{ "data": { "a": { "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" }, "answer": "Drex 1.5 scores 69.7 (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": "nace-drex", "name": "Drex 1.5", "vendor": "Nace AI, Inc. (Nace.AI)", "vendorUrl": "https://www.nace.ai", "kind": "model", "category": "decision-models", "summary": "Drex 1.5 is Nace.AI's decision model. It returns a probability for each option in typed yes or no, choice and score questions. Hosted at console.nace.ai, with open weights under the Nace AI Open RAIL-M licence.", "url": "https://www.anchorterminal.com/tools/nace-drex", "markdownUrl": "https://www.anchorterminal.com/tools/nace-drex.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nace-drex.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nace-drex.json", "repo": "https://huggingface.co/nace-ai/drex-v1.5", "license": "Hosted API under the Nace AI Terms of Service, last updated 5 May 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT.", "transports": [ "http" ], "remoteUrl": "https://console.nace.ai/v1/systemone", "packages": [ { "registry": "pypi", "name": "nace-sdk" }, { "registry": "npm", "name": "nace-sdk" }, { "registry": "pypi", "name": "nace-mcp" } ], "auth": "api-key", "authNotes": "A key starting nace_sk_, created in the Console dashboard after an emailed-code sign-in and sent as a Bearer header. The key is shown once. An account can hold three active keys, which share its credit and rate limits. Keys can be revoked and rotated, and no scopes are documented. An agent cannot create its own account, because sign-in needs an emailed code.", "pricing": "freemium", "pricingNotes": "drex-v1.5 costs $0.05 per million input tokens, and output tokens are not billed. The price is on the public pricing reference without a login. New accounts get $25 of signup credit, which expires three months after sign-up, and a $5 monthly credit. Each mailbox gets the signup credit once, and disposable domains get none. Without a saved card, requests stop at zero credit with 402 insufficient_credit. A saved card turns on pay-as-you-go, billed every 14 days.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the pricing reference, the API reference or the OpenAPI document (checked 10 October 2026).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": 318, "pypiWeekly": 156, "asOf": "2026-10-10" }, "docsUrl": "https://console.nace.ai/docs/drex", "llmsTxt": "https://drex.nace.ai/llms.txt", "openapi": "https://console.nace.ai/openapi.json", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "open-weights", "llms-txt", "openapi", "python", "typescript", "mcp", "free-tier", "usage-priced", "status-page" ], "lastRelease": "2026-09-28", "graded": true, "anchor": { "graded": true, "score": 69.7, "grade": "B", "agentReady": false, "rank": 173, "ranked": true, "rankOf": 965, "categoryRank": 2, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 85, "maintenance": 65, "payments": 40, "reliability": 80, "schema": 88, "security": 65, "transparency": 63 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-10" }, "negative": -2, "negativeNotes": [ "10 October 2026, read against the public board generated 28 September 2026. The site at www.nace.ai/drex states a Decision Index 0.2.1 score of 58.28 and says Drex 1.5 leads all 71 entries under 10B parameters. The 0.2.1 board has 70 entries, none of them Drex, and its top score is Surogate Rune 26B-A4B v3 at 57.44 (https://huggingface.co/spaces/multimodalart/jev-decision-index/resolve/main/data/index-v0.2.1.json). The Hugging Face card does say the Drex figure is Nace's own run, but the site does not. Deducted 2 as a misleading claim." ], "verdict": "The hosted endpoint has a public OpenAPI document, published limits and pinned model versions, at $0.05 per million input tokens with no output charge. The #1 under 10B claim rests on Nace's own run, since Drex is absent from both public boards. Weights carry Open RAIL-M, which requires a commercial licence above $1 million in revenue or funding.", "bestFor": "Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.", "strengths": [ "Public OpenAPI 3.1 document for POST /v1/systemone, plus llms.txt. Request limits are 512 questions, a 1,048,576-byte body and a 131,072-token state.", "Price per input token on the pricing reference, readable without a login. drex-v1.5 costs $0.05 per million, and output tokens are not billed.", "Rate limits with numbers for the free tier (120 requests a minute) and the paid tier (600), and Retry-After on 429 and 529 responses.", "Pinned model ids (drex-v1.0, drex-v1.5) that