{
  "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": 438,
        "ranked": true,
        "rankOf": 1094,
        "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",
      "live": {
        "slug": "decision-3",
        "versions": [
          {
            "registry": "github",
            "name": "vllm-project/semantic-router",
            "version": "v0.4.0",
            "released": "2026-09-27",
            "seenAt": "2026-10-14T23:47:59.543090304Z"
          },
          {
            "registry": "pypi",
            "name": "vllm-sr",
            "version": "0.4.0",
            "released": "2026-09-27",
            "seenAt": "2026-10-14T23:47:59.3276365Z"
          }
        ],
        "githubStars": 6167,
        "pypiWeekly": 10712,
        "securityTxt": {
          "url": "https://vllm-sr.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-14T15:46:34.901898231Z"
        },
        "pages": [
          {
            "url": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/docs/records/decision3-parity.md",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-14T21:08:19.510931465Z",
            "changedAt": "2026-10-14T21:08:19.510931465Z",
            "fingerprint": "3fe50aaef2ee"
          }
        ],
        "updatedAt": "2026-10-14T23:47:59.543090304Z"
      }
    },
    "answer": "Decision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema \u0026 documentation and transparency \u0026 trust.",
    "b": {
      "slug": "sprag-spev",
      "name": "SPEV",
      "vendor": "Sprag",
      "vendorUrl": "https://sprag.ai",
      "kind": "model",
      "category": "decision-models",
      "summary": "SPEV is Sprag's open-weight decision model, released on 14 October 2026. It answers predicate, choice and score questions about text, audio or an image with a probability for each answer, through Sprag's hosted API or Apache-2.0 weights.",
      "url": "https://www.anchorterminal.com/tools/sprag-spev",
      "markdownUrl": "https://www.anchorterminal.com/tools/sprag-spev.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/sprag-spev.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/sprag-spev.json",
      "repo": "https://huggingface.co/SpragAI/SPEV",
      "license": "Apache-2.0 (weights and inference code, following the Qwen3-Omni base). Training code and data aren't published",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.sprag.ai/v1/decisions",
      "packages": [],
      "auth": "api-key",
      "authNotes": "A Sprag API key as a bearer token, generated in the web app after signing up and shown once. Rotating a key invalidates the old one at once. Keys carry no scopes, and every key in an organisation shares one rate limit. The weights download from Hugging Face without an account.",
      "pricing": "usage",
      "pricingNotes": "Hosted SPEV is free through 31 October 2026. The pricing page lists $0.09 per million input text or image tokens and $2.00 per million input audio tokens, with output unbilled. Audio counts one token per 100 ms. The docs list a 402 for an account with no payment method, and whether the free period needs a card wasn't established. The weights are free to run yourself.",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the Decisions docs, the OpenAPI document or the pricing page (checked 2026-10-15). Payment is through Stripe on the account.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-15"
      },
      "docsUrl": "https://sprag.ai/docs/decisions",
      "llmsTxt": "https://sprag.ai/llms.txt",
      "openapi": "https://api.sprag.ai/openapi.json",
      "capabilities": [
        "inference.decision"
      ],
      "tags": [
        "hosted",
        "model",
        "open-weights",
        "llms-txt",
        "openapi",
        "usage-priced",
        "audio"
      ],
      "lastRelease": "2026-10-14",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 51.1,
        "grade": "D",
        "agentReady": false,
        "rank": 819,
        "ranked": true,
        "rankOf": 1094,
        "categoryRank": 12,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 76,
          "maintenance": 49,
          "payments": 30,
          "reliability": 45,
          "schema": 81,
          "security": 33,
          "transparency": 54
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-15"
        },
        "negative": -2,
        "negativeNotes": [
          "2026-10-14. The launch post's title and first line call SPEV 'the first open-weight omnimodal decision model' (https://sprag.ai/blog/spev-open-weight-omnimodal-decision-model.md). Cloudflare published Clef-omni on Hugging Face on 9 October 2026, Apache-2.0, on the same Qwen3-Omni-30B-A3B base, taking audio and video (https://huggingface.co/Cloudflare/clef-omni, checked 2026-10-15). The post also describes Clef as text or images only. A misleading claim, -2."
