{ "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": "Decision 3.0 scores 63.1 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in 6 of 7 scored categories. Liquid d1 leads on transparency \u0026 trust.", "b": { "slug": "liquid-d1", "name": "Liquid d1", "vendor": "Liquid AI", "vendorUrl": "https://www.liquid.ai", "kind": "model", "category": "decision-models", "summary": "d1 is Liquid AI's decision model family. It answers typed yes or no, choice and score questions about text and images with probabilities, through a hosted API and the open-weight d1-3B and d1-omni-600M models.", "url": "https://www.anchorterminal.com/tools/liquid-d1", "markdownUrl": "https://www.anchorterminal.com/tools/liquid-d1.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/liquid-d1.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/liquid-d1.json", "repo": "https://huggingface.co/LiquidAI/d1-3B", "license": "The hosted d1 model is proprietary under Liquid AI's terms of service. The d1-3B and d1-omni-600M weights and model code are under the LFM Open Licence v1.0, which is based on Apache-2.0 and conditions commercial use on annual revenue under $10 million. Training code and data aren't published", "transports": [ "http" ], "remoteUrl": "https://api.liquid.ai/decisions/v1/systemone", "packages": [], "auth": "api-key", "authNotes": "A key created at console.liquid.ai under Dashboard, API Keys, after registering and joining an organisation, sent as a Bearer header. Keys start with `liquid_`. No scopes, expiry or rotation were found in the reviewed documentation. The weights download from Hugging Face without an account.", "pricing": "freemium", "pricingNotes": "The hosted `d1` model costs $0.04 per million input tokens and bills no output tokens, per the launch post of 5 October 2026 (https://www.liquid.ai/blog/d1-decision-model). Each question is billed as its own prompt, and an image counts 1.5 tokens per 32 by 32 pixel patch. A text-only `d1:free` model exists, with no published limits. Liquid's pricing page covers model licensing only. The open weights are free to run, and commercial use is free below $10 million in annual revenue.", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the d1 docs, the launch posts or the terms of service (checked 2026-10-08).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-08" }, "docsUrl": "https://docs.liquid.ai/lfm/models/decision-models", "llmsTxt": "https://docs.liquid.ai/llms.txt", "capabilities": [ "inference.decision" ], "tags": [ "hosted", "model", "open-weights", "source-available", "self-hosted", "llms-txt", "free-tier", "usage-priced" ], "lastRelease": "2026-10-07", "graded": true, "anchor": { "graded": true, "score": 43.5, "grade": "E", "agentReady": false, "rank": 896, "ranked": true, "rankOf": 965, "categoryRank": 14, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 63, "maintenance": 60, "payments": 27, "reliability": 21, "schema": 59, "security": 35, "transparency": 54 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-08" }, "negative": 0, "verdict": "The hosted API costs $0.04 per million input tokens and takes TypeSafe's System One request, and the d1-3B weights run locally through Transformers or llama.cpp. Liquid's terms allow it to train on API content, and no status page, rate limits or error reference were found. The family launched between 22 September and 7 October 2026.", "bestFor": "Classification, routing, yes or no gates and rubric scoring over text and images at a low per-token price, or on your own hardware with d1-3B where data can't leave.", "strengths": [ "$0.04 per million input tokens with no output tokens billed, per the launch post, and a text-only `d1:free` model", "d1-3B (3.12B parameters, 32,768-token context) and d1-omni-600M are ungated on Hugging Face, with GGUF builds", "llama.cpp's server README documents `/v1/systemone` for d1, so the same request runs locally", "The hosted `d1` model accepts up to 8 images a request as Base64 data", "Docs are served as Markdown with an llms.txt index, and say when to use a language model instead" ], "weaknesses": [ "The terms of 30 September 2026 allow Liquid to train on API content, with no opt-out or zero-retention option found", "No status page, rate limits, SLA or error reference found for the hosted API", "The LFM Open Licence v1.0 ends free commercial use at $10 million in annual revenue, so the weights aren't open source", "No OpenAPI file, API changelog or versioned model IDs. The hosted models are `d1` and `d1:free`", "No SDK of its own. TypeSafe's SDKs are the documented clients and don't send images" ], "agentNotes": [ "POST to https://api.liquid.ai/decisions/v1/systemone with a `liquid_` key as a Bearer header. This is not a chat-completions endpoint", "Use `d1` for images. `d1:free` is text-only and answers that it does not accept images", "Send images as Base64 data URLs in `images`, at most 8, with the whole JSON body under 4.5 MB. Remote image URLs are refused", "Budget tokens per question. Each question is billed as its own prompt, with its text and every image counted again", "Don't send confidential content to the hosted API, since the terms allow training on it. Run d1-3B locally for that data" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "E", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 43.5 } ], "editorialScores": { "ergonomics": 63, "maintenance": 60, "payments": 27, "reliability": 21, "schema": 59, "security": 35, "transparency": 46 }, "provenanceScore": 62 }, "connect": { "install": "pip install typesafe-sdk # or: npm install @typesafe-ai/sdk", "http": "curl -s https://api.liquid.ai/decisions/v1/systemone \\\n -H \"Authorization: Bearer $LIQUID_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\":\"d1\",\"state\":\"I have been waiting over three weeks for my order and nobody has responded to my emails.\",\"questions\":{\"is_complaint\":{\"type\":\"noul\",\"instructions\":\"Is this message a complaint from the customer?\"}}}'" }, "letme": { "capability": "https://letme.dev/inference.decision", "tool": "https://letme.dev/liquid-d1" }, "area": "models", "unitPrices": [ { "item": "d1 input", "unit": "1m-tokens", "usd": 0.04, "note": "No output tokens. Each question is billed as its own prompt, images at 1.5 tokens per 32 by 32 pixel patch" } ], "provenance": { "legalEntity": "Liquid AI, Inc.", "domain": "liquid.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": true, "terms": "https://www.liquid.ai/terms-conditions", "privacy": "https://www.liquid.ai/privacy-policy", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-08", "notes": [ "The terms of service (updated 30 September 2026) name Liquid AI, Inc., a Delaware corporation, and Massachusetts law. The privacy policy carries the same date.", "RDAP gives liquid.ai a registration date of 16 December 2017 and a transfer on 20 April 2023. The site footer says the company was established in 2023.", "The hosted endpoint is on api.liquid.ai. The weights sit on huggingface.co under the LiquidAI organisation.", "/.well-known/security.txt returned 404 on www.liquid.ai, liquid.ai and api.liquid.ai.", "No status page is linked from the site, the docs or the launch posts, and status.liquid.ai did not answer our reader. No changelog for the API or the docs was found. docs.liquid.ai/changelog returned 404.", "A trust centre at trust.liquid.ai is hosted by Vanta and renders only with JavaScript, so its contents are unread." ], "score": 62 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/liquid-d1.json", "live": { "slug": "liquid-d1", "probe": { "target": "https://api.liquid.ai/decisions/v1/systemone", "method": "get", "lastAt": "2026-10-12T04:49:06.087875856Z", "lastOk": true, "lastStatus": 404, "lastMs": 135, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 135, "p95ms24h": 361, "samples24h": 247, "samples30d": 886, "days": [ { "date": "2026-10-08", "probes": 93, "ok": 93 }, { "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": 49, "ok": 49 } ] }, "securityTxt": { "url": "https://liquid.ai/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-11T15:42:24.951754851Z" }, "llmsTxt": { "url": "https://docs.liquid.ai/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-11T14:06:58.043799177Z" }, "domain": { "domain": "liquid.ai", "registered": "2017-12-16", "source": "https://rdap.identitydigital.services/rdap/domain/liquid.ai", "checkedAt": "2026-10-11T13:18:35.535693069Z" }, "pages": [ { "url": "https://www.liquid.ai/privacy-policy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-11T19:40:04.846007104Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "42d9e4ba3a39" }, { "url": "https://www.liquid.ai/terms-conditions", "kind": "terms", "status": 200, "checkedAt": "2026-10-11T19:40:07.085258372Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8fd8f3573ffc" } ], "updatedAt": "2026-10-12T04:49:06.087875856Z" } }, "facts": [ { "a": "Model API", "b": "Model API", "name": "Kind" }, { "a": "vLLM Semantic Router Team", "b": "Liquid