{
  "data": {
    "a": {
      "slug": "pplx-decider",
      "name": "pplx-decider",
      "vendor": "Perplexity",
      "vendorUrl": "https://www.perplexity.ai/",
      "kind": "model",
      "category": "decision-models",
      "summary": "pplx-decider is Perplexity's multimodal decision model, a fine-tune of Qwen3.8-27B. It answers yes or no, choice and score questions about text, JSON and images with probabilities, through Perplexity's hosted Decisions API or from open weights on Hugging Face.",
      "url": "https://www.anchorterminal.com/tools/pplx-decider",
      "markdownUrl": "https://www.anchorterminal.com/tools/pplx-decider.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/pplx-decider.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/pplx-decider.json",
      "repo": "https://huggingface.co/perplexity-ai/pplx-decider-v1.1-27b",
      "license": "Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service",
      "transports": [
        "http"
      ],
      "remoteUrl": "https://api.perplexity.ai/v1/decisions",
      "packages": [],
      "auth": "api-key",
      "authNotes": "Hosted API. Bearer Perplexity API key in the `Authorization` header. A key sent in `x-api-key` returns 401. Keys are created in the API console after a project exists, are shown once, and can be generated and revoked through `/generate_auth_token` and `/revoke_auth_token`. No per-key scopes were found. Weights. The Hugging Face repository is public and not gated, and the bundled server takes an optional `AUTOJEV_API_KEY`.",
      "pricing": "usage",
      "pricingNotes": "$0.02 per million input tokens on Perplexity's Decisions API for both `pplx-decider-v1.1-27b` and `pplx-decider-v1-27b`. Output tokens are free and there is no per-request fee. The changelog says v1 launched at $0.04. Usage draws on prepaid credits, and the billing guide asks for a credit card. No free allowance was found. The weights are free to download and need a GPU with about 49 GiB for weights.",
      "priceSummary": "Pay per use",
      "where": "hosted",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402 in the Decisions API guide, the reference, the pricing page or llms.txt, read on 9 October 2026.",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": null,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-09"
      },
      "docsUrl": "https://docs.perplexity.ai/docs/decisions/quickstart",
      "llmsTxt": "https://docs.perplexity.ai/llms.txt",
      "openapi": "https://docs.perplexity.ai/openapi-gateway-preview.json",
      "capabilities": [
        "inference.decision"
      ],
      "tags": [
        "official",
        "hosted",
        "model",
        "open-weights",
        "multimodal",
        "openapi",
        "llms-txt",
        "usage-priced",
        "status-page"
      ],
      "lastRelease": "2026-10-05",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 62.9,
        "grade": "B",
        "agentReady": false,
        "rank": 417,
        "ranked": true,
        "rankOf": 950,
        "categoryRank": 7,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 76,
          "maintenance": 62,
          "payments": 25,
          "reliability": 61,
          "schema": 90,
          "security": 61,
          "transparency": 52
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-09"
        },
        "negative": 0,
        "verdict": "The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.",
        "bestFor": "High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.",
        "strengths": [
          "Weights for v1.1 and v1 are public on Hugging Face under Apache-2.0, with training code, config and a data manifest in the repository",
          "One request takes up to 128 questions about one `state`, mixing `noul`, `choice` and `score`, with under 262,144 input tokens",
          "$0.02 per million input tokens with free output and no per-request fee, published without a login",
          "OpenAPI 3.0.3 description, llms.txt and Markdown pages for the guide and reference",
          "Rate limit stated as 10 requests a second per organisation, with `Retry-After` on 429 and `x-ratelimit-*` headers"
        ],
        "weaknesses": [
          "The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee",
          "The official Python SDK at 0.43.8 has no Decisions method. The guide uses a plain HTTP client",
          "An image over 2,048 tiles is not rejected. The request waits about a minute and returns 504",
          "The zero-retention statement on the Privacy and Security page names only the Chat Completions API",
          "The bundled server in the weights repository caps a question at 8,192 tokens and reads a `playground.html` the v1.1 repository does not include"
        ],
        "agentNotes": [
          "Send `Authorization: Bearer`. A key in `x-api-key` returns 401 on this endpoint.",
          "Set `model` on every request. A missing or unknown model returns 400, and the guide shows a `-latest` name rejected.",
          "Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.",
          "Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and `error.code` changes type.",
          "For the weights, use the repository's `autojev` code. The card says default causal inference does not reproduce the evaluated setup."