        ],
        "verdict": "SPEV answers typed questions over text, audio or an image in one call, with a public OpenAPI schema and Apache-2.0 weights on Hugging Face. It is a day old, has an 8,192-token context, no status page or changelog, and Sprag's terms let it train on API content unless the customer opts out by email.",
        "bestFor": "Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted.",
        "strengths": [
          "Native audio evidence, so turn detection and call triage need no transcription step first",
          "Apache-2.0 weights and inference code on Hugging Face, ungated, with a pinned requirements file",
          "Public OpenAPI 3.1 contract with typed predicate, choice and score questions and up to 200 questions a call",
          "Hosted calls free through 31 October 2026, then $0.09 per million text or image tokens and $2.00 per million audio tokens, output unbilled",
          "One error envelope with `code` and `param`, documented rate limits and `Retry-After` on 429 and 503"
        ],
        "weaknesses": [
          "Published on 14 October 2026, with no service record, no status page and no API changelog",
          "Sprag's terms license API content for model training by default. Opting out means emailing privacy@sprag.ai",
          "8,192-token context on the hosted model and in the weights' config",
          "No security.txt, disclosure policy or certification found, and API keys carry no scopes",
          "The launch post calls SPEV the first open-weight omnimodal decision model, five days after Cloudflare published Clef-omni"
        ],
        "agentNotes": [
          "Send `model: \"spev\"` to `POST https://api.sprag.ai/v1/decisions` with a bearer key. `/v1/systemone` returns 410",
          "Ask every question about one piece of evidence in one request. Answers come back in question order",
          "Send audio as base64 in `input_audio` with `format`, not as a data URL, and at most one image across all messages",
          "Keep evidence and questions under 8,192 tokens. Over the limit returns 400 `model_limit_exceeded`",
          "Back off on 429 and 503 for `Retry-After` seconds. Limits are 60 requests a minute per organisation by default",
          "Handle an answer of type `refusal`, which carries no probabilities"
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "D",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 51.1
          }
        ],
        "editorialScores": {
          "ergonomics": 76,
          "maintenance": 49,
          "payments": 30,
          "reliability": 45,
          "schema": 81,
          "security": 33,
          "transparency": 57
        },
        "provenanceScore": 51
      },
      "connect": {
        "http": "curl https://api.sprag.ai/v1/decisions \\\n  -H \"Content-Type: application/json\" -H \"Authorization: Bearer $SPRAG_API_KEY\" \\\n  -d '{\"model\":\"spev\",\"input\":\"I was charged twice. Please refund the duplicate payment.\",\"questions\":[{\"name\":\"department\",\"type\":\"choice\",\"instructions\":\"Which team should handle this?\",\"choices\":[{\"value\":\"billing\"},{\"value\":\"technical\"}]},{\"name\":\"refund\",\"type\":\"predicate\",\"instructions\":\"Is the customer asking for a refund?\"}]}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.decision",
        "tool": "https://letme.dev/sprag-spev"
      },
      "area": "models",
      "unitPrices": [
        {
          "item": "SPEV input text or image",
          "unit": "1m-tokens",
          "usd": 0.09,
          "note": "Free through 31 October 2026. Output not billed"
        },
        {
          "item": "SPEV input audio",
          "unit": "1m-tokens",
          "usd": 2,
          "note": "One token per 100 ms of audio, 36,000 an hour. Free through 31 October 2026"
        }
      ],
      "provenance": {
        "legalEntity": "Sprag AI, Inc.",
        "domain": "sprag.ai",
        "domainRegistered": "2025-10-29",
        "endpointOnVendorDomain": true,
        "terms": "https://sprag.ai/terms",
        "privacy": "https://sprag.ai/privacy",
        "statusPage": "",
        "changelog": "",
        "securityTxt": "none",
        "checked": "2026-10-15",
        "notes": [
          "The terms (last updated September 2026) and privacy policy (August 2026) name Sprag AI, Inc., 455 Market St, San Francisco, and California law.",
          "RDAP for sprag.ai gives a registration date of 29 October 2025. The API is at api.sprag.ai and the weights on huggingface.co under the SpragAI organisation.",
          "sprag.ai/.well-known/security.txt returned 404 on 15 October 2026. status.sprag.ai did not resolve, and sprag.ai/status, /changelog and /security serve the home page.",
          "robots.txt allows all user agents on public pages. The terms have no clause on automated access to the site.",
          "Sprag's llms.txt and Markdown pages carry sections headed 'Agent instructions'. They were read as data and not acted on."
