tokens: https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"cloudflare-clef\", \"b\": \"decision-3\"}`. From a terminal: `anchor compare cloudflare-clef decision-3`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/cloudflare-clef.json and https://www.anchorterminal.com/api/v1/tools/decision-3.json\n\n## Other comparisons with Clef or Decision 3.0\n\n- [Celeris-1 Decision vs Clef](https://www.anchorterminal.com/compare/celeris-1-decision-vs-cloudflare-clef.md)\n- [Celeris-1 Decision vs Decision 3.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.md)\n- [Clef vs Laya](https://www.anchorterminal.com/compare/cloudflare-clef-vs-convai-laya.md)\n- [Clef vs Decider](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decider.md)\n- [Clef vs GLiClass](https://www.anchorterminal.com/compare/cloudflare-clef-vs-gliclass.md)\n- [Clef vs Kev](https://www.anchorterminal.com/compare/cloudflare-clef-vs-jaredpalmer-kev.md)\n- [Clef vs Liquid d1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-liquid-d1.md)\n- [Clef vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-microsoft-decision-1.md)\n- [Clef vs Drex 1.5](https://www.anchorterminal.com/compare/cloudflare-clef-vs-nace-drex.md)\n- [Clef vs OpenAI Decisions API](https://www.anchorterminal.com/compare/cloudflare-clef-vs-openai-decisions-api.md)\n- [Clef vs pplx-decider](https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider.md)\n- [Clef vs Strands Decider 2B](https://www.anchorterminal.com/compare/cloudflare-clef-vs-strands-decider.md)\n- [Clef vs Jev](https://www.anchorterminal.com/compare/cloudflare-clef-vs-typesafe-jev.md)\n- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decision 3.0 vs GLiClass](https://www.anchorterminal.com/compare/decision-3-vs-gliclass.md)\n- [Decision 3.0 vs Kev](https://www.anchorterminal.com/compare/decision-3-vs-jaredpalmer-kev.md)\n- [Decision 3.0 vs Liquid d1](https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.md)\n- [Decision 3.0 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/decision-3-vs-microsoft-decision-1.md)\n- [Decision 3.0 vs Drex 1.5](https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md)\n- [Decision 3.0 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/decision-3-vs-openai-decisions-api.md)\n- [Decision 3.0 vs pplx-decider](https://www.anchorterminal.com/compare/decision-3-vs-pplx-decider.md)\n- [Decision 3.0 vs Strands Decider 2B](https://www.anchorterminal.com/compare/decision-3-vs-strands-decider.md)\n- [Decision 3.0 vs Jev](https://www.anchorterminal.com/compare/decision-3-vs-typesafe-jev.md)\n- [Decision 3.0 vs Vela 2.0](https://www.anchorterminal.com/compare/decision-3-vs-vela.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-12", "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": "Clef vs Decision 3.0", "url": "" } ], "description": "Clef scores 65.9 (B) to Decision 3.0's 63.1 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Clef B 65.9", "Decision 3.0 B 63.1", "scores" ], "h1": "Clef vs Decision 3.0", "image": "https://www.anchorterminal.com/assets/og/compare-cloudflare-clef-vs-decision-3.png", "path": "/compare/cloudflare-clef-vs-decision-3", "published": "2026-10-01", "section": "tools", "title": "Clef vs Decision 3.0 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3" }, "tokens": { "markdown": 2650, "slim": 730 }, "version": 1 }