stay on their version, with a dated record of the drex-latest alias moves.", "Official Python and TypeScript SDKs (nace-sdk), an MCP server (nace-mcp) with 21 tools, and the weights on Hugging Face." ], "weaknesses": [ "The rank 1 claim comes from Nace's own run on Decision Index 0.3.1, and Drex is not on the public board for 0.3 or 0.2.1.", "The weights are under Open RAIL-M, which restricts commercial use above $1 million in revenue or funding and excludes competing products.", "The data statements conflict. The developer page says no training on your data, while the privacy notice allows input and output to improve the Services.", "No SLA, changelog or readable incident list for the model. Drex has been public for 12 days.", "Sign-up needs an emailed code and a browser step. The $25 signup credit is granted once per mailbox and expires after three months." ], "agentNotes": [ "Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin model drex-v1.5 rather than drex-latest in production.", "Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.", "Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.", "Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.", "Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.", "Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key." ], "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": 69.7 } ], "editorialScores": { "ergonomics": 85, "maintenance": 65, "payments": 40, "reliability": 80, "schema": 88, "security": 65, "transparency": 50 }, "provenanceScore": 75 }, "connect": { "install": "pip install nace-sdk # or: npm install nace-sdk", "http": "curl https://console.nace.ai/v1/systemone \\\n -H \"Authorization: Bearer $NACE_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"drex-v1.5\",\"state\":\"I was charged twice for order A-104.\",\"questions\":{\"refund\":{\"type\":\"noul\",\"instructions\":\"Does the customer ask for a refund?\"}}}'", "claudeCode": "uvx nace-mcp login\nclaude mcp add nace -- uvx nace-mcp" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/nace-drex" }, "area": "models", "unitPrices": [ { "item": "Drex 1.5 input", "unit": "1m-tokens", "usd": 0.05, "note": "Per input token, as reported in usage.input_tokens. The pinned drex-v1.0 costs $0.04." }, { "item": "Drex 1.5 output", "unit": "1m-tokens", "usd": 0, "note": "Reported in usage.output_tokens and not billed." } ], "provenance": { "legalEntity": "Nace AI, Inc.", "domain": "nace.ai", "domainRegistered": "", "endpointOnVendorDomain": true, "terms": "https://www.nace.ai/policies/terms-of-service", "privacy": "https://www.nace.ai/policies/privacy-policy", "statusPage": "https://status.nace.ai/", "changelog": "", "securityTxt": "valid", "checked": "2026-10-10", "notes": [ "The Terms were last updated 5 May 2026, before Drex was released, and no Drex-specific service terms were found.", "The security.txt expires on 9 October 2027. The console changelog URL returned 500 and nace.ai/changelog returned 404.", "The Hugging Face cardData field marks the repository as private, while the Hub API returns it as public and the files download without an account." ], "score": 75 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nace-drex.json", "live": { "slug": "nace-drex", "probe": { "target": "https://console.nace.ai/v1/systemone", "method": "get", "lastAt": "2026-10-12T04:49:08.559669809Z", "lastOk": true, "lastStatus": 405, "lastMs": 200, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 187, "p95ms24h": 313, "samples24h": 247, "samples30d": 430, "days": [ { "date": "2026-10-10", "probes": 134, "ok": 134 }, { "date": "2026-10-11", "probes": 247, "ok": 247 }, { "date": "2026-10-12", "probes": 49, "ok": 49 } ] }, "vendorStatus": { "page": "https://status.nace.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-12T03:24:36.716415285Z" }, "versions": [ { "registry": "npm", "name": "nace-sdk", "version": "0.1.0", "seenAt": "2026-10-11T19:45:26.740095818Z" }, { "registry": "pypi", "name": "nace-mcp", "version": "0.1.0", "released": "2026-10-08", "seenAt": "2026-10-11T19:45:26.993253973Z" }, { "registry": "pypi", "name": "nace-sdk", "version": "0.1.0", "released": "2026-10-08", "seenAt": "2026-10-11T19:45:26.549607691Z" } ], "npmWeekly": 364, "pypiWeekly": 168, "securityTxt": { "url": "https://nace.ai/.well-known/security.txt", "state": "valid", "expires": "2027-10-09T23:54:47.318Z", "checkedAt": "2026-10-11T15:42:55.500940758Z" }, "llmsTxt": { "url": "https://drex.nace.