        ],
        "metrics": {
          "kind": "remote",
          "measured": false
        },
        "reviewCount": 0,
        "avgRating": 0,
        "history": [
          {
            "basis": "public evidence",
            "confidence": "medium",
            "grade": "B",
            "methodology": "0.4",
            "pending": [
              "performance",
              "tasks"
            ],
            "run": "2026-10-01",
            "runLabel": "October 2026 research run",
            "score": 62.9
          }
        ],
        "editorialScores": {
          "ergonomics": 76,
          "maintenance": 62,
          "payments": 25,
          "reliability": 61,
          "schema": 90,
          "security": 61,
          "transparency": 54
        },
        "provenanceScore": 49
      },
      "connect": {
        "http": "curl -X POST https://api.perplexity.ai/v1/decisions \\\n  -H \"Authorization: Bearer $PERPLEXITY_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"model\":\"pplx-decider-v1.1-27b\",\"state\":\"The headphones sound great, but the battery stopped charging after two weeks.\",\"questions\":{\"defect\":{\"type\":\"noul\",\"instructions\":\"Does the review report a product defect?\"}}}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.decision",
        "tool": "https://letme.dev/pplx-decider"
      },
      "area": "models",
      "unitPrices": [
        {
          "item": "Decision input",
          "unit": "1m-tokens",
          "usd": 0.02,
          "note": "Same price for v1.1 and v1. State, questions and images count as input."
        },
        {
          "item": "Decision output",
          "unit": "1m-tokens",
          "usd": 0,
          "note": "Output tokens are free. No per-request fee."
        }
      ],
      "provenance": {
        "legalEntity": "",
        "domain": "perplexity.ai",
        "domainRegistered": "",
        "endpointOnVendorDomain": true,
        "terms": "https://www.perplexity.ai/hub/legal/terms-of-service",
        "privacy": "https://www.perplexity.ai/hub/legal/privacy-notice",
        "statusPage": "https://status.perplexity.com/",
        "changelog": "https://docs.perplexity.ai/docs/resources/changelog",
        "securityTxt": "unknown",
        "checked": "2026-10-09",
        "notes": [
          "The terms of service and privacy notice linked here are the two the status page links. www.perplexity.ai answered our researcher with a bot check (403) on 9 October 2026, so neither was read.",
          "No legal entity was established. The pages read name the vendor only as Perplexity, and the Hugging Face organisation is marked as a verified company.",
          "The status page lists Website, App, Computer and API components, with no Decisions component.",
          "The changelog dates entries by month. The two Decisions entries are under October 2026.",
          "docs.perplexity.ai answered 404 for the well-known security.txt. The main site was not readable, so security.txt is unknown. Domain registration was not checked."
        ],
        "score": 49
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/pplx-decider.json",
      "live": {
        "slug": "pplx-decider",
        "probe": {
          "target": "https://api.perplexity.ai/v1/decisions",
          "method": "get",
          "lastAt": "2026-10-10T02:55:06.655029958Z",
          "lastOk": true,
          "lastStatus": 401,
          "lastMs": 326,
          "lastNote": "asks for credentials",
          "authRequired": true,
          "uptime24h": 100,
          "uptime30d": 100,
          "p50ms24h": 211,
          "p95ms24h": 1253,
          "samples24h": 115,
          "samples30d": 115,
          "days": [
            {
              "date": "2026-10-09",
              "probes": 85,
              "ok": 85
            },
            {
              "date": "2026-10-10",
              "probes": 30,
              "ok": 30
            }
          ]
        },
        "vendorStatus": {
          "page": "https://status.perplexity.com",
          "indicator": "none",
          "summary": "All Systems Operational",
          "checkedAt": "2026-10-10T02:50:43.559119689Z"
        },
        "pages": [
          {
            "url": "https://docs.perplexity.ai/docs/resources/changelog",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-09T18:38:00.707248662Z",
            "changedAt": "0001-01-01T00:00:00Z",
            "fingerprint": "ab545eed1660"
          },
          {
            "url": "https://www.perplexity.ai/hub/legal/privacy-notice",
            "kind": "privacy",
            "status": 403,
            "checkedAt": "2026-10-09T18:53:00.205668839Z",
            "changedAt": "0001-01-01T00:00:00Z"
          },
          {
            "url": "https://www.perplexity.ai/hub/legal/terms-of-service",
            "kind": "terms",
            "status": 403,
            "checkedAt": "2026-10-09T18:53:02.2245445Z",
