Skip to main content
Quiver logo

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 key
1

Step 1

Go to https://quiver.ai and sign up or log in
2

Step 2

Open your account dashboard and navigate to API keys
3

Step 3

Create a new API key or copy your existing one
4

Step 4

Paste the API key below

Required Credentials

Available Actions

Parameters

string
required
A text description of the desired SVG
string
The model to use for SVG generation (e.g. “arrow-1.1”) (Default: arrow-1.1)
string
Style or formatting guidance for the SVG output
array
Reference image URLs to guide SVG generation (up to 4 for arrow-1.1, 16 for arrow-1.1-max)
integer
Number of SVGs to generate (1-16, default 1)
number
Sampling temperature (0-2, default 1)
number
Nucleus sampling probability (0-1, default 1)
integer
Maximum output tokens (1-65536)
number
Token penalty for prior output (-2 to 2, default 0)

Response

Parameters

string
required
URL of the raster image to vectorize into SVG
string
The model to use for vectorization (e.g. “arrow-1.1”) (Default: arrow-1.1)
boolean
Automatically crop the image to its dominant subject
integer
Square resize target in pixels (128-4096)
number
Sampling temperature (0-2, default 1)
number
Nucleus sampling probability (0-1, default 1)
integer
Maximum output tokens (1-65536)
number
Token penalty for prior output (-2 to 2, default 0)

Response

Response

Limits & Quotas

  • Models: arrow-1.1 is the default; arrow-1.1-max offers higher fidelity for detailed images and supports more reference images.
  • Generation: n of 1-16 outputs per request; temperature 0-2, top_p 0-1, presence_penalty -2 to 2, max_output_tokens up to 65536.
  • Vectorization: decoded images cannot exceed 4096 x 4096 px; target_size accepts 128-4096 px.
  • Billing: each request reports a credits debit; usage token fields are retained for compatibility and may be zeroed.
  • Error model: non-2xx responses and timeouts are caught and returned as success=False + error rather than raising. Plan for retries on the agent side based on the error string.

Amazon Alexa

Browser Use

ElevenLabs