AI", "name": "Vendor" }, { "a": "no (local only)", "b": "https://api.liquid.ai/decisions/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": "The hosted d1 model is proprietary under Liquid AI's terms of service. The d1-3B and d1-omni-600M weights and model code are under the LFM Open Licence v1.0, which is based on Apache-2.0 and conditions commercial use on annual revenue under $10 million. Training code and data aren't published", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-11", "b": "2026-10-07", "name": "Last release" }, { "a": "no document linked", "b": "2026-09-30", "name": "Terms last updated" }, { "a": "no document linked", "b": "2026-09-30", "name": "Privacy policy last updated" }, { "a": "", "b": "yes", "name": "Customer content may train models" }, { "a": "", "b": "not found in the text", "name": "Terms restrict automated access" }, { "a": "", "b": "not found in the text", "name": "Terms restrict benchmarking" }, { "a": "", "b": "not found in the text", "name": "Terms or service can change without notice" }, { "a": "", "b": "not found in the text", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Decision 3.0 scores 63.1 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in 6 of 7 scored categories. Liquid d1 leads on transparency \u0026 trust.", "question": "Which is better for AI agents, Decision 3.0 or Liquid d1?" }, { "answer": "Decision 3.0 needs no key. Liquid d1 needs an API key.", "question": "Do Decision 3.0 and Liquid d1 need an API key?" }, { "answer": "No hosted endpoint is listed for Decision 3.0. Liquid d1 has a hosted endpoint at https://api.liquid.ai/decisions/v1/systemone.", "question": "Can an agent call Decision 3.0 and Liquid d1 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 Liquid d1.", "question": "Are Decision 3.0 and Liquid d1 open source?" } ], "goodFor": [ { "aheadOn": [ "Reliability, 58 against 21", "Schema \u0026 documentation, 70 against 59", "Agent ergonomics, 72 against 63", "Security \u0026 auth, 56 against 35", "Payments \u0026 pricing, 60 against 27", "Maintenance \u0026 community, 82 against 60" ], "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": [ "Transparency \u0026 trust, 54 against 45" ], "also": [ "A hosted endpoint, with nothing to install" ], "goodFor": "Classification, routing, yes or no gates and rubric scoring over text and images at a low per-token price, or on your own hardware with d1-3B where data can't leave.", "slug": "liquid-d1", "watchFor": "The terms of 30 September 2026 allow Liquid to train on API content, with no opt-out or zero-retention option found" } ], "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-liquid-d1.json", "title": "Celeris-1 Decision vs Liquid d1", "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-liquid-d1" }, { "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-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/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-liquid-d1.json", "title": "Laya vs Liquid d1", "url": "https://www.anchorterminal.com/compare/convai-laya-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/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-liquid-d1.json", "title": "Decider vs Liquid d1", "url": "https://www.anchorterminal.com/compare/decider-vs-liquid-d1" }, { "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-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" }, { "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/jaredpalmer-kev-vs-liquid-d1.json", "title": "Kev vs Liquid d1", "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-liquid-d1" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1.json", "title": "Liquid d1 vs Microsoft-Decision-1", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1" }, { "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/liquid-d1-vs-openai-decisions-api.json", "title": "Liquid d1 vs OpenAI Decisions API", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-openai-decisions-api" }, { "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/liquid-d1-vs-strands-decider.json", "title": "Liquid d1 vs Strands Decider 2B", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-strands-decider" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-typesafe-jev.json", "title": "Liquid d1 vs Jev", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-typesafe-jev" }, { "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-vela.json", "title": "Liquid d1 vs Vela 2.0", "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-vela" } ], "scores": [ { "by": 37, "decision-3": 58, "edge": "decision-3", "key": "reliability", "liquid-d1": 21, "name": "Reliability", "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 11, "decision-3": 70, "edge": "decision-3", "key": "schema", "liquid-d1": 59, "name": "Schema \u0026 documentation", "weight": 13 }, { "by": 9, "decision-3": 72, "edge": "decision-3", "key": "ergonomics", "liquid-d1": 63, "name": "Agent ergonomics", "weight": 13 }, { "by": 21, "decision-3": 56, "edge": "decision-3", "key": "security", "liquid-d1": 35, "name": "Security \u0026 auth", "weight": 14 }, { "by": 33, "decision-3": 60, "edge": "decision-3", "key": "payments", "liquid-d1": 27, "name": "Payments \u0026 pricing", "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 22, "decision-3": 82, "edge": "decision-3", "key": "maintenance", "liquid-d1": 60, "name": "Maintenance \u0026 community", "weight": 7 }, { "by": 9, "decision-3": 45, "edge": "liquid-d1", "key": "transparency", "liquid-d1": 54, "name": "Transparency \u0026 trust", "weight": 7 } ], "summary": "Decision 3.0 scores 63.1 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in 6 of 7 scored categories. Liquid d1 leads on transparency \u0026 trust. 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.", "liquid-d1": "The hosted API costs $0.04 per million input tokens and takes TypeSafe's System One request, and the d1-3B weights run locally through Transformers or llama.cpp. Liquid's terms allow it to train on API content, and no status page, rate limits or error reference were found. The family launched between 22 September and 7 October 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1", "json": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.md", "slim": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.min.md" }, "markdown": "Decision 3.0 scores 63.1 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in 6 of 7 scored categories. Liquid d1 leads on transparency \u0026 trust. 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- Liquid d1: grade E, 43.5/100, rank #896 of 965. Markdown https://www.anchorterminal.com/tools/liquid-d1.md · JSON https://www.anchorterminal.com/api/v1/tools/liquid-d1.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- Reliability, 58 against 21\n- Schema \u0026 documentation, 70 against 59\n- Agent ergonomics, 72 against 63\n- Security \u0026 auth, 56 against 35\n- Payments \u0026 pricing, 60 against 27\n- Maintenance \u0026 community, 82 against 60\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### Liquid d1 (E)\n\nGood for: Classification, routing, yes or no gates and rubric scoring over text and images at a low per-token price, or on your own hardware with d1-3B where data can't leave.\n\nAhead on:\n- Transparency \u0026 trust, 54 against 45\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: The terms of 30 September 2026 allow Liquid to train on API content, with no opt-out or zero-retention option found\n\n\n## Score by category\n\n| Category | Weight | Decision 3.0 | Liquid d1 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 58 | 21 | Decision 3.0 +37 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 59 | Decision 3.0 +11 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 63 | Decision 3.0 +9 |\n| Security \u0026 auth | 14% (17.5 this run) | 56 | 35 | Decision 3.0 +21 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 27 | Decision 3.0 +33 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 60 | Decision 3.0 +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 54 | Liquid d1 +9 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **63.1 · B** | **43.5 · E** | |\n\n## Facts side by side\n\n| Fact | Decision 3.0 | Liquid d1 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | vLLM Semantic Router Team | Liquid AI |\n| Hosted endpoint | no (local only) | `https://api.liquid.ai/decisions/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 | The hosted d1 model is proprietary under Liquid AI's terms of service. The d1-3B and d1-omni-600M weights and model code are under the LFM Open Licence v1.0, which is based on Apache-2.0 and conditions commercial use on annual revenue under $10 million. Training code and data aren't published |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-10-11 | 2026-10-07 |\n| Terms last updated | no document linked | 2026-09-30 |\n| Privacy policy last updated | no document linked | 2026-09-30 |\n| Customer content may train models | | yes |\n| Terms restrict automated access | | not found in the text |\n| Terms restrict benchmarking | | not found in the text |\n| Terms or service can change without notice | | not found in the text |\n| Arbitration or class-action waiver | | not found in the text |\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**Liquid d1.