Output resolution2K native and 4K upscaled in Krea.See specification notes below
Reference imagesUp to eight references in Krea web.See specification notes below
Input billingSee billing notesKrea web
Output billingSee billing notesAccess and billing notes below
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 model or hosted pipeline.
Maximum input tokens
Not collected
Not established for this exact model or hosted pipeline.
Maximum output
Not collected
Not established for this exact model or hosted pipeline.
Reasoning
Not collected
Not established for this exact model or hosted pipeline.
Tool calling
Not collected
Not established for this exact model or hosted pipeline.
Structured output
Not collected
Not established for this exact model or hosted pipeline.
Streaming
Not collected
Not established for this exact model or hosted pipeline.
Batch processing
Not collected
Not established for this exact model or hosted pipeline.
Fine-tuning
Not collected
Not established for this exact model or hosted pipeline.
Knowledge cutoff
Not collected
Not established for this exact model or hosted pipeline.
Release date
Not collected
Not established for this exact model or hosted pipeline.
Parameters
Not collected
Not established for this exact model or hosted pipeline.
Architecture
Provider describes region-aware editing that identifies and renders the changed region. Full architecture and parameter count are not established.Source for Architecture (opens in a new tab)
Languages
Not collected
Not established for this exact model or hosted pipeline.
Context caching
Not collected
Not established for this exact model or hosted pipeline.
Fal uses a separately documented total-pixel ceiling; see endpoint details.
Published price
Krea advertises USD 0.06 per 2K edit as a launch list price. Exact configuration and billing contract require confirmation; Fal early-access pricing is provided separately.Source for Published price (opens in a new tab)
Access & pricing
Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.
Krea advertises USD 0.06 per 2K edit as a launch list price. Exact configuration and billing contract require confirmation; Fal early-access pricing is provided separately.Source for Published price (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
General service terms provide broad content-use licenses and make submission visibility depend on plan settings. Exact API retention, residency and a no-training commitment have not been established; enterprise terms may differ.
Exact model selector not established for this access path.
Access
Documented web or hosted access; account entitlement and successful inference not tested.
Regions
Not established
Availability
Official model page advertises Krea API access, but no Krea 3 route is present in the reviewed OpenAPI snapshot. Exact native selector remains unverified.Source for Availability (opens in a new tab)
Published price
Krea advertises USD 0.06 per 2K edit as a launch list price. Exact configuration and billing contract require confirmation; Fal early-access pricing is provided separately.Source for Published price (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
General service terms provide broad content-use licenses and make submission visibility depend on plan settings. Exact API retention, residency and a no-training commitment have not been established; enterprise terms may differ.
Model guide specifies custom dimensions 256–3200 px. Shared ImageSize schema allows positive integers up to 14142, but the model-specific pixel cap still applies. Follow the model guide until this range conflict is reconciled.Source for Configuration discrepancy (opens in a new tab)
Shared schema and guide are both retained as evidence.
Prompt expansion
Default disabled. When enabled, Krea expands the prompt and chooses the output aspect ratio. Without expansion, unspecified image_size defaults to 2048×2048.Source for Prompt expansion (opens in a new tab)
Model guide specifies custom dimensions 256–3200 px. Shared ImageSize schema allows positive integers up to 14142, but the model-specific pixel cap still applies. Follow the model guide until this range conflict is reconciled.Source for Configuration discrepancy (opens in a new tab)
Shared schema and guide are both retained as evidence.
Prompt expansion
Default disabled. When enabled, Krea expands the prompt and chooses the output aspect ratio. Without expansion, unspecified image_size defaults to 2048×2048.Source for Prompt expansion (opens in a new tab)
Endpoint pricing has not been collected. Check the provider for applicable rates.
Data & enterprise terms
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
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.
Krea web
Not verified
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How it works
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Minimum reusable input
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Lifetime & refresh
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How to enable it
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Usage fields
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Billing rules
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Limits & data boundaries
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
Krea API
Not verified
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How it works
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Minimum reusable input
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Lifetime & refresh
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How to enable it
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Usage fields
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Billing rules
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Limits & data boundaries
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
fal.ai
fal-ai/krea-3
Not verified
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How it works
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Minimum reusable input
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Lifetime & refresh
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How to enable it
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Usage fields
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Billing rules
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Limits & data boundaries
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 15 Oct 2026
fal.ai
fal-ai/krea-3/text-to-image
Not verified
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How it works
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Minimum reusable input
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Lifetime & refresh
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
How to enable it
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Usage fields
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Billing rules
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
Limits & data boundaries
Not collected
No model-specific inference-cache mechanism, TTL or discount established. Reusable styles, moodboards and job records are not prompt caches.
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
Krea identifies Krea 3 as its new editing model rather than a distilled copy of a larger model. Hosted access is documented; no downloadable Krea 3 checkpoint or open-weight license is established in the reviewed primary sources. Closed-weight classification is an evidence-based inference.
