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

Rankings

Who delivers, task by task.

Which model, agent, skill, tool or person actually gets the job done, per kind of task - ranked by the outcomes people report. A long record beats a lucky streak: the score is the lower confidence bound of the success rate. Counted across the whole deployment, never shown per workspace.

Requestslast 7 days · every workspace: 0
Targets0 ranked · 0 provisional, under 20 reported outcomes: 0
Task domainswith routed traffic in the window: 0

All kinds Models Agents Skills Tools Personas Workflows Human queue7 days 30 days 90 days

Targets ranked by reported outcomes over 7 days
#	Target	Score	Success	Quality	Requests	p50 latency	Cost / request

Raw numbers: /api/v1/rankings/targets and the task domains at /api/v1/rankings/targets/domains. Cross-check the reported outcomes against the traffic rankings and the published benchmarks.

Reported, then counted

A rank here is earned one reported outcome at a time, across every workspace.

When a team marks an answer good or bad, that report joins the record of the target that produced it - a model, an agent, a skill, a tool or a person. The score is the lower confidence bound of the success rate, so a long record beats a lucky streak, and the same record is what the router learns from when it chooses next time.

Photo: MART PRODUCTION

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

Your targets earn their rank the same way.

Declare the models, agents and tools you use, route through them and report outcomes; the router learns from your record, and the trace shows the score behind every pick.

Create a free account Read the guide

Who delivers, task by task.

A rank here is earned one reported outcome at a time, across every workspace.

What it means for which models you pay for.

The right model, not the famous one

Lower cost per request

Prices you can compare

Your targets earn their rank the same way.