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.

LLM router

An LLM router that picks the model per request - and shows you why.

OpenSmartRoute is an open-source LLM router. Every request is read, priced against every model you allow and sent to the cheapest one that meets your quality rules, with a trace of the decision. OpenAI-compatible, self-hostable, free plan.

Get a free API key Route this request in the playground

Free plan, no card. Open source under Apache-2.0; self-hosting is free forever.

From the benchmark

89%

less spent than always using the frontier model

On 150 real prompts the router cost 89% less than sending every one to the frontier model, at a higher judged quality (9.53 vs 9.15, two blind judges).

The whole benchmark, with the cases the router lost

The problem

One model for everything is the expensive way to be wrong.

A frontier model answers a one-line rewrite and a forty-page analysis at the same price. A small model is fine for the first and fails the second. Picking by hand does not scale past one application, and a hard-coded if/else on prompt length is not a strategy.

Every request pays frontier prices, whatever it asked for
Switching models means a code change and a redeploy
Nobody can say afterwards why a request went where it went

How the router answers it

Three things it does for every request.

Reads the request first
Task, complexity, domain, language, whether it carries personal data - signals extracted on the way in, before any model is called.
Prices every candidate
Each model you allow is scored on quality for this task, cost for this length and latency; your policy removes the ones that may not answer. The best value wins.
Explains and learns
The answer carries the model, the confidence, the alternatives and the cost. Report whether it was good and the next decision moves.

Watch one decision

Illustrative: the lowest cost that still clears the quality the task needs. The live quote below is the real one.

A real request

Rewrite this paragraph in plain English for a customer e-mail.

A short rewrite routes to a small, fast model; change the prompt to a step-by-step analysis and the same call picks a reasoning model. Same code.

Route it in the playground and read the trace

The callpython

from openai import OpenAI

client = OpenAI(base_url="https://opensmartroute.ai/v1",
                api_key=OSR_API_KEY)
reply = client.chat.completions.create(
    model="auto",                     # the router picks
    messages=[{"role": "user", "content": "<prompt>"}],
)
print(reply.choices[0].message.content)
print(reply.model)                    # the model that answered

Where this stands next to the alternatives, and how to go deeper.

Install

pip install "opensmartroute[yaml]"

Python, TypeScript, CLI or any OpenAI client

Or no install at all: the hosted API answers a plain curl with the decision, and the browser extension shows the price and the router's pick under the composer of the AI chat sites you already use.

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
The catalogue prints input and output prices and what three typical monthly workloads cost on each.
The model catalogue

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.

Route your first request in under a minute.

OpenSmartRoute is open source and the free plan keeps the full trace of every decision. Create a workspace, mint a key and send the request above.

Create a free account Read the benchmark

Free plan, no card. Fifteen thousand decisions a month with the full trace.

from openai import OpenAI client = OpenAI(base_url="https://opensmartroute.ai/v1", api_key=OSR_API_KEY) reply = client.chat.completions.create( model="auto", # the router picks messages=[{"role": "user", "content": "<prompt>"}], ) print(reply.choices[0].message.content) print(reply.model) # the model that answered

An LLM router that picks the model per request - and shows you why.

One model for everything is the expensive way to be wrong.

Three things it does for every request.

Reads the request first

Prices every candidate

Explains and learns

Rewrite this paragraph in plain English for a customer e-mail.

Where this stands next to the alternatives, and how to go deeper.

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Route your first request in under a minute.

An LLM router that picks the model per request - and shows you why.

One model for everything is the expensive way to be wrong.

Three things it does for every request.

Reads the request first

Prices every candidate

Explains and learns

Rewrite this paragraph in plain English for a customer e-mail.

Where this stands next to the alternatives, and how to go deeper.

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Route your first request in under a minute.