Overview
Add Quiver to any ModuleX agent or workflow. AI-powered SVG generation and raster vectorization against the QuiverAI REST API (api.quiver.ai/v1). Generate clean, scalable vector graphics from text prompts or convert raster images into editable SVGs.
Categories: AI & Machine Learning · Image Generation · Design · Auth: API Key · Actions: 3
Authentication
API Key Authentication
Authenticate using your QuiverAI API keyStep 1
Go to https://quiver.ai and sign up or log in
Required Credentials
| Field | Description | Required | Format |
|---|---|---|---|
| QuiverAI API Key | Your QuiverAI API key from quiver.ai | Yes | - |
Available Actions
text_to_svg — Generate SVG images from text prompts using QuiverAI.
text_to_svg — Generate SVG images from text prompts using QuiverAI.
Parameters
A text description of the desired SVG
The model to use for SVG generation (e.g. “arrow-1.1”) (Default:
arrow-1.1)Style or formatting guidance for the SVG output
Reference image URLs to guide SVG generation (up to 4 for arrow-1.1, 16 for arrow-1.1-max)
Number of SVGs to generate (1-16, default 1)
Sampling temperature (0-2, default 1)
Nucleus sampling probability (0-1, default 1)
Maximum output tokens (1-65536)
Token penalty for prior output (-2 to 2, default 0)
Response
image_to_svg — Convert raster images into vector SVG format using QuiverAI.
image_to_svg — Convert raster images into vector SVG format using QuiverAI.
Parameters
URL of the raster image to vectorize into SVG
The model to use for vectorization (e.g. “arrow-1.1”) (Default:
arrow-1.1)Automatically crop the image to its dominant subject
Square resize target in pixels (128-4096)
Sampling temperature (0-2, default 1)
Nucleus sampling probability (0-1, default 1)
Maximum output tokens (1-65536)
Token penalty for prior output (-2 to 2, default 0)
Response
list_models — List all available QuiverAI models.
list_models — List all available QuiverAI models.
Response
Limits & Quotas
- Models:
arrow-1.1is the default;arrow-1.1-maxoffers higher fidelity for detailed images and supports more reference images. - Generation:
nof 1-16 outputs per request;temperature0-2,top_p0-1,presence_penalty-2 to 2,max_output_tokensup to 65536. - Vectorization: decoded images cannot exceed 4096 x 4096 px;
target_sizeaccepts 128-4096 px. - Billing: each request reports a
creditsdebit;usagetoken fields are retained for compatibility and may be zeroed. - Error model: non-2xx responses and timeouts are caught and
returned as
success=False+errorrather than raising. Plan for retries on the agent side based on the error string.