** The hosted API costs $0.04 per million input tokens and takes TypeSafe's System One request, and the d1-3B weights run locally through Transformers or llama.cpp. Liquid's terms allow it to train on API content, and no status page, rate limits or error reference were found. The family launched between 22 September and 7 October 2026.\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### Liquid d1\n\n1. POST to https://api.liquid.ai/decisions/v1/systemone with a `liquid_` key as a Bearer header. This is not a chat-completions endpoint\n2. Use `d1` for images. `d1:free` is text-only and answers that it does not accept images\n3. Send images as Base64 data URLs in `images`, at most 8, with the whole JSON body under 4.5 MB. Remote image URLs are refused\n4. Budget tokens per question. Each question is billed as its own prompt, with its text and every image counted again\n5. Don't send confidential content to the hosted API, since the terms allow training on it. Run d1-3B locally for that data\n\n## Questions\n\n### Which is better for AI agents, Decision 3.0 or Liquid d1?\n\nDecision 3.0 scores 63.1 (B) on agent readiness against Liquid d1's 43.5 (E), and leads in 6 of 7 scored categories. Liquid d1 leads on transparency \u0026 trust.\n\n### Do Decision 3.0 and Liquid d1 need an API key?\n\nDecision 3.0 needs no key. Liquid d1 needs an API key.\n\n### Can an agent call Decision 3.0 and Liquid d1 without installing anything?\n\nNo hosted endpoint is listed for Decision 3.0. Liquid d1 has a hosted endpoint at https://api.liquid.ai/decisions/v1/systemone.\n\n### Are Decision 3.0 and Liquid d1 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 Liquid d1.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"decision-3\", \"b\": \"liquid-d1\"}`. From a terminal: `anchor compare decision-3 liquid-d1`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/liquid-d1.json\n\n## Other comparisons with Decision 3.0 or Liquid d1\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 Liquid d1](https://www.anchorterminal.com/compare/celeris-1-decision-vs-liquid-d1.md)\n- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)\n- [Clef vs Liquid d1](https://www.anchorterminal.com/compare/cloudflare-clef-vs-liquid-d1.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs Liquid d1](https://www.anchorterminal.com/compare/convai-laya-vs-liquid-d1.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decider vs Liquid d1](https://www.anchorterminal.com/compare/decider-vs-liquid-d1.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 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- [GLiClass vs Liquid d1](https://www.anchorterminal.com/compare/gliclass-vs-liquid-d1.md)\n- [Kev vs Liquid d1](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-liquid-d1.md)\n- [Liquid d1 vs Microsoft-Decision-1](https://www.anchorterminal.com/compare/liquid-d1-vs-microsoft-decision-1.md)\n- [Liquid d1 vs Drex 1.5](https://www.anchorterminal.com/compare/liquid-d1-vs-nace-drex.md)\n- [Liquid d1 vs OpenAI Decisions API](https://www.anchorterminal.com/compare/liquid-d1-vs-openai-decisions-api.md)\n- [Liquid d1 vs pplx-decider](https://www.anchorterminal.com/compare/liquid-d1-vs-pplx-decider.md)\n- [Liquid d1 vs Strands Decider 2B](https://www.anchorterminal.com/compare/liquid-d1-vs-strands-decider.md)\n- [Liquid d1 vs Jev](https://www.anchorterminal.com/compare/liquid-d1-vs-typesafe-jev.md)\n- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-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 Liquid d1", "url": "" } ], "description": "Decision 3.0 scores 63.1 (B) to Liquid d1's 43.5 (E) for decision models. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Decision 3.0 B 63.1", "Liquid d1 E 43.5", "scores" ], "h1": "Decision 3.0 vs Liquid d1", "image": "https://www.anchorterminal.com/assets/og/compare-decision-3-vs-liquid-d1.png", "path": "/compare/decision-3-vs-liquid-d1", "published": "2026-10-01", "section": "tools", "title": "Decision 3.0 vs Liquid d1 for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-12", "url": "https://www.anchorterminal.com/compare/decision-3-vs-liquid-d1" }, "tokens": { "markdown": 2600, "slim": 780 }, "version": 1 }