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

Small writing model (writer-small) - OpenSmartRoute

All models

llm

Small writing model

writer-small · runs as qwen3.5:4b via ollama-qwen3-5-4b

Self-hosted small (4B-class) instruct model for clear multilingual prose - posts, emails, summaries, product copy, translations and everyday communication at near-zero cost. The browser extension's writing help and the desktop bar's fixes land here.

Answers requests here On Prem boundary May receive personal data

Try in playground JSON

Price per 1M tokens: $0.05; the target's declared price
Requests · 30d: 1.3K; 10x+
Measured latency: 3.7 min; mean time to a complete answer over 30 days here · declared 1.3 min
Success rate: 99.9%; of the requests it answered; the quality prior is 60% (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 170)
failed
cost

Tokens: 3.2M
Spend: $0.47
Previous window: 1 req

Routed for

Domains the signal layer detected on requests that ended here.

Capabilities

DomainsGeneral, Marketing, Creative

ActionsGeneration, Summarize, Translate

Complexity band0.00 - 0.50

Languages*

Context windowundeclared

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryOn Prem

Regionsanywhere

PIIallowed

Max input tokensunlimited

Tenantsall

Call it

Pin this target with model="writer-small", 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": "writer-small", "messages": [{"role": "user", "content": "Write a short, friendly email announcing our office move next month."}]}'

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="writer-small",            # pin this target, or "auto" to let the router choose
    messages=[{"role": "user", "content": "Write a short, friendly email announcing our office move next month."}],
    extra_body={"models": ["writer-small", "auto"]},   # fall back to the router's pick if it fails
)
print(resp.model, resp.choices[0].message.content)

One target among many