New260+ blocks and 240+ tools are now fully documented
DocumentationReferenceTool IntegrationsFinance & Payments
Tool

Quiver Tools

Generate and convert SVG graphics from text prompts or raster images with QuiverAI

Quiver uses QuiverAI to produce clean, scalable SVG graphics — either generated from a text prompt or vectorized from an existing raster image. Use these tools in a workflow when you need vector artwork (icons, illustrations, logos) created or converted on the fly.

Overview

PropertyValue
Providerquiver
Categorytools
AuthAPI Key (QuiverAI API key; sent as a Bearer token for model listing)

Operations

OperationTool IDDescription
Text to SVGquiver_text_to_svgGenerate SVG images from text prompts using QuiverAI
Image to SVGquiver_image_to_svgConvert raster images into vector SVG format using QuiverAI
List Modelsquiver_list_modelsList all available QuiverAI models

Configuration

quiver_text_to_svg

ParameterTypeRequiredDescription
apiKeystringYesQuiverAI API key. Secret — store as an environment variable.
promptstringYesA text description of the desired SVG.
modelstringYesThe model to use for SVG generation (e.g. arrow-preview).
instructionsstringNoStyle or formatting guidance for the SVG output.
referencesjsonNoReference images to guide SVG generation (up to 4).
nnumberNoNumber of SVGs to generate (1-16, default 1).
temperaturenumberNoSampling temperature (0-2, default 1).
top_pnumberNoNucleus sampling probability (0-1, default 1).
max_output_tokensnumberNoMaximum output tokens (1-131072).
presence_penaltynumberNoToken penalty for prior output (-2 to 2, default 0).

quiver_image_to_svg

ParameterTypeRequiredDescription
apiKeystringYesQuiverAI API key. Secret — store as an environment variable.
modelstringYesThe model to use for vectorization (e.g. arrow-preview).
imagejsonYesThe raster image to vectorize into SVG.
temperaturenumberNoSampling temperature (0-2, default 1).
top_pnumberNoNucleus sampling probability (0-1, default 1).
max_output_tokensnumberNoMaximum output tokens (1-131072).
presence_penaltynumberNoToken penalty for prior output (-2 to 2, default 0).
auto_cropbooleanNoAutomatically crop the image before vectorizing.
target_sizenumberNoSquare resize target in pixels (128-4096).

quiver_list_models

ParameterTypeRequiredDescription
apiKeystringYesQuiverAI API key. Secret — store as an environment variable. Sent as Authorization: Bearer {apiKey}.

Outputs

quiver_text_to_svg

  • success (boolean) — Whether the SVG generation succeeded.
  • output (json) — Generated SVG output, with these properties:
    • file (json) — First generated SVG file.
    • files (json) — All generated SVG files (when n > 1).
    • svgContent (string) — Raw SVG markup content of the first result.
    • id (string) — Generation request ID.
    • usage (json) — Token usage statistics: totalTokens (number), inputTokens (number), outputTokens (number).

quiver_image_to_svg

  • success (boolean) — Whether the vectorization succeeded.
  • output (json) — Vectorized SVG output, with these properties:
    • file (json) — Generated SVG file.
    • svgContent (string) — Raw SVG markup content.
    • id (string) — Vectorization request ID.
    • usage (json) — Token usage statistics: totalTokens (number), inputTokens (number), outputTokens (number).

quiver_list_models

  • success (boolean) — Whether the request succeeded.
  • output (json) — Available models, with this property:
    • models (json) — List of available QuiverAI models (each with id, name, description, created, ownedBy, inputModalities, outputModalities, contextLength, maxOutputLength, supportedOperations, supportedSamplingParameters).

YAML Example

quiver_1:
  type: quiver
  name: "Quiver"
  inputs:
    operation: "text_to_svg"
    apiKey: "{{QUIVER_API_KEY}}"
    model: "quiver-mini"
    prompt: "A minimalist mountain logo with a rising sun"
  connections:
    outgoing:
      - target: next-block-id

Tips

  • Get a QuiverAI API key and store it as an environment variable (e.g. {{QUIVER_API_KEY}}); never hardcode it. The same key works for all three operations.
  • Use Text to SVG to create new vector artwork from a description, and Image to SVG to vectorize an existing raster image. Run List Models first if you are unsure which model id to pass (block presets are quiver-mini and quiver-pro).
  • For Text to SVG, set n (1-16) to get multiple variants in one call — the extra results land in output.files, while output.file and output.svgContent always hold the first result.
  • Reference images (up to 4) help steer the style for Text to SVG; for Image to SVG, enable auto_crop and set target_size (128-4096) to control framing and resolution before vectorizing.