API action
Last updated on
Nov 11, 2025
Applies to enterprise.
This page describes the capabilities of the Firefly Services API and how operations are defined for each.
Firefly Services
Firefly APIs*
| API action | Capability | Condition | Operation definition |
|---|---|---|---|
| Generate Image | Generate images based on a text prompt | 1 Operation = 1 image generated from Firefly foundational model or custom models | |
| Fill Image | Fill the masked area of an image with an optional prompt | 1 Operation = 1 image generated with the foundation Firefly model | |
| Expand Image | Expand an image to a new size/aspect ratio | 1 Operation = 1 image generated with the foundation Firefly model | |
| Generate Similar Images | Generate similar Images based on the reference image | 1 Operation = 1 image generated with the foundation Firefly model | |
| Generate Object Composite | Upload an image (with or without mask), such as a product photo, and utilize a text prompt to generate a seamlessly composited scene featuring the product | 1 Operation = 1 image generated with the foundation Firefly model | |
| Generate Video | Generate photorealistic or animated video clips from a text prompt, reference images, or a combination of the two. | Video Model 1, 540p resolution | 0.4 Operations = 1 second of generated video |
| Video Model 1, 720p resolution | 1 Operation = 1 second of generated video | ||
| Video Model 1, 1080p resolution | 2 Operations = 1 second of generated video |
* Firefly APIs include parameters that allow for multiple images to be generated with each API call.
Photoshop APIs
|
|
Capability |
Operation definition |
|---|---|---|
|
Remove Background |
Isolate subject of interest in an image and remove background |
1 Operation = 1 API call |
|
Create Mask |
Isolate a subject of interest in an image (people, objects, etc) and generate an image mask |
1 Operation = 1 API call |
|
Create Renditions |
Create flat image representations of a PSD |
1 Operation = 1 API call |
|
Create actionJSON |
Convert .atn file to an actionJSON format |
1 Operation = 1 API call |
|
Execute actionJSON |
Execute a Photoshop Action with actionJSON format |
1 Operation = 1 API call |
|
Execute Photoshop Actions |
Executes Photoshop Action file against a PSD, JPEG, PNG, or TIFF |
1 Operation = 1 API call |
|
Replace Smart Object |
Replace Smart Object in a PSD |
1 Operation = 1 API call |
|
Product Crop |
Smart crop an image keeping the subject of interest in view |
1 Operation = 1 API call |
|
Depth Blur |
Apply depth blur to an image input |
1 Operation = 1 API call |
|
Edit Text Layer |
Change the contents of a text layer in a PSD, e.g. for localization |
1 Operation = 1 API call |
|
Apply PSD Edits |
Apply basic layer edits (name, state, etc), add/edit adjustment, pixel, and shape layers |
1 Operation = 1 API call |
|
Create New PSD |
Create new PSD with layers |
1 Operation = 1 API call |
|
Create an Artboard |
Create artboards from multiple PSD inputs |
1 Operation = 1 API call |
|
Get Manifest |
Extract metadata from PSD document, including general file and layer information |
1 Operation = 1 API call |
|
Refine Mask |
Improve the edges and precision of a mask |
1 Operation = 1 API call |
|
Fill Mask Area |
Fill in a masked area to complete an image |
1 Operation = 1 API call |
|
Mask Body Features |
Create a labeled mask for each body part of a person in an image |
1 Operation = 1 API call |
|
Mask All Objects |
Create a labeled mask for each object in an image |
1 Operation = 1 API call |
Lightroom APIs
|
API action |
Capability |
Operation definition |
|---|---|---|
|
Straighten Image |
Auto-straighten an image |
1 Operation = 1 API call |
|
Auto Tone |
Apply autotone to an image |
1 Operation = 1 API call |
|
Edit Image |
Adjust Lr adjustments to a photo, including exposure, contrast, detail, etc. |
1 Operation = 1 API call |
|
Apply Preset |
Apply Lr preset to a photo |
1 Operation = 1 API call |
|
Apply XMP |
Add XMP metadata to a photo |
1 Operation = 1 API call |
InDesign APIs
|
API action |
Capability |
Operation definition |
|---|---|---|
|
Data Merge |
Generate multiple asset variations by utilizing variable fields from an InDesign-tagged document and a CSV file |
1 Operation = 1 output page |
|
Rendition |
Create JPEG, PNG, or PDF from the InDesign document |
1 Operation = 1 output page |
|
Custom Scripts |
Create and execute custom scripts using InDesign features |
1 Operation = 1 output* or input page, whichever is higher *Output includes any files saved through Save, Save As, or Save A Copy, and any files created through Export. |
|
List Custom Scripts |
List all custom scripts registered by the user |
No charge |
|
Get Custom Script details |
Fetch details of a specific custom script registered by the user |
No charge |
|
Delete Custom Script |
Delete specific custom script registered by the user |
No charge |
|
Remap Links |
