Pricing

Usage-based pricing with a free tier

Pay for token usage, CPU, memory, and platform fees. Every account gets $10 of free usage each month. No per-seat fees or idle charges.

10

Engineers shipping code to your repositories

1.5 PRs/wk

Pull requests opened per developer each week

50%

Share of those PRs written by @ellipsis

Enable AI code review

Review every PR against your rules and past feedback

Estimated monthly bill
$75/ month

3 PRs/day for a team of 10 developers using AI for 50% of PRs

Code reviews65 runs × $0.55
$36
Agent runs33 runs × $1.50
$50
Free tier
-$10
Total per month$75

What you pay for

Simple metering for each run. Nothing idle, no seats.

Ellipsis CloudPrivate Cloud
TokensAt cost, no markup$0
CPU$0.142 / vCPU-hour$0
Memory$0.024 / GB-hour$0
Platform fee50% of usage50% of usage

Metering

Pay for what each run uses

Every agent run is metered by tokens, CPU, and memory. Run on Ellipsis Cloud, or in your own AWS account and pay only the platform fee.

Examples

What a single run costs

The same per-run prices the estimator uses, broken down by what each run meters.

Code review on a pull request

$0.55

Ellipsis reads the diff, checks it against your team's conventions and past review feedback, then leaves inline comments. No sandbox spins up, so you pay only for tokens and the fee.

Tokens
$0.37
CPU
$0.00
Memory
$0.00
Fee
$0.18

Fix a 2am Sentry alert

$0.54

Someone shipped a query without an "is not null" guard and prod is throwing. Ellipsis reads the Sentry stack trace, finds the unguarded access, adds the check, and opens a PR before the team wakes up.

Tokens
$0.30
CPU
$0.07
Memory
$0.02
Fee
$0.15

Bump a dependency and fix the breakage

$0.84

A minor version bump changes a function signature. Ellipsis updates every call site, runs your test suite until it is green, and opens the PR.

Tokens
$0.46
CPU
$0.12
Memory
$0.03
Fee
$0.23

Add a missing test

$0.79

Coverage dropped on a new endpoint. Ellipsis writes a test that exercises the happy path and the edge cases, confirms it passes, and pushes it.

Tokens
$0.42
CPU
$0.13
Memory
$0.03
Fee
$0.21

Track down a flaky test

$1.16

A test passes locally but fails one CI run in ten. Ellipsis reproduces the failure, traces the race across files, and pushes a fix.

Tokens
$0.64
CPU
$0.16
Memory
$0.04
Fee
$0.32

Build a small feature

$1.50

Add an API route with a schema, validation, and tests. Ellipsis spins up a sandbox, writes it end to end, runs the tests, and opens the PR.

Tokens
$0.83
CPU
$0.20
Memory
$0.05
Fee
$0.42

Frequently asked questions

Every account gets the first $10 of usage free each calendar month. Because common runs cost cents, that covers roughly 45 quick fixes, 32 code reviews, or 14 small features before you pay anything. Public GitHub repositories are free.

Every agent runs in its own sandbox, and you pay for exactly what that run consumes: CPU and memory metered by the second (rates above), tokens passed through at Claude's rates with no markup, and a small per-run platform fee. Nothing runs idle, so nothing bills idle.

A quick fix, such as raising a job timeout, lands near $0.22 total. A code review on a medium PR is about $0.31. A flaky test investigation is about $0.38. Bigger tasks with more files and longer runs cost more, but common runs still land in cents.

No. There are no per-seat fees. Your entire team can use Ellipsis. You only pay for what your agents do.

Yes. Ellipsis is free for public GitHub repositories. Private repos get the $10/month free tier.

Yes. Set monthly spending caps per team or per repo in the dashboard. Once the cap is reached, agents pause until the next billing cycle.

Yes. Volume discounts, priority support, dedicated onboarding, and custom SLAs. Email team@ellipsis.dev to discuss.