Free
per singoli sviluppatori
$0
- Comprensione repo illimitata
- 20 correzioni agente / mese
- Porta la tua chiave del modello
- Repo locali + repo privati
- Self-host dello stack completo per sempre
Prezzi
Inizia gratis. Self-host per sempre.
Capire è deterministico, quindi il triage è illimitato. Le correzioni tramite agente consumano token, quindi paghi solo quando scala.
Pro
per sviluppatori professionisti
Coming soon
- Tutto del piano Free
- LLM gestito, a consumo
- Elevato volume mensile di correzioni
- GitHub App + PR di correzione automatiche
- Esecuzioni concorrenti più veloci
Team
per team
Coming soon
- Tutto del piano Pro
- Workspace condivisi + licenze
- Pool di correzioni a livello org
- SSO + ruoli
Enterprise
per organizzazioni
Custom
- Correzioni illimitate
- Self-host on-prem / air-gapped + supporto
- Audit, governance, SLA
- Successo dedicato
Incluso
Ogni piano inizia con la comprensione.
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 | |
|---|---|---|---|---|
Analisi di un repo triage | Illimitata | Illimitata | Illimitata | Illimitata |
Correzioni agente fix | 20 / mese | Elevato | Pool org | Illimitate |
| LLM | BYOK | Gestito | Gestito | Gestito / on-prem |
| GitHub App + PR di correzione automatiche | — | ✓ | ✓ | ✓ |
| Esecuzioni concorrenti | 1 | Multiple | Multiple | Multiple |
| Licenze / SSO | — | — | ✓ | ✓ |
| Self-host | ✓ per sempre | ✓ | ✓ | ✓ + supporto |
| 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.