            "changedAt": "0001-01-01T00:00:00Z"
          }
        ],
        "updatedAt": "2026-10-10T02:55:06.655029958Z"
      }
    },
    "answer": "Vela 2.0 scores 66.5 (B) on agent readiness against pplx-decider's 62.9 (B), and leads in 3 of 7 scored categories. pplx-decider leads on schema \u0026 documentation.",
    "b": {
      "slug": "vela",
      "name": "Vela 2.0",
      "vendor": "vLLM Semantic Router project and KR Labs",
      "vendorUrl": "https://vllm-sr.ai",
      "kind": "model",
      "category": "decision-models",
      "summary": "Vela 2.0 is a family of four open-weight decision models from the vLLM Semantic Router project and KR Labs, released on 6 October 2026 under Apache-2.0 for routing, safety checks, personal-data spans and hallucination checks.",
      "url": "https://www.anchorterminal.com/tools/vela",
      "markdownUrl": "https://www.anchorterminal.com/tools/vela.md",
      "slimMarkdownUrl": "https://www.anchorterminal.com/tools/vela.min.md",
      "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/vela.json",
      "repo": "https://github.com/vllm-project/semantic-router",
      "license": "Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences",
      "transports": [
        "http"
      ],
      "packages": [
        {
          "registry": "pypi",
          "name": "vllm-sr"
        }
      ],
      "auth": "none",
      "authNotes": "No account. The weights are public and ungated on Hugging Face. The bundled `vela2_serve.py` binds to 127.0.0.1 and ignores the Authorization header unless `VELA2_API_KEY` is set, after which it requires `Authorization: Bearer \u003ckey\u003e` and answers 401 otherwise. The router's model runtime has no authentication and publishes on 127.0.0.1 unless `--host` is passed.",
      "pricing": "free",
      "pricingNotes": "Free and open source, with nothing to buy and no hosted API. Hardware is the owner's cost. The 0.3B runs on a CPU, and the cards put GPU parameter memory at about 17 GB for the 4B. The router docs list about 32 GB for the 9B (checked 2026-10-08).",
      "priceSummary": "Free · OSS",
      "where": "local",
      "x402": {
        "level": "no",
        "evidence": "No x402, MPP or L402. Vela 2.0 is software the owner runs, and neither server has a payment route (checked 2026-10-08).",
        "endpoints": []
      },
      "toolCount": null,
      "popularity": {
        "githubStars": 6054,
        "npmWeekly": null,
        "pypiWeekly": null,
        "asOf": "2026-10-08"
      },
      "docsUrl": "https://huggingface.co/collections/vllm-sr/vela-20",
      "openapi": "https://raw.githubusercontent.com/vllm-project/semantic-router/main/src/model-runtime/vllm_srun/api/openapi.yaml",
      "capabilities": [
        "inference.decision",
        "guard.pii",
        "guard.injection",
        "guard.moderation",
        "guard.self-host"
      ],
      "tags": [
        "model",
        "open-source",
        "open-weights",
        "self-hosted",
        "local",
        "free",
        "python",
        "openapi"
      ],
      "lastRelease": "2026-10-06",
      "graded": true,
      "anchor": {
        "graded": true,
        "score": 66.5,
        "grade": "B",
        "agentReady": false,
        "rank": 290,
        "ranked": true,
        "rankOf": 950,
        "categoryRank": 5,
        "methodology": "0.4",
        "run": "2026-10-01",
        "scores": {
          "ergonomics": 79,
          "maintenance": 84,
          "payments": 60,
          "reliability": 57,
          "schema": 78,
          "security": 60,
          "transparency": 48
        },
        "pending": [
          "performance",
          "tasks"
        ],
        "assessment": {
          "confidence": "medium",
          "date": "2026-10-08"
        },
        "negative": 0,
        "verdict": "One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.",
        "bestFor": "Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.",
        "strengths": [
          "Five question types in one request (choice, noul, score, set and span), with span answers as labelled character offsets and a probability each",
          "Apache-2.0 weights, code and documentation, ungated on Hugging Face, with safetensors files and a SHA256SUMS manifest in the three decoder repositories",
          "Two serving routes. A bundled FastAPI server on `POST /v1/systemone`, and the router's model runtime with an OpenAPI 3.0.3 contract and Prometheus metrics",
          "The model cards disclose evaluation protocol, including that the 0.3B release selection considered test results and that SQuAD v2 isn't zero-shot",
          "The router's release note lists where the 0.3B default is behind Vela 1.0, with numbers, and how to restore each Vela 1.0 model"
        ],
        "weaknesses": [
          "No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026",