        ],
        "score": 51
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/sprag-spev.json",
      "live": {
        "slug": "sprag-spev",
        "probe": {
          "target": "https://api.sprag.ai/v1/decisions",
          "method": "get",
          "lastAt": "2026-10-15T11:30:11.89010817Z",
          "lastOk": true,
          "lastStatus": 405,
          "lastMs": 639,
          "authRequired": false,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 631,
          "p95ms24h": 691,
          "samples24h": 16,
          "samples30d": 16,
          "days": [
            {
              "date": "2026-10-15",
              "probes": 16,
              "ok": 16
            }
          ]
        },
        "updatedAt": "2026-10-15T11:30:11.89010817Z"
      }
    },
    "facts": [
      {
        "a": "Model API",
        "b": "Model API",
        "name": "Kind"
      },
      {
        "a": "vLLM Semantic Router Team",
        "b": "Sprag",
        "name": "Vendor"
      },
      {
        "a": "no (local only)",
        "b": "https://api.sprag.ai/v1/decisions",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "None",
        "b": "API key",
        "name": "Auth"
      },
      {
        "a": "Free",
        "b": "Pay per use",
        "name": "Pricing"
      },
      {
        "a": "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": "Apache-2.0 (weights and inference code, following the Qwen3-Omni base). 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": "2026-10-14",
        "name": "Last release"
      },
      {
        "a": "no document linked",
        "b": "2026-09-01",
        "name": "Terms last updated"
      },
      {
        "a": "no document linked",
        "b": "2026-08-01",
        "name": "Privacy policy last updated"
      },
      {
        "a": "",
        "b": "yes, with an opt-out",
        "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 SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema \u0026 documentation and transparency \u0026 trust.",
        "question": "Which is better for AI agents, Decision 3.0 or SPEV?"
      },
      {
        "answer": "Decision 3.0 needs no key. SPEV needs an API key.",
        "question": "Do Decision 3.0 and SPEV need an API key?"
      },
      {
        "answer": "No hosted endpoint is listed for Decision 3.0. SPEV has a hosted endpoint at https://api.sprag.ai/v1/decisions.",
        "question": "Can an agent call Decision 3.0 and SPEV 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 SPEV.",
        "question": "Are Decision 3.0 and SPEV open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Reliability, 58 against 45",
          "Security \u0026 auth, 56 against 33",
          "Payments \u0026 pricing, 60 against 30",
          "Maintenance \u0026 community, 82 against 49"
        ],
        "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": [
          "Schema \u0026 documentation, 81 against 70",
          "Transparency \u0026 trust, 54 against 45"
        ],
        "also": [
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted.",
        "slug": "sprag-spev",
        "watchFor": "Published on 14 October 2026, with no service record, no status page and no API changelog"
      }
    ],
    "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-sprag-spev.json",
        "title": "Celeris-1 Decision vs SPEV",
        "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-sprag-spev"
      },
      {
        "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-sprag-spev.json",
        "title": "Clef vs SPEV",
        "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-sprag-spev"
      },
      {
        "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-sprag-spev.json",
        "title": "Laya vs SPEV",
        "url": "https://www.anchorterminal.com/compare/convai-laya-vs-sprag-spev"
      },
      {
        "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-sprag-spev.json",
        "title": "Decider vs SPEV",
        "url": "https://www.anchorterminal.com/compare/decider-vs-sprag-spev"
      },
      {
        "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-scaledown.json",
        "title": "Decision 3.0 vs ScaleDown",
        "url": "https://www.anchorterminal.com/compare/decision-3-vs-scaledown"
      },
      {
        "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-sprag-spev.json",
        "title": "GLiClass vs SPEV",
        "url": "https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-sprag-spev.json",
        "title": "Kev vs SPEV",
        "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev.json",
        "title": "Liquid d1 vs SPEV",
        "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev.json",
        "title": "Microsoft-Decision-1 vs SPEV",
        "url": "https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/nace-drex-vs-sprag-spev.json",
        "title": "Drex 1.5 vs SPEV",
        "url": "https://www.anchorterminal.com/compare/nace-drex-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-sprag-spev.json",
        "title": "OpenAI Decisions API vs SPEV",
        "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-sprag-spev.json",
        "title": "pplx-decider vs SPEV",
        "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.json",
