Skip to main content
POST
/
v1
/
svgs
/
generations
curl --request POST \
  --url https://api.quiver.ai/v1/svgs/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "instructions": "Use a flat monochrome style with rounded corners and clean geometry.",
  "max_output_tokens": 4096,
  "model": "arrow-1.1",
  "n": 2,
  "presence_penalty": 0.2,
  "prompt": "Generate a minimalist unicorn icon for a SaaS dashboard",
  "stream": false,
  "temperature": 0.4,
  "top_p": 0.95
}
'
{
  "created": 1704067200,
  "data": [
    {
      "svg": "<svg xmlns=\"http://www.w3.org/2000/svg\" viewBox=\"0 0 24 24\"><path d=\"M12 2l8 20H4z\"/></svg>"
    }
  ],
  "id": "resp_01J9AZ3XJ7D5S9ZV2Q5Z8E1A4N",
  "credits": 1,
  "usage": {
    "input_tokens": 0,
    "output_tokens": 0,
    "total_tokens": 0
  }
}

Documentation Index

Fetch the complete documentation index at: https://docs.quiver.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Authentication via Bearer token API key

Body

application/json
​
model
string
required

Model identifier to use for generation or vectorization.

Minimum string length: 1
Example:

"arrow-1.1"

​
prompt
string
required

Primary text prompt that describes the desired SVG.

Minimum string length: 1
Example:

"Generate an icon of a unicorn"

​
attributes
object

Optional SVG root attributes requested by the caller.

​
max_output_tokens
integer

Upper bound for output token count.

Required range: 1 <= x <= 131072
Example:

4096

​
presence_penalty
number | null
default:0

Penalty for tokens already present in prior output.

Required range: -2 <= x <= 2
Example:

0.2

​
stream
boolean
default:false

When true, emits a Server-Sent Events stream.

Example:

false

​
temperature
number
default:1

Sampling temperature.

Required range: 0 <= x <= 2
Example:

0.4

​
top_p
number
default:1

Nucleus sampling probability.

Required range: 0 <= x <= 1
Example:

0.95

​
instructions
string

Additional style or formatting guidance.

Minimum string length: 1
Example:

"Use a flat monochrome style with clean geometry."

​
n
integer
default:1

Number of outputs to generate.

Required range: 1 <= x <= 16
Example:

1

​
references
object · object · string<uri>[]

Optional reference images to guide style/composition. Accepts { url }, { base64 }, or URL string shorthand. Runtime limits are model-specific: 4 for Arrow 1.1/Arrow 1.x aliases, 16 for Arrow 1.1 Max.

Maximum array length: 16

Response

When stream is false, returns application/json with the full SVG response. When stream is true, returns text/event-stream with Server-Sent Events. Each SSE message contains an event: line (generating, reasoning, draft, or content) and a data: line with a JSON payload. For n > 1, events are interleaved across outputs, each output keeps a stable data.id, and data.index indicates the output position. usage token fields are deprecated and set to 0; use credits for billing values. For streaming, credits is emitted on completed content events. The stream terminates with data: [DONE].

​
created
integer
required
Required range: x >= 0
Example:

1704067200

​
data
object[]
required
Minimum array length: 1
​
id
string
required
Minimum string length: 1
Example:

"resp_01J9AZ3XJ7D5S9ZV2Q5Z8E1A4N"

​
credits
integer

Credit cost for this request. Use this for billing instead of usage tokens.

Required range: x >= 0
Example:

1

​
usage
object
deprecated

Deprecated. Use credits for billing values.