          "Loading with `transformers` needs `trust_remote_code=True`, which runs Python from the model repository",
          "The router's `vllm-sr serve MODEL` engine mode is newer than the 0.4.0 stable release and needs the development channel",
          "By the authors' figures the 4B scores 31.63 on the Jev Decision Index 0.2.1 against 42.55 for its Decision 2.0 base",
          "The model runtime has no authentication, and the bundled server is open unless `VELA2_API_KEY` is set"
        ],
        "agentNotes": [
          "Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch",
          "Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name",
          "Name span questions `pii`, `halu` or `toxic`, or set `\"head\": \"router\"`, to get the trained router head. Other labels go to the broad head",
          "Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit",
          "Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network"
        ],
        "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": 66.5
          }
        ],
        "editorialScores": {
          "ergonomics": 79,
          "maintenance": 84,
          "payments": 60,
          "reliability": 57,
          "schema": 78,
          "security": 60,
          "transparency": 68
        },
        "provenanceScore": 27
      },
      "connect": {
        "install": "pip install torch \"transformers\u003e=5.17\" safetensors tokenizers numpy fastapi uvicorn\n# from a local snapshot of vllm-sr/Vela-2.0-4B\npython vela2_serve.py --model . --device cuda --port 8001",
        "http": "curl -s localhost:8001/v1/systemone -H 'content-type: application/json' \\\n  -d '{\"model\":\"vllm-sr/Vela-2.0-4B\",\"state\":\"My card was charged twice and the parcel never arrived.\",\"questions\":{\"issues\":{\"type\":\"set\",\"instructions\":\"Which issues does the customer report?\",\"criteria\":{\"billing\":\"payments, charges, refunds or invoices\",\"shipping\":\"delivery of an order or a parcel\",\"login\":\"signing in, passwords or account access\"}}}}'"
      },
      "letme": {
        "capability": "https://letme.dev/inference.decision",
        "tool": "https://letme.dev/vela"
      },
      "area": "models",
      "provenance": {
        "legalEntity": "",
        "domain": "vllm-sr.ai",
        "domainRegistered": "2026-07-13",
        "endpointOnVendorDomain": null,
        "terms": "",
        "privacy": "",
        "statusPage": "",
        "changelog": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals",
        "securityTxt": "none",
        "checked": "2026-10-08",
        "notes": [
          "An open-source project with no company named as publisher. The site footer reads vLLM Semantic Router Team, and the model cards credit KR Labs and vLLM Semantic Router.",
          "RDAP gives 13 July 2026 as the registration date of vllm-sr.ai.",
          "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 returns 404. SECURITY.md in the repository takes private reports through GitHub Security Advisories.",
          "The weights are on huggingface.co under the vllm-sr organisation, and the code for the router and its model runtime is at github.com/vllm-project/semantic-router."
        ],
        "score": 27
      },
      "pageJsonUrl": "https://www.anchorterminal.com/tools/vela.json",
      "live": {
        "slug": "vela",
        "versions": [
          {
            "registry": "github",
            "name": "vllm-project/semantic-router",
            "version": "v0.4.0",
            "released": "2026-09-27",
            "seenAt": "2026-10-09T17:26:43.396072974Z"
          },
          {
            "registry": "pypi",
            "name": "vllm-sr",
            "version": "0.4.0",
            "released": "2026-09-27",
            "seenAt": "2026-10-09T17:26:43.275825559Z"
          }
        ],
        "githubStars": 6069,
        "pypiWeekly": 15068,
        "securityTxt": {
          "url": "https://vllm-sr.ai/.well-known/security.txt",
          "state": "none",
          "checkedAt": "2026-10-09T15:39:13.1700609Z"
        },
        "pages": [
          {
            "url": "https://vllm-sr.ai/docs/release-notes/vela-2-0-built-in-signals",
            "kind": "changelog",
            "status": 200,
            "checkedAt": "2026-10-09T18:47:13.835337297Z",
            "changedAt": "2026-10-09T18:47:13.835337297Z",
            "fingerprint": "10ded21d9f13"
          }
        ],
        "updatedAt": "2026-10-09T18:47:13.835337297Z"
      }
    },
    "facts": [
      {
        "a": "Model API",
        "b": "Model API",
        "name": "Kind"
      },
      {
        "a": "Perplexity",
        "b": "vLLM Semantic Router project and KR Labs",
        "name": "Vendor"
      },
      {
        "a": "https://api.perplexity.ai/v1/decisions",
        "b": "no (local only)",
        "name": "Hosted endpoint"
      },
      {
        "a": "HTTP",
