Image model with strong prompt adherence and accurate typography — create, edit, and remix.
Reve (Reve AI, Inc.) builds its own image model, Reve Image, known for strong prompt adherence, refined aesthetics, and accurate in-image typography. On Opper it powers text-to-image creation, instruction-based editing, and multi-reference remixing through a single model. US-hosted; Reve's API terms commit to no training on your inputs or outputs. The route to pick for high-fidelity image generation and editing where prompt accuracy and legible text matter.
Every model we route through Reve. Compare residency, ZDR, training posture, and price at a glance — full data-handling detail per route below.
| Model | Region | Zero data retention | Training | Context | Input | Output |
|---|---|---|---|---|---|---|
| US | Enterprise | No | — | — | — |
Reve hosts on 1 route. Each route has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; unknown.
