Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

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 do we compare AI gateways and routers?

The compare pages score each product against the same documented capabilities and say when the review was done; the benchmark page shows measured cost and quality, including the cases the router lost.

Model catalogue

Every AI model vendor, side by side

59 vendors and 468 models in one catalogue. Each vendor page lists prices per million tokens, context windows, what each model can read and produce, and benchmark scores, so you pick models on real numbers rather than reputation.

Browse every model Price a workload

Prices are vendor list prices per million tokens; OpenSmartRoute routes to the cheapest target that meets your quality bar.

One contract, every vendor

Keep the vendor accounts you already have; let the router decide which one answers.

Each vendor page prices its models side by side so a decision is a number, not a reputation. Bring your own keys for the vendors you already pay, or buy by the token here, and the same request is scored against all of them - the trace names the vendor that answered and what the alternatives would have cost.

Photo: LinkedIn Sales Navigator

For the business

What it does for the vendor strategy.

One URL, every vendor
No vendor lock-in
Point your OpenAI-compatible client at one address; add, swap or retire providers in the catalogue without touching application code.
Every vendor side by side
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
Self-hosting is free
Open source, Apache-2.0
The router is a library, a sidecar or a control plane you can run yourself, so the exit is always open.
What is open

Will this lock us into another vendor?: No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.
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 do we compare AI gateways and routers?: The compare pages score each product against the same documented capabilities and say when the review was done; the benchmark page shows measured cost and quality, including the cases the router lost.

Keep every vendor. Pay only the one that answers.

Connect the provider accounts you already have, or buy by the token here. Either way each request is priced against all of them before it is sent.

Create a free account Connect a provider

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

Every AI model vendor, side by side

OpenAI

Google

Qwen

Anthropic

Mistral AI

Z.ai

DeepSeek

NVIDIA

MiniMax

Moonshot AI

xAI

Meta

Meta Llama

Tencent

Aion Labs

ByteDance Seed

Cohere

OpenRouter

Amazon

Perplexity

Xiaomi

Poolside

Sakana AI

Thinking Machines

Inception

inclusionAI

Nous Research

StepFun

TheDrummer

Unbiased

Upstage

IBM Granite

Inference Net

Liquid AI

Moondream

Morph

Nex AGI

Perceptron

Reka

Relace

Sao10K

Scaledown

Anthracite

Arcee AI

ByteDance

Cognitive Computations

dots.studio

Elorian

Fireworks

Gryphe

Mancer

Meituan LongCat

Microsoft

Prism Ml

Reflection

Typesafe

Undi95

Writer

Xingchen Agi

Keep the vendor accounts you already have; let the router decide which one answers.

What it does for the vendor strategy.

No vendor lock-in

Lower cost per request

Open source, Apache-2.0

Keep every vendor. Pay only the one that answers.

Every AI model vendor, side by side

OpenAI

Google

Qwen

Anthropic

Mistral AI

Z.ai

DeepSeek

NVIDIA

MiniMax

Moonshot AI

xAI

Meta

Meta Llama