        "b": "HTTP",
        "name": "Transports"
      },
      {
        "a": "API key",
        "b": "None",
        "name": "Auth"
      },
      {
        "a": "Pay per use",
        "b": "Free",
        "name": "Pricing"
      },
      {
        "a": "free",
        "b": "free",
        "name": "Price for decision models"
      },
      {
        "a": "no",
        "b": "no",
        "name": "x402"
      },
      {
        "a": "Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service",
        "b": "Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences",
        "name": "Licence"
      },
      {
        "a": "no",
        "b": "no",
        "name": "Read-only variant documented"
      },
      {
        "a": "yes",
        "b": "no",
        "name": "llms.txt"
      },
      {
        "a": "2026-10-05",
        "b": "2026-10-06",
        "name": "Last release"
      },
      {
        "a": "couldn't be read",
        "b": "no document linked",
        "name": "Terms last updated"
      },
      {
        "a": "couldn't be read",
        "b": "no document linked",
        "name": "Privacy policy last updated"
      },
      {
        "a": "couldn't be read",
        "b": "",
        "name": "Customer content may train models"
      },
      {
        "a": "couldn't be read",
        "b": "",
        "name": "Terms restrict automated access"
      },
      {
        "a": "couldn't be read",
        "b": "",
        "name": "Terms restrict benchmarking"
      },
      {
        "a": "couldn't be read",
        "b": "",
        "name": "Terms or service can change without notice"
      },
      {
        "a": "couldn't be read",
        "b": "",
        "name": "Arbitration or class-action waiver"
      },
      {
        "a": "none",
        "b": "6.1k stars",
        "name": "Popularity"
      }
    ],
    "faq": [
      {
        "answer": "Vela 2.0 scores 66.5 (B) on agent readiness against pplx-decider's 62.9 (B), and leads in 3 of 7 scored categories. pplx-decider leads on schema \u0026 documentation.",
        "question": "Which is better for AI agents, pplx-decider or Vela 2.0?"
      },
      {
        "answer": "pplx-decider, at free against free for Vela 2.0. These are the vendors' published prices for the job.",
        "question": "Which is cheaper for decision models, pplx-decider or Vela 2.0?"
      },
      {
        "answer": "pplx-decider needs an API key. Vela 2.0 needs no key.",
        "question": "Do pplx-decider and Vela 2.0 need an API key?"
      },
      {
        "answer": "pplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions. No hosted endpoint is listed for Vela 2.0.",
        "question": "Can an agent call pplx-decider and Vela 2.0 without installing anything?"
      },
      {
        "answer": "No open-source release is listed for pplx-decider. Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).",
        "question": "Are pplx-decider and Vela 2.0 open source?"
      }
    ],
    "goodFor": [
      {
        "aheadOn": [
          "Schema \u0026 documentation, 90 against 78"
        ],
        "also": [
          "Cheaper for decision models, $0 against $0 per 1M tokens",
          "A hosted endpoint, with nothing to install"
        ],
        "goodFor": "High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.",
        "slug": "pplx-decider",
        "watchFor": "The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee"
      },
      {
        "aheadOn": [
          "Payments \u0026 pricing, 60 against 25",
          "Maintenance \u0026 community, 84 against 62"
        ],
        "also": [
          "No key needed to call it",
          "Open source"
        ],
        "goodFor": "Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.",
        "slug": "vela",
        "watchFor": "No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026"
      }
    ],
    "job": {
      "capability": "inference.decision",
      "name": "Decision models"
    },
    "others": [
      {
        "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-pplx-decider.json",
        "title": "Celeris-1 Decision vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.json",
        "title": "Celeris-1 Decision vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider.json",
        "title": "Clef vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.json",
        "title": "Clef vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider.json",
        "title": "Laya vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/convai-laya-vs-vela.json",
        "title": "Laya vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/convai-laya-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decider-vs-pplx-decider.json",
        "title": "Decider vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/decider-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/decider-vs-vela.json",
