Reve 2.0

Released
2026-06-03
Last refreshed
2026-07-09
Status
Researched 135d ago
ProprietaryCommercial use: conditionalMultimodalVision

Reve 2.0 is available now for vision; evaluate it while provider pricing coverage matures.

Reve releases · 2 in the last 12 monthsChangelog →
Specifications
Released
2026-06-03
Specialization
image-generation
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Created by
Reve

Creative AI image generation.

Palo Alto, CA, USA
Website
Pricing

No tracked provider pricing is available yet.

Links
Website

About

Reve 2.0 by Reve AI is a native 4K text-to-image model that separates planning from rendering with a code-based intermediate layout representation. It generates precise layout structures before rendering final images, enabling lossless iterative editing, exact typography control, and agent-native manipulation. Reve says the model has 3x more parameters than Reve Image 1.0, and it debuted near the top of the Text-to-Image Arena at launch. Available at app.reve.com; no third-party API was confirmed at launch.

Providers

No active provider routes are tracked for this model yet.

Capabilities

VisionMultimodal

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.