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

Human escalation queue (human-escalation) - OpenSmartRoute

All models

human

Human escalation queue

human-escalation · runs as a person on the queue

Live human agent for escalations, safety issues, or when confidence is low.

Answers requests here May receive personal data

Try in playground JSON

Price per 1M tokens: $500; the target's declared price
Requests · 30d: 2; +100%
Measured latency: 22.7 ms; mean time to a complete answer over 30 days here · declared 5.0 min
Success rate: 100.0%; of the requests it answered; the quality prior is 90% (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.

requests (peak 2)
failed

Tokens: 0
Spend: $0
Previous window: 1 req

Routed for

Domains the signal layer detected on requests that ended here.

No routed requests yet. Declared domains: General, Customer Support, Legal, Medical, Finance.

Capabilities

DomainsGeneral, Customer Support, Legal, Medical, Finance

ActionsEscalate, Action, Q&A

Complexity band0.00 - 1.00

Languages*

Context windowundeclared

Streamingyes

Tagssafety

Policy constraints

Hard stops enforced before scoring.

Data boundaryPublic

Regionsanywhere

PIIallowed

Max input tokensunlimited

Call it

Pin this target with model="human-escalation", or send a candidate list and let the router choose and fall back.

curlbash

curl https://api.opensmartroute.ai/v1/chat/completions \
  -H "Authorization: Bearer $OSR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "human-escalation", "messages": [{"role": "user", "content": "I want to speak to a real person right now."}]}'

OpenAI SDKpython

from openai import OpenAI

client = OpenAI(base_url="https://api.opensmartroute.ai/v1", api_key="osr_live_...")
resp = client.chat.completions.create(
    model="human-escalation",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "I want to speak to a real person right now."}],
    extra_body={"models": ["human-escalation", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)

One target among many