Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Reve / Reve Image

Reve Image 1.5

Historical text-to-image release using native pixel-space generation for 4K images.

Image generation
retiredClosed weightsImage generation
Official documentation (opens in a new tab)Reviewed 15 Oct 2026
6 of 20 specification fields collected
Output resolution4KSee specification notes below
Output formatsNot collectedAwaiting source review
Input billingNot collectedReve web (historical)
Output billingNot collectedNo inferred price

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Maximum input tokens
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Maximum output
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Maximum prompt characters
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Reasoning
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Tool calling
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Structured output
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Streaming
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Batch processing
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Fine-tuning
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Context caching
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Knowledge cutoff
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Release date
2026-02-23Source for Release date (opens in a new tab)
Parameters
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Architecture
Native pixel-space generation rather than a latent autoencoder, as described by the provider.Source for Architecture (opens in a new tab)
Languages
Not collected

Not established for this exact historical model. Image-generation capabilities do not establish a general language-model token budget or API contract.

Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
ImageSource for Output modalities (opens in a new tab)
Endpoint availability
Historical model. Reve stopped new image and video creation after September 27, 2026; existing assets remain downloadable until October 31, 2026.Source for Endpoint availability (opens in a new tab)

This is a service-wide creation cutoff, not a verified per-version API shutdown date.

Output resolutions
4KSource for Output resolutions (opens in a new tab)

No exact aspect-ratio matrix or byte ceiling is provided in the launch post.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Reve web (historical)

Provider source (opens in a new tab)
API model ID
Not collected

Exact historical model selector was not recovered; do not invent an ID from a product name.

Access
Retired early-release text-to-image web model.
Regions
Historical deployment regions not established
Endpoint availability
Historical access only; no current generation verified. The September 27 service-wide cutoff is distinct from the unverified exact API shutdown date.Source for Endpoint availability (opens in a new tab)
API endpoint URL
Not collected

Historical path and authentication contract not recovered from an accessible first-party schema.

Request quotas
Not collected

Exact historical request and concurrency quotas not established.

Endpoint pricing has not been collected. Check the provider for applicable rates.

Data & enterprise terms

Historical service terms retain model rights and provide a paid-account training opt-out. A distinct API data-processing contract was not recovered.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Reve web (historical)

Not verified

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

How it works
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

Minimum reusable input
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

Lifetime & refresh
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

How to enable it
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

Usage fields
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

Billing rules
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

Limits & data boundaries
Not collected

No reviewed prompt-cache contract or cache tariff. Layout reuse is not evidence of a billed prompt cache.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 15 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Private hosted-model classification is inferred from the provider identifying its own trained image models and reserving model rights under service terms. No matching weight release was established in this review. The layout research discloses continued training of open Qwen models; those upstream weights do not establish public availability of Reve derivatives or its renderer. Exact checkpoint provenance remains incomplete.

Classification evidence (opens in a new tab)

Lifecycle dates

Official model announcement23 Feb 2026Source (opens in a new tab)
Reve 2.0 replaces earlier models in the first-party app; historical API host timing is separate3 Jun 2026Source (opens in a new tab)
Reve service-wide creation cutoff; downloads only afterward27 Sept 2026Source (opens in a new tab)

Sources reviewed