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

On-prem private model (llm-onprem) - OpenSmartRoute

All models

llm

On-prem private model

llm-onprem · runs as qwen3.5:4b via ollama-qwen3-5-4b

Self-hosted model for sensitive data that must not leave the boundary.

Answers requests here On Prem boundary May receive personal data

Try in playground JSON

Price per 1M tokens: $1.00; the target's declared price
Requests · 30d: 71; +549%
Measured latency: 5.64 s; mean time to a complete answer over 30 days here · declared 1.20 s
Success rate: 98.6%; of the requests it answered; the quality prior is 70% (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 21)
failed
cost

Tokens: 3.9K
Spend: $0.0053
Previous window: 2 req

Routed for

Domains the signal layer detected on requests that ended here.

General5 · 56%
General Chat1 · 11%

Capabilities

DomainsGeneral, Finance, Legal, Medical, Hr, Customer Support

ActionsSummarize, Extract, Q&A, Classify, Generation

Complexity band0.00 - 0.70

Languages*

Context windowundeclared

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryOn Prem

RegionsEU, IN

PIIallowed

Max input tokensunlimited

Tenantsall

Call it

Pin this target with model="llm-onprem", 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": "llm-onprem", "messages": [{"role": "user", "content": "Extract the account number and email from this support ticket."}]}'

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="llm-onprem",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "Extract the account number and email from this support ticket."}],
    extra_body={"models": ["llm-onprem", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)

One target among many