Free
個人向け
$0
- リポジトリ理解 無制限
- エージェント修正 月 20 回
- 自分のモデルキーを持ち込む
- ローカル + プライベートリポジトリ
- フルスタックを永久にセルフホスト
個人向け
$0
プロ開発者向け
$20/mo
$17/mo$204/yr
Everything in Free, plus
For power users clearing a backlog of red PRs — more parallelism, more allowance, deeper security.
$60/mo
$51/mo$612/yr
Everything in Pro, plus
Maximum throughput for whole-repo migrations and the busiest teams.
$200/mo
$170/mo$2,040/yr
Everything in Pro+, plus
チーム向け
$40/mo
$34/mo$408/yr
Everything in Pro, plus
for production deployments
$200/Compute Unit/mo
$167/Compute Unit/mo$2,000/yr
Production deployment license
組織向け
Custom
Everything in Team, plus
含まれる機能
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 | |
|---|---|---|---|---|
リポジトリ理解 triage | 無制限 | 無制限 | 無制限 | 無制限 |
エージェント修正 fix | 20 / mo | High | Org pool | Unlimited |
| LLM | BYOK | Managed | Managed | Managed / on-prem |
| GitHub App + 自動修正 PR | — | ✓ | ✓ | ✓ |
| 並列実行数 | 1 | Multiple | Multiple | Multiple |
| シート / SSO | — | — | ✓ | ✓ |
| セルフホスト | ✓ forever | ✓ | ✓ | ✓ + support |
| 監査 / ガバナンス / SLA | — | — | — | ✓ |
Every fix is verified by your own test suite before it lands.
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.