{
  "data": null,
  "kind": "anchor.page",
  "links": {
    "api": "https://www.anchorterminal.com/api/v1/index.json",
    "html": "https://www.anchorterminal.com/niches/decision-models.route-to-queue/",
    "json": "https://www.anchorterminal.com/niches/decision-models.route-to-queue/index.json",
    "llms": "https://www.anchorterminal.com/llms.txt",
    "markdown": "https://www.anchorterminal.com/niches/decision-models.route-to-queue/index.md",
    "mcp": "https://www.anchorterminal.com/mcp",
    "slim": "https://www.anchorterminal.com/niches/decision-models.route-to-queue/index.min.md"
  },
  "markdown": "Four or more companies' docs show a full fit.\n\n| Companies, full fit | With a limit | Carry the tag | Share of the category's work | First-hand accounts |\n| --- | --- | --- | --- | --- |\n| 5 | 18 | 30 | 22 | 12 |\n\n## What counts as done\n\nOne label from the caller's list with a probability per option, in one call, with low-probability answers routable to a human by threshold.\n\nMeasured, for our own tests: under 500 ms hosted or under 1 s local.\n\nHow agents ask for it: which team should handle this ticket; is this billing, shipping, technical or spam; which model tier does this prompt need; what is the intent of this message\n\n## Does the job\n\nThe docs show it meets the test above, and nothing we read says otherwise.\n\n- **Decision 3.0 (vLLM Semantic Router project)**: choice with a probability per option on /v1/systemone through vLLM, Engine mode or d3_server.py; 54 ms median text on d3 and 18 ms on d3-mini (MI325X). First on the Decision Index text board at 66.3. Languages not stated.\n- **Liquid d1 (Liquid AI, Inc.)**: POST /decisions/v1/systemone returns a choice, a probability per option and confidence; $0.02 per million input tokens with $2 free credit. Arize measured p50 0.20 s and Dataiku about 86 percent on routing. d1-2B's card lists 16 languages.\n- **Microsoft-Decision-1 (Microsoft)**: choice with a probability per option on Foundry's /providers/microsoft/v1/systemone or OpenRouter's Decisions API at $0.042 per million input tokens; OpenRouter shows 0.42 s latency and Dataiku about 86 percent. Microsoft's perturbation test found zero flips on reversed or shuffled options.\n- **OpenAI Decisions API (OpenAI OpCo, LLC)**: choice with probabilities and confidence, a documented 'other' fallback, and answers that can come back as refusal; Arize measured p50 0.16 s and Dataiku 91 percent, the best in its test. GPT-6 Luna needs the Build tier ($5 of credit).\n- **pplx-decider (Perplexity AI, Inc.)**: choice with 1 to 255 options returns a probability per option and confidence on /v1/decisions in Jev's state-and-questions shape, with an 'other: null' option in the example; $0.02 per million, 10 requests a second per organisation by default. Dataiku about 86 percent. Card lists no languages.\n- **pplx-decider-flash (Perplexity AI, Inc.)**: Same /v1/decisions shape at $0.01 per million with one question answered on its own; Decider for Mac runs it at 127.0.0.1 with no key for private text. Decision Index 54.81, 10.74 behind the 27B. Card lists no languages.\n\n## Does the job, with a limit\n\nIt does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.\n\n- **Celeris-1 Decision (Marqo Inc)**: Choice answers carry a probability per option and a rescaled confidence, up to 512 options, on /v1/systemone or /v1/decisions. Workspace activation still runs a capacity waitlist and credit needs a card with a $5 minimum. No latency figure is published for the decision model.\n- **Clef (Cloudflare, Inc.)**: choice with a probability per option, 1 to 64 questions a call, 10,000 free neurons a day. Vendor median 209 ms (Clef) and 39 ms (Clef-flash); Arize measured p50 0.50 s on RAGTruth-length inputs. Dataiku had Clef about 86 percent, Clef-flash 77. Languages unstated.\n- **Laya (Convai Innovations Pvt. Ltd.)