Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Adobe / Adobe Firefly

Firefly Image 5

Image generation and instruction-based edits, with native resolutions up to 4MP and an optional prompt reasoner.

Image generation
availableClosed weightsImage generationImage editing
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
13 of 25 specification fields collected
Output resolution1MP, 2.4MP (default), 4MPSee specification notes below
Reference imagesOne reference image per API requestSee specification notes below
Input billingSee billing notesAdobe Firefly web app
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
Maximum output
Not collected
Input modalities
Text, ImageSource for Input modalities (opens in a new tab)
Output modalities
Image, TextSource for Output modalities (opens in a new tab)

Optional altText is an image description, not a general-purpose language-model endpoint.

Reasoning
SupportedSource for Reasoning (opens in a new tab)

Prompt processing strategy only, not general-purpose reasoning or an exposed chain of thought.

Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
2025-10-28Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Maximum prompt characters
1,500 charactersSource for Maximum prompt characters (opens in a new tab)
Reference images
One reference image per API requestSource for Reference images (opens in a new tab)

The narrative guide says one or more, but the OpenAPI schema explicitly limits maxItems to 1.

Output resolutions
1MP, 2.4MP (default), 4MPSource for Output resolutions (opens in a new tab)
Aspect ratios
1:1, 4:3, 3:4, 16:9, 9:16, autoSource for Aspect ratios (opens in a new tab)
Outputs per generation
One image per requestSource for Outputs per generation (opens in a new tab)
Reasoning controls
prompt_reasoner: speed (default) or quality; quality includes altText.Source for Reasoning controls (opens in a new tab)
Image and motion controls
Empty referenceBlobs generates an image; one reference triggers instruction editing. With a reference, aspectRatio must be auto or omitted.Source for Image and motion controls (opens in a new tab)
Published price
10 credits / generation (one image)Source for Published price (opens in a new tab)

Adobe app generative credits, not USD or an API quote. Do not convert credits to dollars without the exact eligible plan.

Usage metering
Firefly web app credits; API pricing not establishedSource for Usage metering (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.

Adobe Firefly web app

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

No pinned public API model selector established for this surface.

Access
Adobe account and eligible app/plan required. App credits are separate from Firefly Services API billing.
Regions
Availability and residency terms depend on the contracted service and region.

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.

Adobe Firefly Services API

Provider source (opens in a new tab)
API model ID
image5

Model version supplied in the x-model-version header, not an OpenAI-style model field.

Access
Firefly Services credentials, Adobe IMS bearer token and x-api-key. Availability and commercial terms depend on the account.
Regions
Availability and residency terms depend on the contracted service and region.
API endpoint URL
https://firefly-api.adobe.io/v4/images/generate-asyncSource for API endpoint URL (opens in a new tab)
Request mode
Asynchronous job submission and status pollingSource for Request mode (opens in a new tab)
Request limits
Default organization limits: 4 requests/minute and 9,000 requests/day; higher limits require an account-manager arrangement.Source for Request limits (opens in a new tab)
Application selector
modelId: firefly_image in the body; x-model-version: image5 in the headerSource for Application selector (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.

Adobe Firefly web app

Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

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

Adobe Firefly Services API

image5
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

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

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

Inference from Adobe’s native-model announcement and managed product/API documentation: no downloadable weights or open-weight license for this exact identity were established. Partner models have separate developers. Public Adobe research code is not proof that Firefly production weights are public.

Classification evidence (opens in a new tab)

Lifecycle dates

Public beta launched28 Oct 2025Source (opens in a new tab)

Sources reviewed