GLiNER-2.5-Decide

Context

Max output

–

Input → output

text → typed answers

Weights

–

Providers

1 provider · list price, latency and uptime

ProviderInput /1MOutput /1MTTFB p50Uptime · hourly, 24hRetention

Fastino

direct API

$0.03$0.00–

–

none

Context: 8K
Max output: –
Cache read /1M: –
Precision: –
Regions: default
Headquarters: –
Data retention: Zero retention

Uptime · last 3 days10-05 04:00 – 10-08 03:36 UTC

MonTueWedNow

By default the router tries our listings in routing order and fails over before the first byte — never mid-answer. Prices are each provider's own list price; you pay $0.03 in / $0.00 out per 1M, whichever runs the request. Uptime is our own measurement; an hour stays grey until it has a sample. Open the row for the provider's specs and policies.

Quickstart

plain HTTP — one JSON call, one typed answer per question

curl https://api.routerplus.com/v1/decisions \
  -H "Authorization: Bearer $TM_API_KEY" -H "content-type: application/json" \
  -d '{"model":"fastino/gliner-2.5-decide",
       "state":"Help! My payouts have been failing for 3 days.",
       "schema":{"classifications":[
         {"task":"Which team should handle this?",
          "labels":["billing: Payments and refunds","technical: Bugs and outages"]},
         {"task":"Is this urgent?","labels":["yes","no"]}]}}'
# answers["Which team should handle this?"].label and .confidence, answers["Is this urgent?"].label

import os, httpx
r = httpx.post("https://api.routerplus.com/v1/decisions",
  headers={"Authorization": f"Bearer {os.environ['TM_API_KEY']}"},
  json={"model": "fastino/gliner-2.5-decide", "state": "Help! My payouts have been failing for 3 days.",
        "schema": {"classifications": [{"task": "Is this urgent?", "labels": ["yes", "no"]}]}})
r.json()["answers"]["Is this urgent?"]  # {"label": "yes" | "no", "confidence": 0–1}

const r = await fetch("https://api.routerplus.com/v1/decisions", {
  method: "POST",
  headers: { authorization: `Bearer ${process.env.TM_API_KEY}`, "content-type": "application/json" },
  body: JSON.stringify({ model: "fastino/gliner-2.5-decide", state: "Help! My payouts have been failing for 3 days.",
    schema: { classifications: [{ task: "Is this urgent?", labels: ["yes", "no"] }] } }),
});
const { answers } = await r.json();  // answers["Is this urgent?"]: { label: "yes" | "no", confidence: 0–1 }

.qs pre[hidden] { display: block; border-top: 1px solid var(--code-line); } .qsb { display: none; } .qcode::before { content: attr(data-lang); display: block; color: var(--code-muted); font-size: 11px; margin-bottom: 6px; }

Pricing

per 1M tokens

prompt	$0.03
completion	$0

Every billed response carries usage.cost — recompute your bill from the wire.

Uptime

10-05 04:00 – 10-08 03:36 UTC

Last 3 days–last 24h · TTFB p50 – · uptime n<100

MonTueWedNow

An hour counts at the best provider's uptime: a request goes to another provider when one fails. Grey hours have no sample yet.