Free
for individuals
$0
- Unlimited repo understanding
- 20 agent fixes / month
- Bring your own model key
- Local repos + private repos
- Self-host the full stack forever
Pricing
Start free. Self-host forever.
Verified fixes for about $0.02 each. Self-host on your own keys, free forever — or scale up when you're ready.
Pro
for professional developers
Coming soon
- Everything in Free
- Managed LLM, metered
- High monthly fix volume
- GitHub App + automatic fix PRs
- Faster concurrent runs
Team
for teams
Coming soon
- Everything in Pro
- Shared workspaces + seats
- Org-wide fix pool
- SSO + roles
Enterprise
for organizations
Custom
- Unlimited fixes
- On-prem / air-gapped self-host + support
- Audit, governance, SLA
- Dedicated success
Included
Every plan starts with understanding.
Why it's priced this way: understanding your repo is deterministic and costs almost nothing — so triage is unlimited on every plan. Agent fixes spend model tokens, so you pay only when you scale.
| Free | Pro | Team | Enterprise | |
|---|---|---|---|---|
Understand a repo triage | Unlimited | Unlimited | Unlimited | Unlimited |
Agent fixes fix | 20 / mo | High | Org pool | Unlimited |
| LLM | BYOK | Managed | Managed | Managed / on-prem |
| GitHub App + auto fix PRs | — | ✓ | ✓ | ✓ |
| Concurrent runs | 1 | Multiple | Multiple | Multiple |
| Seats / SSO | — | — | ✓ | ✓ |
| Self-host | ✓ forever | ✓ | ✓ | ✓ + support |
| Audit / governance / SLA | — | — | — | ✓ |
Every fix is verified by your own test suite before it lands.
Frequently asked
Triage is unlimited at no cost. You can map repositories, explore the dependency graph, and see blast-radius analysis — all for zero tokens, zero spend.
Yes. The self-hosted tier is free forever. You bring your own key, your code never leaves your infrastructure, and there is no expiration.
You connect your own API key from your preferred provider. Codna charges nothing for inference — you pay your provider directly, typically pennies per fix.
Fix generation is metered on managed plans. Triage — mapping repos, surfacing evidence bundles, identifying blast radius — stays unlimited regardless of plan.
The deterministic engine reduces each fix to a ~600-token evidence bundle, measured at 162x less context than reading the repo. Less context means dramatically lower inference cost — 5× fewer tokens than Cursor and 1.7× faster in head-to-head tests.
Yes. Managed plans handle hosting and scale with your usage. You get the same verified, test-confirmed fixes — without running your own infrastructure.