        "title": "ScaleDown vs SPEV",
        "url": "https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/sprag-spev-vs-strands-decider.json",
        "title": "SPEV vs Strands Decider 2B",
        "url": "https://www.anchorterminal.com/compare/sprag-spev-vs-strands-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/sprag-spev-vs-typesafe-jev.json",
        "title": "SPEV vs Jev",
        "url": "https://www.anchorterminal.com/compare/sprag-spev-vs-typesafe-jev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/sprag-spev-vs-vela.json",
        "title": "SPEV vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/sprag-spev-vs-vela"
      }
    ],
    "scores": [
      {
        "by": 13,
        "decision-3": 58,
        "edge": "decision-3",
        "key": "reliability",
        "name": "Reliability",
        "sprag-spev": 45,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 11,
        "decision-3": 70,
        "edge": "sprag-spev",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "sprag-spev": 81,
        "weight": 13
      },
      {
        "by": 4,
        "decision-3": 72,
        "edge": "sprag-spev",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "sprag-spev": 76,
        "weight": 13
      },
      {
        "by": 23,
        "decision-3": 56,
        "edge": "decision-3",
        "key": "security",
        "name": "Security \u0026 auth",
        "sprag-spev": 33,
        "weight": 14
      },
      {
        "by": 30,
        "decision-3": 60,
        "edge": "decision-3",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "sprag-spev": 30,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 33,
        "decision-3": 82,
        "edge": "decision-3",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "sprag-spev": 49,
        "weight": 7
      },
      {
        "by": 9,
        "decision-3": 45,
        "edge": "sprag-spev",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "sprag-spev": 54,
        "weight": 7
      }
    ],
    "summary": "Decision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema \u0026 documentation and 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.",
      "sprag-spev": "SPEV answers typed questions over text, audio or an image in one call, with a public OpenAPI schema and Apache-2.0 weights on Hugging Face. It is a day old, has an 8,192-token context, no status page or changelog, and Sprag's terms let it train on API content unless the customer opts out by email."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev",
    "json": "https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.md",
    "slim": "https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.min.md"
  },
  "markdown": "Decision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema \u0026 documentation and transparency \u0026 trust. Both do decision models.\n\n- Decision 3.0: grade B, 63.1/100, rank #438 of 1094. Markdown https://www.anchorterminal.com/tools/decision-3.md · JSON https://www.anchorterminal.com/api/v1/tools/decision-3.json\n- SPEV: grade D, 51.1/100, rank #819 of 1094. Markdown https://www.anchorterminal.com/tools/sprag-spev.md · JSON https://www.anchorterminal.com/api/v1/tools/sprag-spev.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 136 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\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 45\n- Security \u0026 auth, 56 against 33\n- Payments \u0026 pricing, 60 against 30\n- Maintenance \u0026 community, 82 against 49\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### SPEV (D)\n\nGood for: Typed decisions over raw audio, such as end-of-turn detection, call triage and flagging, plus text and single images, hosted or self-hosted.\n\nAhead on:\n- Schema \u0026 documentation, 81 against 70\n- Transparency \u0026 trust, 54 against 45\n\nAlso in its favour:\n- A hosted endpoint, with nothing to install\n\nWatch for: Published on 14 October 2026, with no service record, no status page and no API changelog\n\n\n## Score by category\n\n| Category | Weight | Decision 3.0 | SPEV | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 58 | 45 | Decision 3.0 +13 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 70 | 81 | SPEV +11 |\n| Agent ergonomics | 13% (16.2 this run) | 72 | 76 | SPEV +4 |\n| Security \u0026 auth | 14% (17.5 this run) | 56 | 33 | Decision 3.0 +23 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 60 | 30 | Decision 3.0 +30 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 82 | 49 | Decision 3.0 +33 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 45 | 54 | SPEV +9 |\n| Negative events | ≤15 | 0 | -2 | |\n| **Total** | | **63.1 · B** | **51.1 · D** | |\n\n## Facts side by side\n\n| Fact | Decision 3.0 | SPEV |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | vLLM Semantic Router Team | Sprag |\n| Hosted endpoint | no (local only) | `https://api.sprag.ai/v1/decisions` |\n| Transports | HTTP | HTTP |\n| Auth | None | API key |\n| Pricing | Free | Pay per use |\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 | Apache-2.0 (weights and inference code, following the Qwen3-Omni base). 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 | 2026-10-14 |\n| Terms last updated | no document linked | 2026-09-01 |\n| Privacy policy last updated | no document linked | 2026-08-01 |\n| Customer content may train models |  | yes, with an opt-out |\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**SPEV.