Free
pour les particuliers
$0
- Compréhension de dépôt illimitée
- 20 corrections d'agent / mois
- Apportez votre propre clé de modèle
- Dépôts locaux + dépôts privés
- Auto-hébergement complet pour toujours
Tarifs
Démarrez gratuitement. Auto-hébergez pour toujours.
La compréhension est déterministe, donc le triage est illimité. Les corrections d'agent consomment des tokens, vous payez donc uniquement quand vous passez à l'échelle.
Pro
Popularpour les développeurs professionnels
$20/mo
$17/mo$204/yr
Everything in Free, plus
- 3 parallel fixes · 3 devices
- Always offline-first — CLI
- Security autofix — deepest level, always (secrets, CVEs, IaC)
- 150 cloud fix PRs / month via the GitHub App
- Bring your own key for uncapped usage
Pro+
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
- 10 parallel fixes · 5 devices
- 500 cloud fix PRs / month via the GitHub App
- Priority fix queue
- All frontier models
- Bring your own key for uncapped usage
Ultra
Maximum throughput for whole-repo migrations and the busiest teams.
$200/mo
$170/mo$2,040/yr
Everything in Pro+, plus
- 25 parallel fixes · 10 devices
- Unlimited cloud fix PRs via the GitHub App (fair use)
- Highest-priority fix queue
- Earliest access to new models
- Bring your own key for uncapped usage
Team
pour les équipes
$40/mo
$34/mo$408/yr
Everything in Pro, plus
- 5 parallel fixes · 2 devices per seat
- Pooled model allowance across the team
- 250 cloud fix PRs / month via the GitHub App
- Centralized billing usage analytics
- Shared fix rules · SSO available
Server
for production deployments
$200/Compute Unit/mo
$167/Compute Unit/mo$2,000/yr
Production deployment license
- Licensed per Compute Unit — 1 CU = 4 vCPU
- Pinned node or floating pool via your own relay
- Fully air-gapped activation
- RS256-signed license, verified locally
- No usage monitoring — runs on your hardware
- A lapse degrades to Free — the runtime never stops
Enterprise
pour les organisations
Custom
Everything in Team, plus
- Corrections illimitées
- Auto-hébergement on-prem / air-gapped + support
- Audit, gouvernance, SLA
- Succès dédié
Inclus
Chaque plan commence par la compréhension.
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 | |
|---|---|---|---|---|
Comprendre un dépôt triage | Illimité | Illimité | Illimité | Illimité |
Corrections d'agent fix | 20 / mois | Élevé | Pool org | Illimité |
| LLM | BYOK | Managé | Managé | Managé / on-prem |
| GitHub App + PRs de correction auto | — | ✓ | ✓ | ✓ |
| Exécutions concurrentes | 1 | Plusieurs | Plusieurs | Plusieurs |
| Sièges / SSO | — | — | ✓ | ✓ |
| Auto-hébergement | ✓ pour toujours | ✓ | ✓ | ✓ + support |
| Audit / gouvernance / 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.