        "title": "Decider vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/decider-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.json",
        "title": "GLiClass vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/gliclass-vs-vela.json",
        "title": "GLiClass vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/gliclass-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-pplx-decider.json",
        "title": "Kev vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.json",
        "title": "Kev vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela"
      },
      {
        "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-vela.json",
        "title": "Liquid d1 vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/liquid-d1-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider.json",
        "title": "OpenAI Decisions API vs pplx-decider",
        "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.json",
        "title": "OpenAI Decisions API vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider.json",
        "title": "pplx-decider vs Strands Decider 2B",
        "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider"
      },
      {
        "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev.json",
        "title": "pplx-decider vs Jev",
        "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev"
      },
      {
        "json": "https://www.anchorterminal.com/compare/strands-decider-vs-vela.json",
        "title": "Strands Decider 2B vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/strands-decider-vs-vela"
      },
      {
        "json": "https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.json",
        "title": "Jev vs Vela 2.0",
        "url": "https://www.anchorterminal.com/compare/typesafe-jev-vs-vela"
      }
    ],
    "scores": [
      {
        "by": 4,
        "edge": "pplx-decider",
        "key": "reliability",
        "name": "Reliability",
        "pplx-decider": 61,
        "vela": 57,
        "weight": 16
      },
      {
        "key": "performance",
        "name": "Performance",
        "pending": true,
        "weight": 10
      },
      {
        "by": 12,
        "edge": "pplx-decider",
        "key": "schema",
        "name": "Schema \u0026 documentation",
        "pplx-decider": 90,
        "vela": 78,
        "weight": 13
      },
      {
        "by": 3,
        "edge": "vela",
        "key": "ergonomics",
        "name": "Agent ergonomics",
        "pplx-decider": 76,
        "vela": 79,
        "weight": 13
      },
      {
        "by": 1,
        "edge": "pplx-decider",
        "key": "security",
        "name": "Security \u0026 auth",
        "pplx-decider": 61,
        "vela": 60,
        "weight": 14
      },
      {
        "by": 35,
        "edge": "vela",
        "key": "payments",
        "name": "Payments \u0026 pricing",
        "pplx-decider": 25,
        "vela": 60,
        "weight": 10
      },
      {
        "key": "tasks",
        "name": "Task success",
        "pending": true,
        "weight": 10
      },
      {
        "by": 22,
        "edge": "vela",
        "key": "maintenance",
        "name": "Maintenance \u0026 community",
        "pplx-decider": 62,
        "vela": 84,
        "weight": 7
      },
      {
        "by": 4,
        "edge": "pplx-decider",
        "key": "transparency",
        "name": "Transparency \u0026 trust",
        "pplx-decider": 52,
        "vela": 48,
        "weight": 7
      }
    ],
    "summary": "Vela 2.0 scores 66.5 (B) on agent readiness against pplx-decider's 62.9 (B), and leads in 3 of 7 scored categories. pplx-decider leads on schema \u0026 documentation. Both do decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens.",
    "verdicts": {
      "pplx-decider": "The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.",
      "vela": "One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures."
    }
  },
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela",
    "json": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela.md",
    "slim": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela.min.md"
  },
  "markdown": "Vela 2.0 scores 66.5 (B) on agent readiness against pplx-decider's 62.9 (B), and leads in 3 of 7 scored categories. pplx-decider leads on schema \u0026 documentation. Both do decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens.\n\n- pplx-decider: grade B, 62.9/100, rank #417 of 950. Markdown https://www.anchorterminal.com/tools/pplx-decider.md · JSON https://www.anchorterminal.com/api/v1/tools/pplx-decider.json\n- Vela 2.0: grade B, 66.5/100, rank #290 of 950. Markdown https://www.anchorterminal.com/tools/vela.md · JSON https://www.anchorterminal.com/api/v1/tools/vela.json\n- Best decision models for AI agents: https://www.anchorterminal.com/best/decision-models/index.md\n- All 66 decisions comparisons: https://www.anchorterminal.com/compare/decision-models/index.md\n\n## Which one, for what\n\n### pplx-decider (B)\n\nGood for: High-volume classification, routing and rubric scoring over text and images where a team wants a low hosted price and the option to run the same weights itself.