** SPEV answers typed questions over text, audio or an image in one call, with a public OpenAPI schema and Apache-2.0 weights on Hugging Face. It is a day old, has an 8,192-token context, no status page or changelog, and Sprag's terms let it train on API content unless the customer opts out by email.\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### SPEV\n\n1. Send `model: \"spev\"` to `POST https://api.sprag.ai/v1/decisions` with a bearer key. `/v1/systemone` returns 410\n2. Ask every question about one piece of evidence in one request. Answers come back in question order\n3. Send audio as base64 in `input_audio` with `format`, not as a data URL, and at most one image across all messages\n4. Keep evidence and questions under 8,192 tokens. Over the limit returns 400 `model_limit_exceeded`\n5. Back off on 429 and 503 for `Retry-After` seconds. Limits are 60 requests a minute per organisation by default\n6. Handle an answer of type `refusal`, which carries no probabilities\n\n## Questions\n\n### Which is better for AI agents, Decision 3.0 or SPEV?\n\nDecision 3.0 scores 63.1 (B) on agent readiness against SPEV's 51.1 (D), and leads in 4 of 7 scored categories. SPEV leads on schema \u0026 documentation and transparency \u0026 trust.\n\n### Do Decision 3.0 and SPEV need an API key?\n\nDecision 3.0 needs no key. SPEV needs an API key.\n\n### Can an agent call Decision 3.0 and SPEV without installing anything?\n\nNo hosted endpoint is listed for Decision 3.0. SPEV has a hosted endpoint at https://api.sprag.ai/v1/decisions.\n\n### Are Decision 3.0 and SPEV 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 SPEV.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.json, and with the fewest tokens: https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"decision-3\", \"b\": \"sprag-spev\"}`. From a terminal: `anchor compare decision-3 sprag-spev`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/decision-3.json and https://www.anchorterminal.com/api/v1/tools/sprag-spev.json\n\n## Other comparisons with Decision 3.0 or SPEV\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 SPEV](https://www.anchorterminal.com/compare/celeris-1-decision-vs-sprag-spev.md)\n- [Clef vs Decision 3.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-decision-3.md)\n- [Clef vs SPEV](https://www.anchorterminal.com/compare/cloudflare-clef-vs-sprag-spev.md)\n- [Laya vs Decision 3.0](https://www.anchorterminal.com/compare/convai-laya-vs-decision-3.md)\n- [Laya vs SPEV](https://www.anchorterminal.com/compare/convai-laya-vs-sprag-spev.md)\n- [Decider vs Decision 3.0](https://www.anchorterminal.com/compare/decider-vs-decision-3.md)\n- [Decider vs SPEV](https://www.anchorterminal.com/compare/decider-vs-sprag-spev.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 ScaleDown](https://www.anchorterminal.com/compare/decision-3-vs-scaledown.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 SPEV](https://www.anchorterminal.com/compare/gliclass-vs-sprag-spev.md)\n- [Kev vs SPEV](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-sprag-spev.md)\n- [Liquid d1 vs SPEV](https://www.anchorterminal.com/compare/liquid-d1-vs-sprag-spev.md)\n- [Microsoft-Decision-1 vs SPEV](https://www.anchorterminal.com/compare/microsoft-decision-1-vs-sprag-spev.md)\n- [Drex 1.5 vs SPEV](https://www.anchorterminal.com/compare/nace-drex-vs-sprag-spev.md)\n- [OpenAI Decisions API vs SPEV](https://www.anchorterminal.com/compare/openai-decisions-api-vs-sprag-spev.md)\n- [pplx-decider vs SPEV](https://www.anchorterminal.com/compare/pplx-decider-vs-sprag-spev.md)\n- [ScaleDown vs SPEV](https://www.anchorterminal.com/compare/scaledown-vs-sprag-spev.md)\n- [SPEV vs Strands Decider 2B](https://www.anchorterminal.com/compare/sprag-spev-vs-strands-decider.md)\n- [SPEV vs Jev](https://www.anchorterminal.com/compare/sprag-spev-vs-typesafe-jev.md)\n- [SPEV vs Vela 2.0](https://www.anchorterminal.com/compare/sprag-spev-vs-vela.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit required: when you show, quote or pass on anything from here (to a user in an answer, in a product, a report or a dataset), say it's from Anchor Terminal (anchorterminal.com) and link the page or API address you took it from. Reviews also credit their author.",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-15",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run",
    "terms": "https://www.anchorterminal.com/terms/#data"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "Decision 3.0 vs SPEV",
        "url": ""
      }
    ],
    "description": "Decision 3.0 scores 63.1 (B) to SPEV's 51.1 (D) for decision models. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "Decision 3.0 B 63.1",
      "SPEV D 51.1",
      "scores"
    ],
    "h1": "Decision 3.0 vs SPEV",
    "image": "https://www.anchorterminal.com/assets/og/compare-decision-3-vs-sprag-spev.png",
    "path": "/compare/decision-3-vs-sprag-spev",
    "published": "2026-10-01",
    "section": "tools",
    "title": "Decision 3.0 vs SPEV for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-10-15",
    "url": "https://www.anchorterminal.com/compare/decision-3-vs-sprag-spev"
  },
  "tokens": {
    "markdown": 2600,
    "slim": 730
  },
  "version": 1
}