Console

Bespoke Nimble v3

Context
33K
Max output
–
Input → output
text → typed answers
Weights
–
Providers
1
01

Providers

1 provider · list price, latency and uptime
ProviderInput /1MOutput /1MTTFB p50Uptime · hourly, 24hRetention
1
Bespoke Labs
direct API
$0.04$0.00219 ms
100.00%
may retain
Context
33K
Max output
–
Cache read /1M
–
Precision
–
Regions
default
Headquarters
–
Data retention
May retain prompts
Uptime · last 3 days10-05 04:00 – 10-08 03:35 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 $0.04 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.

02

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":"bespokelabs/nimble-v3",
       "state":"Help! My payouts have been failing for 3 days.",
       "questions":{
         "team":{"type":"choice","instructions":"Which team should handle this?",
                 "criteria":{"billing":"Payments and refunds","technical":"Bugs and outages"}},
         "urgent":{"type":"noul","instructions":"Is this urgent?"}}}'
# answers.team.choice, answers.team.probabilities, answers.urgent.noul
03

Pricing

per 1M tokens · 100% off every decision while the offer lasts; usage.cost is the debit
prompt$0.04
completion$0

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

04

Uptime

10-05 04:00 – 10-08 03:35 UTC
Last 3 days–last 24h · 126 requests · TTFB p50 219 ms · uptime 100.00%
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.