\n\nAhead on:\n- Schema \u0026 documentation, 90 against 78\n\nAlso in its favour:\n- Cheaper for decision models, $0 against $0 per 1M tokens\n- A hosted endpoint, with nothing to install\n\nWatch for: The Decisions API was released in October 2026, so its incident record is days long, and Perplexity's FAQ says it gives no uptime guarantee\n\n### Vela 2.0 (B)\n\nGood for: Self-hosted routing and guardrail checks in one call, where span offsets for personal data or unsupported claims matter.\n\nAhead on:\n- Payments \u0026 pricing, 60 against 25\n- Maintenance \u0026 community, 84 against 62\n\nAlso in its favour:\n- No key needed to call it\n- Open source\n\nWatch for: No version tags on the four Hub repositories, and the 4B and 9B weights were replaced in place on 3 October 2026\n\n\n## Score by category\n\n| Category | Weight | pplx-decider | Vela 2.0 | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 61 | 57 | pplx-decider +4 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 90 | 78 | pplx-decider +12 |\n| Agent ergonomics | 13% (16.2 this run) | 76 | 79 | Vela 2.0 +3 |\n| Security \u0026 auth | 14% (17.5 this run) | 61 | 60 | pplx-decider +1 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 25 | 60 | Vela 2.0 +35 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 62 | 84 | Vela 2.0 +22 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 52 | 48 | pplx-decider +4 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.9 · B** | **66.5 · B** | |\n\n## Facts side by side\n\n| Fact | pplx-decider | Vela 2.0 |\n| --- | --- | --- |\n| Kind | Model API | Model API |\n| Vendor | Perplexity | vLLM Semantic Router project and KR Labs |\n| Hosted endpoint | `https://api.perplexity.ai/v1/decisions` | no (local only) |\n| Transports | HTTP | HTTP |\n| Auth | API key | None |\n| Pricing | Pay per use | Free |\n| Price for decision models | free | free |\n| x402 | no | no |\n| Licence | Apache-2.0 for the published weights. The hosted Decisions API is a proprietary service | Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences |\n| Read-only variant documented | no | no |\n| llms.txt | yes | no |\n| Last release | 2026-10-05 | 2026-10-06 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | couldn't be read | no document linked |\n| Customer content may train models | couldn't be read |  |\n| Terms restrict automated access | couldn't be read |  |\n| Terms restrict benchmarking | couldn't be read |  |\n| Terms or service can change without notice | couldn't be read |  |\n| Arbitration or class-action waiver | couldn't be read |  |\n| Popularity | none | 6.1k stars |\n\n## Verdicts\n\n**pplx-decider.** The hosted Decisions API has an OpenAPI description, typed questions, documented limits and a published price of $0.02 per million input tokens, and the v1.1 weights are public under Apache-2.0. The API is days old, the official Python SDK has no method for it, and the governing terms and privacy notice could not be read on 9 October 2026.\n\n**Vela 2.0.** One self-hosted call answers routing, prompt-attack, personal-data and unsupported-claim questions with probabilities and character offsets, under Apache-2.0 with SHA-256 manifests. The models are days old and carry no Hub version tags, and the three larger sizes keep 74 to 89 per cent of their Decision 2.0 bases on the Jev Decision Index by the authors' figures.\n\n## Before you call either\n\n### pplx-decider\n\n1. Send `Authorization: Bearer`. A key in `x-api-key` returns 401 on this endpoint.\n2. Set `model` on every request. A missing or unknown model returns 400, and the guide shows a `-latest` name rejected.\n3. Resize images to 2,048 tiles of 32 by 32 pixels or fewer before sending. Larger images end in a 504 after about a minute.\n4. Check the HTTP status before parsing an error. 404 and 405 have empty bodies, 504 can be HTML, and `error.code` changes type.\n5. For the weights, use the repository's `autojev` code. The card says default causal inference does not reproduce the evaluated setup.\n\n### Vela 2.0\n\n1. Pin a commit hash with `revision=` when loading from the Hub. The repositories have no tags and `main` has changed since launch\n2. Send the served name in `model`, for example `vllm-sr/Vela-2.0-4B`. The bundled server answers 422 to any other name\n3. Name span questions `pii`, `halu` or `toxic`, or set `\"head\": \"router\"`, to get the trained router head. Other labels go to the broad head\n4. Keep input under 16,384 tokens a sequence (8,192 on the 0.3B). The bundled server answers 413 when the questions alone don't fit\n5. Set `VELA2_API_KEY` before binding the bundled server beyond 127.0.0.1, and keep the model runtime on a trusted network\n\n## Questions\n\n### Which is better for AI agents, pplx-decider or Vela 2.0?