Security in every review: Semgrep runs before the model reads a line See how

Pricing

Pay for reviews directly with your model provider.

Every review runs on your own model keys, so your provider bills the tokens and we add nothing on top. The plan covers the platform, with unlimited seats.

Free for 3 repositories and 250 events a month, no card

On-premise

For teams whose code never leaves the building. The full platform deployed inside your network, air-gapped if you need it, with your own model endpoints, premium plugins included and no event metering.

Talk to us

Estimate

Work out your month

Put in what your team ships in a typical month. Nothing is sent anywhere; the sum happens in your browser.

1,000 events a month

Lands on Solo $14 well inside the 2,000 included

Each webhook counts 1. A redelivery of the same webhook does not count. MCP reads by your coding agents are free.

A monorepo counts as one repository, and a quiet one costs you nothing but its place in the band. Splitting a service out should be an architecture decision, not a billing one.

At the limit

When your workspace uses its monthly events, reviews pause until the allowance resets. On a paid plan you can choose overage instead, and extra events bill at your plan’s rate up to a cap you set.

And what the models cost

The plan price is the platform: holding your repositories, indexing them, and serving the graph. Every review runs on your own OpenAI, Anthropic or compatible key, so your provider bills the models directly and we never mark them up.

Start

Two ways to start

Run the engine on your own machine, or connect a repository on the cloud and read the first review. Neither needs a card.

On your machine

curl -fsSL https://raw.githubusercontent.com/sourceant/cli/main/scripts/install.sh | sh

FAQ

Questions

How the price works

Do you charge per seat?

No. Adding engineers or agents does not change your bill. Plans scale on how many repositories you connect and how many events arrive each month.

What counts as an event?

One webhook that arrives at your workspace, such as a push, a pull request update or a comment. Each one counts as 1. A redelivery of the same webhook does not count.

Do MCP reads by coding agents count?

No. MCP reads by your coding agents are free and never count as events.

What happens at the limit?

Reviews pause until the allowance resets. On a paid plan you can choose overage instead: extra events bill at your plan’s rate, up to a cap you set.

Why bands rather than pure usage?

A pure meter makes the bill hard to predict. A plan gives you a number you can budget, and you decide what happens at the limit.

Is the overage rate for model usage?

No. Overage is the platform meter: events past your included allowance. Model usage is billed by your own provider, never by us.

Is there a free plan?

Yes. Every workspace starts on Free: 250 events a month across 3 repositories, with no card. It pauses at the allowance rather than billing past it, and starts again when the allowance resets.

We have thousands of engineers on a handful of monorepos. What do we pay?

Whatever band your event volume lands in, and nothing for the engineers. A monorepo counts as one repository, so a large team on few repositories usually sits lower than its headcount would suggest. Talk to us and we will size it from your real pull-request and commit volume rather than guessing.

Models and keys

Do we need our own model keys?

Yes. Every plan, including Free, runs on your own OpenAI, Anthropic or compatible key. Your provider bills each review directly, and we bill you nothing for inference.

Are retried runs billed?

By your provider, yes. A run that had to be retried consumed its tokens twice, and your provider bills both. We never bill tokens.

Which AI tools does it work with?

Any tool that speaks MCP. Context and graph queries are served over a standard interface, so you are not locked to one assistant.

What you get, and where it runs

Is anything held back from a smaller plan?

Plans differ by how many repositories you connect and how many events arrive each month. Code review, your team’s knowledge and unlimited seats come with every plan. Memory and Triage are add-ons.

Can we try it before paying?

Yes, two ways. Install the CLI and run the engine on your own machine, which is free and needs no account. Or start on the cloud on the free plan: 250 events a month, for as long as you like. Move to a paid plan when you need more.

Can we run it on-prem or air-gapped?

Yes. On-premise deploys the full platform inside your network, premium plugins included, and supports air-gapped setups with your own model endpoints. There is no event metering on-prem. Talk to us at hello@sourceant.ai.

Something not answered here? Ask us directly.