Which LLM is the cheapest for our workload?

The best-for pages rank the live catalogue per task by the index that measures it, and the router picks the cheapest model that meets your quality rule for each request.

How much can we save on our LLM bill?

On the public benchmark the router saved 89% against sending everything to the reference model. Import last month's provider bill on the bill page and the estimate is computed on your own traffic before you change a line of code.

How often do model prices change?

The catalogue is refreshed from the vendors' price lists; each model page shows the date of its data.

90 days of the enterprise, pro and team plans free, no card needed. See the plans

OpenSmartRoute

Friendly support persona (persona-friendly-support) - OpenSmartRoute

All models

personaplan slot only

Friendly support persona

persona-friendly-support · runs on the model the router picks for the request

Warm, concise, de-escalating tone for customer conversations.

Chosen and quoted; no provider connected yet May receive personal data

Try in playground JSON

Price per 1M tokens: free; the target's declared price
Requests · 30d: 0; no traffic
Declared latency: -; from the catalogue entry; nothing measured here in the window
Success rate: n/a; of the requests it answered; the quality prior is 75% (the router's starting estimate, not a benchmark)

Traffic over 30 days

Requests per day this target answered on this deployment, with the cost line.

No requests yet. Route something from the playground to see usage here.

Tokens: 0
Spend: $0
Previous window: 0 req

Routed for

Domains the signal layer detected on requests that ended here.

No routed requests yet. Declared domains: Customer Support, General Chat.

Capabilities

DomainsCustomer Support, General Chat

ActionsQ&A, Action, Generation

Complexity band0.00 - 1.00

Languagesen

Context windowundeclared

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryPublic

Regionsanywhere

PIIallowed

Max input tokensunlimited

Tenantsall

Route to it

This persona is not executed by the platform. Ask the router for a decision restricted to kinds=["persona"] and dispatch the winner in your own stack; send feedback afterwards so the learners improve.

curlbash

curl https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route \
  -H "Authorization: Bearer $OSR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "I'm frustrated, my order still hasn't arrived.", "kinds": ["persona"], "top_k": 3}'

# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of persona targets happens in your stack.

httpxpython

import httpx

r = httpx.post(
    "https://osr-api.kindrock-caaab1a2.centralindia.azurecontainerapps.io/api/v1/route",
    headers={"Authorization": "Bearer osr_live_..."},
    json={"text": "I'm frustrated, my order still hasn't arrived.", "kinds": ["persona"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]])  # e.g. persona-friendly-support first when it fits

One target among many