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

Mid-tier model (llm-mid) - OpenSmartRoute

All models

llm

Mid-tier model

llm-mid · runs as GPT-4.1 Mini OpenAI

Balanced model for moderate reasoning, drafting, data analysis and marketing copy.

Chosen and quoted; no provider connected yet Personal data blocked by policy Tool calling

Try in playground JSON

Price per 1M tokens: $3.00; the target's declared price; the vendor's list price is below
Requests · 30d: 0; no traffic
Declared latency: 900.0 ms; 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)

Underlying model

Catalogue entry

Published by the vendor; the platform bills at the target's declared price.

GPT-4.1 Mini

tools

OpenAI openai/gpt-4.1-mini

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.1% on hard...

Input $/1M: $0.40
Output $/1M: $1.60
Context: 1.0M
Max output: 33K
Released

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: General, Marketing, Data Analysis, Hr, Travel, Creative.

Capabilities

DomainsGeneral, Marketing, Data Analysis, Hr, Travel, Creative

ActionsGeneration, Summarize, Reasoning, Planning, Extract, Q&A

Complexity band0.25 - 0.75

Languages*

Context windowundeclared

Streamingyes

Policy constraints

Hard stops enforced before scoring.

Data boundaryPublic

Regionsanywhere

PIInot allowed

Max input tokensunlimited

Tenantsall

Route to it

This llm is not executed by the platform. Ask the router for a decision restricted to kinds=["llm"] 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": "Draft a newsletter announcing our new pricing tiers.", "kinds": ["llm"], "top_k": 3}'

# Returns the chosen target, confidence, the ranked alternatives and the
# per-strategy trace. Execution of llm 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": "Draft a newsletter announcing our new pricing tiers.", "kinds": ["llm"]},
)
d = r.json()
print(d["target"]["id"], d["confidence"])
print([t["id"] for t in d["ranked"]])  # e.g. llm-mid first when it fits

One target among many

Mid-tier model is chosen per request, and the trace says why.

The figures above are this target's own record on this deployment: what it cost, how fast it answered, how often the people who used it said the answer was good. The router weighs that record against every other candidate for each request, so pinning it is a choice you make, not one you are stuck with.

Photo: Varun Bhatheja

For the business

What it means for which models you pay for.

Catalogue of every vendor
The right model, not the famous one
Price, context, abilities and benchmark indexes side by side, with the model that fits each task named.
The rankings
89% less
Lower cost per request
On the 150-prompt benchmark the router spent 89% less than sending every prompt to the reference model, and the judged quality went up, not down.
Read the benchmark
Per million tokens, every model
Prices you can compare

Send Mid-tier model a request - or let the router decide.

Create a free workspace, mint a key and route the request above; the trace shows this target's score against every alternative.

Create a free account Try it in the playground