Replace local asset links with Experience Manager Assets Links in the InDesign file |
No charge |
|
Document Info |
Fetch information about the InDesign document like spreads, pages, links, fonts, page Items, layers etc. |
1 Operation = 1 API call |
Video & Audio APIs
| API action | Capability | Condition | Operation definition |
|---|---|---|---|
| Reframe Video V1 | Identify actions in a video and reframe the clip for different aspect ratios | <= 30 FPS | 1 Operation = 1 minute of output video |
| > 30 and <= 60 FPS | 2 Operation = 1 minute of output video | ||
| > 60 FPS | 4 Operation = 1 minute of output video | ||
Reframe Video V2 |
Reframes videos into different aspect ratios. Supports Semantic Subject Lock, which leverages plain text input to define and track key subjects across scenes |
<= 30 FPS (with Semantic Subject Lock) |
1 Operation = 1 minute of output video |
> 30 and <= 60 FPS (with Semantic Subject Lock) |
2 Operations = 1 minute of output video |
||
> 60 FPS (with Semantic Subject Lock) |
4 Operations = 1 minute of output video |
||
<= 30 FPS (without Semantic Subject Lock) |
1 Operation = 1 minute of output video |
||
> 30 and <= 60 FPS (without Semantic Subject Lock) |
2 Operations = 1 minute of output video |
||
> 60 FPS (without Semantic Subject Lock) |
4 Operations = 1 minute of output video |
||
Text to Speech |
Transform written text into spoken speech, allowing businesses to create dynamic audio |
|
0.25 Operation = 1 minute of output video |
Text to Avatar |
Convert text scripts into videos featuring lifelike human avatars with a variety of pre-shot avatar selections and natural-sounding voices |
|
0.5 Operation = 1 second of output video |
Video & Audio APIs, Add-On
| API action | Capability | Condition | Operation definition |
|---|---|---|---|
| Transcribe | Generate transcripts and captions for audio and video content in the original or translated language | 1 Operation = 10 mins of input video or audio | |
| Dub | Automate audio and video voice translation with optional lip-syncing, producing high-quality dubbing output regardless of background noise and music | Without Lipsync | 1 Operation = 10 seconds of output video or audio |
| Without Lipsync | 1 Operation = 5 seconds of output video |
Content tagging APIs
|
API action |
Capability |
Operation definition |
|---|---|---|
|
Color Tagging |
Given an image, can compute a histogram of pixel colors and sort them by dominant colors into buckets |
1 Operation = 1 API call per asset |
|
Keyword Tagging |
Given a text document, the keyword tagging service automatically extracts keywords or key phrases that best describe the subject of the document |
1 Operation = 1 API call per asset |
|
OCR |
Given an image, can indicate if text is present in the image. If text is present, OCR can return the text |
1 Operation = 1 API call per asset |
Substance 3D APIs
| API action | Capability | Condition | Operation definition |
|---|---|---|---|
| Generate 3D Object Composite* | Seamlessly composite 3D objects into Firefly-generated 2D scenes to create pixel-perfect fidelity compositions, with photorealistic lighting, shadows, and textures | Firefly Image Model 4: Less than or equal to 2000 pixels on the longest side | 2 Operations = 1 output image (or variant) |
Firefly Image Model 4: Greater than 2000 pixels on the longest side |
3 Operations = 1 output image (or variant) |
||
Firefly Image Model 4 Ultra: Less than or equal to 2000 pixels on the longest side |
3 Operations = 1 output image (or variant) |
||
Firefly Image Model 4 Ultra: Greater than 2000 pixels on the longest side |
4 Operations = 1 output image (or variant) |
||
| Render 3D Object* | Render pixel-perfect product pack shots at scale by automating the creation of photorealistic pack shots with precise lighting, shadows, and reflections | Less than or equal to 2000 pixels on the longest side | 1 Operation = 1 output image |
Greater than 2000 pixels on the longest side |
2 Operations = 1 output image |
||
| Convert 3D Files API | Convert existing 3D content in formats such as FBX and OBJ into more universal file formats like gITF and USD | 1 Operation = 1 output file | |
| Create 3D Scene API | Merge multiple 3D assets into a cohesive and detailed scene designed to host a digital twin | 1 Operation = 1 output file | |
| Describe 3D Scene API | Generate detailed statistics about 3D scene content | No charge |
*Generate 3D Object Composite API and Render 3D Object API include parameters that allow for multiple images to be generated with each API call.
Credit Conversions
| API Operation | Generative Credit |
|---|---|
| 1 API Operation | 100 Generative Credits* |
* Fractional conversions apply; credits are converted proportionally and not rounded up to a whole operation.
View the Generative credit pool article to learn more about the credit conversion related to generative credit pooling for organizations.
