site/docs/providers/quiverai.md
The QuiverAI provider generates SVG vector graphics from text prompts using the Arrow model. Output is raw SVG markup, which works with text-based assertions like is-xml, contains, and llm-rubric.
export QUIVERAI_API_KEY=your-api-key
quiverai:<model-name>
The default model is arrow-preview.
providers:
- id: quiverai:arrow-preview
config:
temperature: 0.7
max_output_tokens: 8192
instructions: 'flat design, minimal color palette'
With reference images:
providers:
- id: quiverai:arrow-preview
config:
references:
- url: https://example.com/style-reference.png
instructions: 'Match the style of the reference image'
| Parameter | Type | Default | Description |
|---|---|---|---|
instructions | string | — | Style guidance separate from the prompt |
references | array | — | Up to 4 reference images: [{ url }] or [{ base64 }] |
temperature | number | 1 | Randomness (0–2) |
top_p | number | 1 | Nucleus sampling (0–1) |
presence_penalty | number | 0 | Penalize repeated patterns (-2 to 2) |
max_output_tokens | integer | — | Maximum output tokens (1–131,072) |
n | integer | 1 | Number of SVGs to generate (1–16) |
stream | boolean | true | Set false to enable response caching |
apiKey | string | — | API key (overrides environment variable) |
apiBaseUrl | string | — | Custom API base URL |
When n > 1, multiple SVGs are joined with double newlines.
prompts:
- 'Create a simple SVG icon of: {{subject}}'
providers:
- id: quiverai:arrow-preview
config:
max_output_tokens: 8192
tests:
- vars:
subject: a red heart
assert:
- type: is-xml
- type: llm-rubric
value: Contains a heart shape in red color
- vars:
subject: a yellow star
assert:
- type: is-xml
- type: llm-rubric
value: Contains a star shape in yellow/gold color
:::note
llm-rubric assertions require a grading provider. By default this uses OpenAI, so set OPENAI_API_KEY or configure a different grader.
:::
| Error | Cause | Fix |
|---|---|---|
insufficient_credits | Account has no credits | Add credits at app.quiver.ai |
invalid_api_key | Key is missing or invalid | Check QUIVERAI_API_KEY is set correctly |
rate_limit_exceeded | Too many requests | Reduce --max-concurrency or add delays between requests |
model_not_found | Invalid model name | Use arrow-preview (the default) |
Error messages include a request_id for debugging with QuiverAI support.
| Variable | Description |
|---|---|
QUIVERAI_API_KEY | API key (required) |