\n\nVela 2.0 scores 66.5 (B) on agent readiness against pplx-decider's 62.9 (B), and leads in 3 of 7 scored categories. pplx-decider leads on schema \u0026 documentation.\n\n### Which is cheaper for decision models, pplx-decider or Vela 2.0?\n\npplx-decider, at free against free for Vela 2.0. These are the vendors' published prices for the job.\n\n### Do pplx-decider and Vela 2.0 need an API key?\n\npplx-decider needs an API key. Vela 2.0 needs no key.\n\n### Can an agent call pplx-decider and Vela 2.0 without installing anything?\n\npplx-decider has a hosted endpoint at https://api.perplexity.ai/v1/decisions. No hosted endpoint is listed for Vela 2.0.\n\n### Are pplx-decider and Vela 2.0 open source?\n\nNo open-source release is listed for pplx-decider. Vela 2.0 is open source (Apache-2.0 (weights, code and documentation). The 0.3B's tokeniser keeps the Gemma Terms of Use, and training data keeps its own licences).\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/pplx-decider-vs-vela.json, and with the fewest tokens: https://www.anchorterminal.com/compare/pplx-decider-vs-vela.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"pplx-decider\", \"b\": \"vela\"}`. From a terminal: `anchor compare pplx-decider vela`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/pplx-decider.json and https://www.anchorterminal.com/api/v1/tools/vela.json\n\n## Other comparisons with pplx-decider or Vela 2.0\n\n- [Celeris-1 Decision vs pplx-decider](https://www.anchorterminal.com/compare/celeris-1-decision-vs-pplx-decider.md)\n- [Celeris-1 Decision vs Vela 2.0](https://www.anchorterminal.com/compare/celeris-1-decision-vs-vela.md)\n- [Clef vs pplx-decider](https://www.anchorterminal.com/compare/cloudflare-clef-vs-pplx-decider.md)\n- [Clef vs Vela 2.0](https://www.anchorterminal.com/compare/cloudflare-clef-vs-vela.md)\n- [Laya vs pplx-decider](https://www.anchorterminal.com/compare/convai-laya-vs-pplx-decider.md)\n- [Laya vs Vela 2.0](https://www.anchorterminal.com/compare/convai-laya-vs-vela.md)\n- [Decider vs pplx-decider](https://www.anchorterminal.com/compare/decider-vs-pplx-decider.md)\n- [Decider vs Vela 2.0](https://www.anchorterminal.com/compare/decider-vs-vela.md)\n- [GLiClass vs pplx-decider](https://www.anchorterminal.com/compare/gliclass-vs-pplx-decider.md)\n- [GLiClass vs Vela 2.0](https://www.anchorterminal.com/compare/gliclass-vs-vela.md)\n- [Kev vs pplx-decider](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-pplx-decider.md)\n- [Kev vs Vela 2.0](https://www.anchorterminal.com/compare/jaredpalmer-kev-vs-vela.md)\n- [Liquid d1 vs pplx-decider](https://www.anchorterminal.com/compare/liquid-d1-vs-pplx-decider.md)\n- [Liquid d1 vs Vela 2.0](https://www.anchorterminal.com/compare/liquid-d1-vs-vela.md)\n- [OpenAI Decisions API vs pplx-decider](https://www.anchorterminal.com/compare/openai-decisions-api-vs-pplx-decider.md)\n- [OpenAI Decisions API vs Vela 2.0](https://www.anchorterminal.com/compare/openai-decisions-api-vs-vela.md)\n- [pplx-decider vs Strands Decider 2B](https://www.anchorterminal.com/compare/pplx-decider-vs-strands-decider.md)\n- [pplx-decider vs Jev](https://www.anchorterminal.com/compare/pplx-decider-vs-typesafe-jev.md)\n- [Strands Decider 2B vs Vela 2.0](https://www.anchorterminal.com/compare/strands-decider-vs-vela.md)\n- [Jev vs Vela 2.0](https://www.anchorterminal.com/compare/typesafe-jev-vs-vela.md)\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-10-10",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.4",
    "openapi": "https://www.anchorterminal.com/openapi.json",
    "preview": false,
    "run": "2026-10-01",
    "runLabel": "October 2026 research run"
  },
  "page": {
    "breadcrumbs": [
      {
        "name": "Home",
        "url": "https://www.anchorterminal.com/"
      },
      {
        "name": "Compare",
        "url": "https://www.anchorterminal.com/compare/"
      },
      {
        "name": "pplx-decider vs Vela 2.0",
        "url": ""
      }
    ],
    "description": "Vela 2.0 scores 66.5 (B) to pplx-decider's 62.9 (B) for decision models. pplx-decider is cheaper for decision models, $0 against $0 per 1M tokens. Prices, MCP, x402, uptime and agent notes side by side.",
    "facts": [
      "pplx-decider B 62.9",
      "Vela 2.0 B 66.5",
      "scores"
    ],
    "h1": "pplx-decider vs Vela 2.0",
    "image": "https://www.anchorterminal.com/assets/og/compare-pplx-decider-vs-vela.png",
    "path": "/compare/pplx-decider-vs-vela",
    "published": "2026-10-01",
    "section": "tools",
    "title": "pplx-decider vs Vela 2.0 for AI agents in 2026: scores and prices",
    "toc": null,
    "updated": "2026-10-09",
    "url": "https://www.anchorterminal.com/compare/pplx-decider-vs-vela"
  },
  "tokens": {
    "markdown": 2550,
    "slim": 730
  },
  "version": 1
}