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

Translation skill (skill-translate) - OpenSmartRoute

All models

skill

Translation skill

skill-translate · runs as translategemma:4b via ollama-translategemma-4b

High-quality translation with glossary enforcement.

Answers requests here May receive personal data

Try in playground JSON

Price per 1M tokens: $0.50; the target's declared price
Requests · 30d: 9; +360%
Measured latency: 4.63 s; mean time to a complete answer over 30 days here · declared 400.0 ms
Success rate: 100.0%; of the requests it answered; the quality prior is 85% (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
cost

Tokens: 428
Spend: $0.0004
Previous window: 4 req

Routed for

Domains the signal layer detected on requests that ended here.

General2 · 67%
Customer Support1 · 33%

Capabilities

DomainsGeneral

ActionsTranslate

Complexity band0.00 - 1.00

Languages*

Context windowundeclared

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryPublic

Regionsanywhere

PIIallowed

Max input tokensunlimited

Tenantsall

Call it

Pin this target with model="skill-translate", 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": "skill-translate", "messages": [{"role": "user", "content": "Translate this product description into French and German."}]}'

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="skill-translate",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "Translate this product description into French and German."}],
    extra_body={"models": ["skill-translate", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)

One target among many