Skip to main content
Forma AI adds model-backed media understanding and generative image work to your pipeline. Every plan includes a monthly Forma AI unit allowance (Free: 200, Starter: 3,000, Pro: 12,000, Business: 50,000). Free and Starter hard-cap at the included quota; Pro and Business can continue with overage billing when enabled in Usage settings. You do not bring model keys or manage AI vendors. Your app calls Convertly, Convertly runs the AI operation, and usage is billed through your Convertly plan. There are two endpoint families:

Analysis — /api/ai/tools

Returns structured JSON describing the input image.
Analysis calls cost between 2 and ~10 AI units depending on the image size, so most Pro accounts run hundreds of analyses inside their monthly quota.

Image transforms — /api/ai/transform

Generative endpoints return a new image. The output is persisted to your Convertly storage automatically and returned as a file record with a signed download URL. image.generate is the only operation that does not require a source image — the model produces an image purely from the prompt. Pair it with aspectRatio to control the canvas shape, for example a 16:9 hero image or a 9:16 story.

Examples

Edit an image already in the user’s library:
Generate from a text prompt with no source image:
Queue a long-running job instead of waiting for the response:

Costs

At the default 1K output size, generative image operations use 100 units plus 1 unit per MB of source and reference images. A 4 MB edit therefore uses 104 units. The base is 150 units at 2K and 225 units at 4K. Standard studio upscaling is free; generative edits, outpainting, object removal, background replacement, and style transfer use the Forma AI pool. Monthly allowances, hard caps, and overage rates are in Limits.

Generative fill (in-app)

Convertly’s editor at /app/editor/<id> exposes an Expand tool that surfaces the generative-fill capability directly. Drag the canvas handles outward to add space on any side, optionally write a guidance prompt, and click Generative fill with Forma AI. The editor composites the current preview onto a larger transparent canvas in the browser, then sends that composite to /api/ai/transform with operation=image.outpaint. Forma AI fills the transparent regions with content that continues the existing scene. The result lands as a temporary step in the edit stack; it is written to the library only when the user chooses Save or Save as copy. The same outcome can be reproduced server-side by submitting a multipart file already padded with transparent pixels to operation=image.outpaint — the behaviour is identical.

Background-removal previews

The Remove BG quick action in the file lightbox runs managed ML subject segmentation. It automatically chooses a small, medium, or large cutout model from the image complexity. The preview uses 5 Forma AI units plus 1 unit per MB of source image; saving an accepted preview does not charge those units again. If the source already contains a meaningful transparent cutout, Convertly preserves it and uses 0 Forma AI units. The standalone POST /api/media/remove-background Media Tools endpoint is metered as a Media API operation instead. It uses the same managed segmentation service but does not consume the Forma AI pool.

Quotas

AI endpoints use X-Convertly-AI-* response headers, shared between the analysis and transform routes: Free and Starter plans receive a 402 when the monthly Forma AI quota is exhausted (no overage). Pro and Business accounts can continue past the included quota when overage billing is enabled. Enterprise plans use the same surface with larger allowances. See Limits for included units per plan.

MCP for agents

The Convertly MCP server (@convertly-sh/mcp) exposes Forma AI to Claude, Cursor, and other MCP clients: Useful when the connected model cannot generate images natively: the agent calls Convertly with your API key and Forma AI units. See MCP for AI agents.

Forma AI runtime

Forma AI is a managed Convertly service. The underlying model runtime may change by operation, region, cost, latency, or quality target, but the public API response shapes remain stable. All calls are authenticated and billed through your Convertly API key — there is nothing to configure on your side.
Last modified on July 31, 2026