Bria Product Shot API pricing: $0.0575 per image

TL;DR

• Bria Product Shot: Upload a product photo and choose an English scene description or a scene reference image.
• Each image costs $0.0575, with one PNG per request. View budget calculations
• Budget $5.75 for 100 images. Check the edit on one set of inputs before scheduling a batch.

What does one image cost?

Bria Product Shot costs $0.0575 per output image on HiAPI. Each request returns one result, so multiply the number of planned outputs by the unit price. Price checked on October 28, 2026.

Model	Per image	100 images	1,000 images
bria-product-shot	$0.0575	$5.75	$57.50

Text scenes and reference-image scenes use the same unit price. Both fast settings cost the same; placement and original_quality control composition and size without creating separate price tiers.

How much should you budget each month?

Planned outputs	Calculation	Image charges
100 images	100 × $0.0575	$5.75
1,000 images	1,000 × $0.0575	$57.50
10,000 images	10,000 × $0.0575	$575.00

Count every generated candidate when planning a budget, rather than counting only the images you eventually use. For example, three candidate images for each of 100 products means 300 outputs and $17.25 in image charges. The table covers the generation charges for those images.

What should you check before submitting?

Choose either an English prompt or reference_image_url. With a scene reference, omit optimize_description entirely; sending it as false is still not allowed.

Use manual_placement for a preset position. To retain the original placement, select original and omit manual_placement_selection. original_quality is available only with original. Keep the product image and placement fixed while adjusting a scene so that each change has a clear purpose.

A source image and its result

Skincare: a countertop by a window

Open this scene description in the model page; also upload the product image and choose placement.

Open this scene description in the model page; also upload the product image and choose placement.

The source shows a dropper bottle against a pale background. In the result, the bottle sits low in the frame, with a window frame, green leaves and a veined pale surface around it.

On a white marble countertop beside a window, soft morning light, a few green leaves in the background

The description specifies the surface, light and background objects. bottom_center controls placement; you still need to upload the product image.

bria-product-shot returns one image per request at $0.0575 per image.

Cleanup or a new product scene?

Task	HiAPI model	Per image
Erase a selected object with a mask	bria-eraser	$0.0575
Create a product scene from text or a reference	bria-product-shot	$0.0575

The models solve different tasks. Eraser needs a source image and mask. Product Shot needs a product photo plus a text scene or reference image. Start with your inputs and desired edit, then estimate the number of outputs.

Convert a product count into a budget

Separate products, scene directions and candidate attempts. A product that needs both a window-side countertop and a bedroom setting needs outputs for each direction. Even if you eventually select one image, both directions use the budget. A request returns one PNG, so a product is not automatically equivalent to one generation.

The example of 100 products with three candidates each, totaling $17.25, is a planning scenario. It neither guarantees that those candidates suit the job nor requires every product to receive the same number. Establish a scene direction with a representative product before allocating more candidates, rather than discovering after a batch that the surface, lighting or placement was wrong.

Track scene exploration separately from batch use. During exploration, keep the product image fixed and adjust the scene or placement deliberately. Once a direction works for the intended use, apply it to other products and inspect each result. Do not assume a common acceptance rate in advance. Record actual outputs and accepted images separately to inform later budgets.

How should you choose settings at the same price?

fast=true and fast=false have the same rate. Their names do not establish a specific time saving, and there is no basis here for promising more accurate product detail in either mode. For a comparison, hold the product image, scene input and placement constant, change the mode alone and judge the results you receive.

optimize_description expands text scenes and defaults to true in text mode. Reference mode must omit the field entirely, including false. placement_type chooses a preset position or the original placement. original_quality applies only with original: true keeps the input dimensions and false scales to about one megapixel. Keeping dimensions is a file requirement, not a price upgrade or a detail-quality guarantee.

The current image rate lists no additional tier for these valid combinations. Keep the parameters your intended use requires. Do not combine original placement with a position preset. First make the request express the scene and composition you need, then estimate the output count.

What work sits outside the image charges?

The estimate covers image generation. Allow separately for preparing a clear product photo, choosing references, reviewing brand details, storing downloads and retouching. A result with the right background but unsuitable product proportions or markings is still a generated candidate. Planning around only the final accepted images misses those outputs.

The published unit rate does not establish the billing treatment of failed or canceled tasks or interrupted connections. Review the task state and actual account charges in those cases. A client timeout does not establish generation failure; check an existing taskId before submitting another task.

How should you choose product photos and scene directions?

Choose a clear product with complete edges and decide whether delivery requires its original placement. Use original to retain the source composition, or manual_placement for a preset position. A longer scene description should not be relied on to repair a missing bottle opening, cup rim or headphone edge in the source.

Text mode is a useful starting point when you can describe the supporting surface, light and background objects in English. Choose reference mode when you already have a visual direction, then check the relative position of the product and reference objects. The headphone example carries over warm colors and leaf elements, but places the headphones in front of the pedestal. It does not promise precise placement on a particular surface in a reference.

When is another candidate worthwhile?

Define the use before comparing candidates. For a product image, check the complete silhouette, scale and contact with the supporting surface. For a layout with copy, also check the available empty space. A busier background may not suit the job. Record a specific reason for accepting or rejecting a candidate.

If candidates repeatedly have the same placement problem, revisit the placement setting and source composition. If the scene direction is wrong, revise the description or reference. Allocate more candidates once the inputs express the intended direction and you need to compare results. Record the product image, scene input and parameters for each change so different configurations are not mistaken for the same plan.

FAQ

How many images does one request return?

One image, priced at $0.0575.

How much do 100 images cost?

100 × $0.0575 = $5.75; 1,000 images cost $57.50.

How should I budget for multiple candidates?

Count every candidate output. Three candidates for each of 100 products means 300 images and a $17.25 budget.

Where can I start?

Open the Bria Product Shot model page and upload a product image, then choose an English scene description or a reference image.

Related guides

API integration guide · Examples and input preparation

Open the model page and upload your input image.