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-11T14:07:09.87004921Z" }, "domain": { "domain": "nace.ai", "registered": "2024-01-30", "source": "https://rdap.identitydigital.services/rdap/domain/nace.ai", "checkedAt": "2026-10-11T13:17:10.993409397Z" }, "pages": [ { "url": "https://www.nace.ai/policies/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-11T19:40:50.422711867Z", "changedAt": "2026-10-11T19:40:50.422711867Z", "fingerprint": "1d31d054e67b" }, { "url": "https://www.nace.ai/policies/terms-of-service", "kind": "terms", "status": 200, "checkedAt": "2026-10-11T19:40:53.373624282Z", "changedAt": "2026-10-11T19:40:53.373624282Z", "fingerprint": "8f6a0971efc2" } ], "updatedAt": "2026-10-12T04:49:08.559669809Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "vLLM Semantic Router Team", "b": "Nace AI, Inc. (Nace.AI)", "name": "Vendor" }, { "a": "no (local only)", "b": "https://console.nace.ai/v1/systemone", "name": "Hosted endpoint" }, { "a": "HTTP", "b": "HTTP", "name": "Transports" }, { "a": "None", "b": "API key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases", "b": "Hosted API under the Nace AI Terms of Service, last updated 5 May 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT.", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-11", "b": "2026-09-28", "name": "Last release" }, { "a": "no document linked", "b": "", "name": "Terms last updated" }, { "a": "no document linked", "b": "", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "318 npm/wk, 156 PyPI/wk", "name": "Popularity" } ], "faq": [ { "answer": "Drex 1.5 scores 69.7 (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, Decision 3.0 or Drex 1.5?" }, { "answer": "Decision 3.0 needs no key. Drex 1.5 needs an API key.", "question": "Do Decision 3.0 and Drex 1.5 need an API key?" }, { "answer": "No hosted endpoint is listed for Decision 3.0. Drex 1.5 has a hosted endpoint at https://console.nace.ai/v1/systemone.", "question": "Can an agent call Decision 3.0 and Drex 1.5 without installing anything?" }, { "answer": "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). No open-source release is listed for Drex 1.5.", "question": "Are Decision 3.0 and Drex 1.5 open source?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 60 against 40", "Maintenance \u0026 community, 82 against 65" ], "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" }, { "aheadOn": [ "Reliability, 80 against 58", "Schema \u0026 documentation, 88 against 70", "Agent ergonomics, 85 against 72", "Security \u0026 auth, 65 against 56", "Transparency \u0026 trust, 63 against 45" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.", "slug": "nace-drex", "watchFor": "The rank 1 claim comes from Nace's own run on Decision Index 0.3.1, and Drex is not on the public board for 0.3 or 0.2.1." } ], "job": { "capability": "inference.decision", "name": "Decision models" }, "others": [ { "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/celeris-1-decision-vs-nace-drex.json", "title": "Celeris-1 Decision vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.json", "title": "Clef vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3" }, { "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/convai-laya-vs-decision-3.json", "title": "Laya vs Decision 3.0", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-decision-3" }, { "json": "https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex.json", "title": "Laya vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/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/decider-vs-nace-drex.json", "title": "Decider vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/decider-vs-nace-drex" }, { "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-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" }, { "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/jaredpalmer-kev-vs-nace-drex.json", "title": "Kev vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-nace-drex.json", "title": "Liquid d1 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex.json", "title": "Microsoft-Decision-1 vs Drex 1.5", "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-openai-decisions-api.json", "title": "Drex 1.5 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-openai-decisions-api" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-pplx-decider.json", "title": "Drex 1.5 vs pplx-decider", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-pplx-decider" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider.json", "title": "Drex 1.5 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-typesafe-jev.json", "title": "Drex 1.5 vs Jev", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/nace-drex-vs-vela.json", "title": "Drex 