**: laya-serve answers /v1/systemone in 33 ms on a T4 with a Router across 100+ languages, but the base checkpoints need fine-tuning: 0.425 on Banking77, weak past about 20 options and 37 percent on Hebrew intent (yuv.ai), Portuguese fell to 0.500 after 0.4.0 (issue 1453).\n- **Decider (Mark Marosi (Mapika))**: /v1/systemone with 2 to 255 options and a probability per option, 50 ms median on CUDA and 133 ms on an M1 Pro. English only by the README's limits; issue 9's Chinese cases failed, and the 2B needs bucket-like option names.\n- **Drex Max v1 (Nace AI, Inc.)**: choice returns a probability per option through /v1/systemone on the Python loader, Kapitsa, MLX or Nace's llama.cpp fork. The Open RAIL-M licence bars commercial use above $1 million in revenue or funding, and the card lists no languages.\n- **elephant-1 (Baseten Labs, Inc.)**: choice with a probability per option from one shared-prefix prefill, hosted on Baseten's /v1/systemone at $0.035 per million input tokens or locally through qev's DecisionEngine. The card's language is English only, and self-hosting needs OneJev at a pinned commit plus serve.patch.\n- **GLiClass (Knowledgator Engineering Ltd.)**: One forward pass scores every label with a softmax (classification_type single-label) up to 128 labels, locally on CPU or GPU. No Jev shape (issue 47 asks for one), F1 only on the cards, and issue 12 reports every label scoring 0.99.\n- **Granite Switch 4.1 (International Business Machines Corporation)**: The decision aLoRA returns a softmax over single-token option labels, read through vLLM chat completions with logprob_token_ids and max_completion_tokens 1; the caller writes the prompt, tokenises labels and chunks past 128 options. Decision Index 46.72 on the 8B (IBM's run).\n- **Kev (Jared Palmer)**: /v1/systemone with 1 to 255 options and a probability per option; Kev-4B answers six questions in 41.5 ms on an L40S and Arize had Kev 9B at 48 of 52 on routing. English only by the card, so non-English tickets are a blocker.\n- **JEV-27B-VL (AutoTrust AI Lab)**: POST /v1/decide takes one question a request with 2 to 256 options and returns a probability per option, about 264 ms a row on an RTX PRO 6000; CLINC150 with 150 intents zero-shot is on the card. Needs an 80 GB GPU and the card's vLLM development build.\n- **joey-1 (Baseten Labs, Inc.)**: choice with a probability per option from one shared-prefix prefill, hosted on Baseten's /v1/systemone at $0.01 per million input tokens or locally through qev's DecisionEngine. The card's language is English only, and self-hosting needs OneJev at a pinned commit plus serve.patch.\n- **mammoth-1 (Baseten)**: choice with a probability per option from one shared-prefix prefill, hosted on Baseten's /v1/systemone at $0.10 per million input tokens or locally through qev's DecisionEngine. The card's language is English only, and self-hosting needs OneJev at a pinned commit plus serve.patch.\n- **Drex 1.5 (Nace AI, Inc.)**: choice returns a probability per option and confidence on /v1/systemone, but drex-v1.5 is a retired id: the OpenAPI lists it among ids answered by drex-max-v1.1 at Max's limits and $0.03 per million. The $5 signup credit needs a Google or GitHub sign-in or a card. No latency figure published.\n- **RightNow System Zero (RightNow AI, Inc.)**: boolean, choice and score answers carry a decision, confidence and ranked alternatives, but every answer says calibrated: false in this release, latency headers come with no guarantee, and starting credit has its own rate and spend limits.\n- **ScaleDown (Carbon ScaleDown, Inc.)**: POST /v1/scaledown mirrors the Jev shape with a probability per option summing to 1, but /classify caps a request at 20 labels (16 multi-label), the key comes from sales, and no latency is published.\n- **SPEV (Sprag AI, Inc.)