1.5 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/nace-drex-vs-vela" } ], "scores": [ { "by": 22, "decision-3": 58, "edge": "nace-drex", "key": "reliability", "nace-drex": 80, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 18, "decision-3": 70, "edge": "nace-drex", "key": "schema", "nace-drex": 88, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 13, "decision-3": 72, "edge": "nace-drex", "key": "ergonomics", "nace-drex": 85, "name": "Agent ergonomics", "weight": 13 }, { "by": 9, "decision-3": 56, "edge": "nace-drex", "key": "security", "nace-drex": 65, "name": "Security \u0026 auth", "weight": 14 }, { "by": 20, "decision-3": 60, "edge": "decision-3", "key": "payments", "nace-drex": 40, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 17, "decision-3": 82, "edge": "decision-3", "key": "maintenance", "nace-drex": 65, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 18, "decision-3": 45, "edge": "nace-drex", "key": "transparency", "nace-drex": 63, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Drex 1.5 scores 69.7 (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": { "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.", "nace-drex": "The hosted endpoint has a public OpenAPI document, published limits and pinned model versions, at $0.05 per million input tokens with no output charge. The #1 under 10B claim rests on Nace's own run, since Drex is absent from both public boards. Weights carry Open RAIL-M, which requires a commercial licence above $1 million in revenue or funding." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex", "json": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.md", "slim": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.min.md" }, "markdown": "Drex 1.5 scores 69.7 (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- 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- Drex 1.5: grade B, 69.7/100, rank #173 of 965. Markdown https://www.anchorterminal.com/tools/nace-drex.md · JSON https://www.anchorterminal.com/api/v1/tools/nace-drex.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### 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 65\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### Drex 1.5 (B)\n\nGood for: Routing, triage and yes or no gates inside an agent, where the caller supplies the options and acts on the probabilities. Suited to hosted use at a low per-token price, or to open weights where the licence fits.\n\nAhead on:\n- Reliability, 80 against 58\n- Schema \u0026 documentation, 88 against 70\n- Agent ergonomics, 85 against 72\n- Security \u0026 auth, 65 against 56\n- Transparency \u0026 trust, 63 against 45\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: The rank 1 claim comes from Nace's own run on Decision Index 0.3.1, and Drex is not on the public board for 0.3 or 0.2.1.\n\n\n## Score by category\n\n| Category | Weight | Decision 3.0 | Drex 1.5 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 58 | 80 | Drex 1.5 +22 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 88 | Drex 1.5 +18 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 85 | Drex 1.5 +13 |\n| Security \u0026 auth | 14% (17.5 this run) | 56 | 65 | Drex 1.5 +9 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 40 | 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) | 82 | 65 | Decision 3.0 +17 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 63 | Drex 1.5 +18 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **63.1 · B** | **69.7 · B** | |\n\n## Facts side by side\n\n| Fact | Decision 3.0 | Drex 1.5 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | vLLM Semantic Router Team | Nace AI, Inc. (Nace.AI) |\n| Hosted endpoint | no (local only) | `https://console.nace.ai/v1/systemone` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Apache-2.0 for the weights and the bundled runtime, built on Apache-2.0 Qwen3.5 and Qwen3.8 bases | Hosted API under the Nace AI Terms of Service, last updated 5 May 2026. Weights under the Nace AI Open RAIL-M licence (modified, version 1.0, October 2026), which is not an open-source licence. Businesses above $1 million in revenue or funding need a separate commercial licence, and competing products are excluded. The bundled code/kev package, derived from Jared Palmer's Kev (https://github.com/jaredpalmer/kev), and the GitHub repository are Apache-2.0, and the agent skill is MIT. |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-11 | 2026-09-28 |\n| Terms last updated | no document linked | |\n| Privacy policy last updated | no document linked | |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Popularity | none | 318 npm/wk, 156 PyPI/wk |\n\n## Verdicts\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**Drex 1.5.** The hosted endpoint has a public OpenAPI document, published limits and pinned model versions, at $0.05 per million input tokens with no output charge. The #1 under 10B claim rests on Nace's own run, since Drex is absent from both public boards. Weights carry Open RAIL-M, which requires a commercial licence above $1 million in revenue or funding.\n\n## Before you call either\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### Drex 1.5\n\n1. Call https://console.nace.ai/v1/systemone with Authorization: Bearer nace_sk_..., and pin model drex-v1.5 rather than drex-latest in production.\n2. Stop on 402 insufficient_credit or 402 payment_required until credit is topped up or the unpaid invoice is paid.\n3. Retry 429 and 529 after retry-after-ms. On a 422 for an unknown model, use one of the ids the error message lists.\n4. Keep state below 131,072 tokens and the body below 1,048,576 bytes, and send at most 512 questions per request.\n5. Keep the key on a server. A key in browser code is exposed, and the /v1 routes send no Access-Control-Allow-Origin header.\n6. Check usage.input_tokens and the usage CSV after retries, since /v1/systemone documents no idempotency key.\n\n## Questions\n\n### Which is better for AI agents, Decision 3.0 or Drex 1.5?\n\nDrex 1.5 scores 69.7 (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 Decision 3.0 and Drex 1.5 need an API key?\n\nDecision 3.0 needs no key. Drex 1.5 needs an API key.\n\n### Can an agent call Decision 3.0 and Drex 1.5 without installing anything?\n\nNo hosted endpoint is listed for Decision 3.0. Drex 1.5 has a hosted endpoint at https://console.nace.ai/v1/systemone.\n\n### Are Decision 3.0 and Drex 1.5 open source?\n\nDecision 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). No open-source release is listed for Drex 1.5.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-nace-drex.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"decision-3\", \"b\": \"nace-drex\"}`. From a terminal: `anchor compare decision-3 nace-drex`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/nace-drex.json\n\n## Other comparisons with Decision 3.0 or Drex 1.5\n\n- [Celeris-1 Decision vs Decision 3.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-decision-3.md)\n- [Celeris-1 Decision vs Drex 1.5](https://www.anchorterminal.com/compare/celeris-1-decision-vs-nace-drex.md)\n- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)\n- [Clef vs Drex 1.5](https://www.anchorterminal.com/compare/cloudflare-clef-vs-nace-drex.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs Drex 1.5](https://www.anchorterminal.com/compare/convai-laya-vs-nace-drex.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decider vs Drex 1.5](https://www.anchorterminal.com/compare/decider-vs-nace-drex.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 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- [GLiClass vs Drex 1.5](https://www.anchorterminal.com/compare/gliclass-vs-nace-drex.md)\n- [Kev vs Drex 1.5](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-nace-drex.md)\n- [Liquid d1 vs Drex 1.5](https://www.anchorterminal.com/compare/liquid-d1-vs-nace-drex.md)\n- [Microsoft-Decision-1 vs Drex 1.5](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-nace-drex.md)\n- [Drex 1.5 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/nace-drex-vs-openai-decisions-api.md)\n- [Drex 1.5 vs pplx-decider](https://www.anchorterminal.com/compare/nace-drex-vs-pplx-decider.md)\n- [Drex 1.5 vs Strands Decider 2B](https://www.anchorterminal.com/compare/nace-drex-vs-strands-decider.md)\n- [Drex 1.5 vs Jev](https://www.anchorterminal.com/compare/nace-drex-vs-typesafe-jev.md)\n- [Drex 1.5 vs Vela 2.0](https://www.anchorterminal.com/compare/nace-drex-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": "Decision 3.0 vs Drex 1.5", "url": "" } ], "description": "Drex 1.5 scores 69.7 (B) to Decision 3.0's 63.1 (B) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Decision 3.0 B 63.1", "Drex 1.5 B 69.7", "scores" ], "h1": "Decision 3.0 vs Drex 1.5", "image": "https://www.anchorterminal.com/assets/og/compare-decision-3-vs-nace-drex.png", "path": "/compare/decision-3-vs-nace-drex", "published": "2026-10-01", "section": "tools", "title": "Decision 3.0 vs Drex 1.5 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/decision-3-vs-nace-drex" }, "tokens": { "markdown": 2700, "slim": 780 }, "version": 1 }