**: choice with 2 to 255 options returns a probability per option and confidence on an OpenAI-style /v1/decisions ($0.09 per million text tokens), with 60 requests a minute per organisation by default, a 402 without a payment method, and no published latency. Card says multilingual without a language list.\n- **kettei (Sqwish Ltd, trading as Sqwish Labs)**: POST /v1/decide (or the Jev shape on /v1/systemone) returns a probability per outcome for up to 128 decisions about one context, with a 'none' outcome and an abstain_below policy worked through in the ticket-routing example. New accounts may start on a waitlist, and no latency figure is published.\n- **Strands Decider 2B (Amazon Web Services, Inc.)**: /v1/systemone locally at 115 ms median on an RTX 3090 and 153 ms on an M3 Pro, but AWS Builder found German recall 16 percent, a 55 percent first-answer preference flipping on swap, routing AUC 0.51, and Dataiku had it at 65 percent against 86 for the leaders.\n- **Jev (TypeSafe AI, Inc.)**: choice up to 255 options with probabilities and confidence, a companion-noul pattern for none-of-these and 0.7/0.3 threshold guidance; OpenRouter's test had 59 of 60 intents at 0.194 s p50 and Arize p50 0.08 s. Early access runs behind a waitlist with no free tier found.\n- **Vela 2.0 (vLLM Semantic Router project (with KR Labs))**: choice over 2 to 255 options with a distribution through vela2_serve.py's /v1/systemone; MASSIVE unseen-scenario intent 0.727 on the 4B and a Jev Decision Index of 31.63, below its Decision 2.0 base. The 0.3B runs on CPU.\n\n1 listings in the category were added after this reading and aren't marked yet.\n\n## What stops agents finishing\n\n- waitlist or no free tier for a hosted model\n- label set over the model's option cap (Laya about 20, Jev 255)\n- non-English text with an English-only checkpoint\n- hosted endpoint behind a bot check that refuses the SDK's default user agent\n\n## Around it\n\nBefore: email.read, support.fetch-ticket, chat.receive-message. After: inference.llm.draft-reply, support.assign-queue, human-review.\n\n## Where this comes from\n\nWeight 22 of 100 in Decision models: 12 of 41 accounts; the most common job in the HN threads, the AWS Builder posts and the Dataiku and yuv.ai tests\n\nAs data: https://www.anchorterminal.com/api/v1/use-cases/decision-models.route-to-queue.json, or the MCP tool get_use_case with id decision-models.route-to-queue. Draft, read 2026-11-12 from public docs and first-hand accounts, not yet reviewed by a person.\n",
  "meta": {
    "attribution": "Anchor Terminal (https://www.anchorterminal.com)",
    "attributionRequired": true,
    "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)",
    "docs": "https://www.anchorterminal.com/docs/",
    "generatedAt": "2026-11-16",
    "license": "CC-BY-4.0",
    "method": "https://www.anchorterminal.com/benchmark/",
    "methodology": "0.8",
    "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": "For agents",
        "url": "https://www.anchorterminal.com/agents/"
      },
      {
        "name": "Niches",
        "url": "https://www.anchorterminal.com/niches/"
      },
      {
        "name": "Route a message or request to a queue, team, intent or model tier",
        "url": ""
      }
    ],
    "description": "Route a message or request to a queue, team, intent or model tier: 5 companies fully do it, 18 with a limit, 30 carry the tag. Every listing in Decision models with the reason and a source.",
    "facts": null,
    "h1": "Route a message or request to a queue, team, intent or model tier",
    "image": "https://www.anchorterminal.com/assets/og/default.png",
    "path": "/niches/decision-models.route-to-queue/",
    "published": "",
    "section": "agents",
    "title": "Route a message or request to a queue, team, intent or model tier |…",
    "toc": null,
    "updated": "2026-11-15",
    "url": "https://www.anchorterminal.com/niches/decision-models.route-to-queue/"
  },
  "tokens": {
    "markdown": 2600,
    "slim": 480
  },
  "version": 1
}
