Skip to content
FLORA FLORA API

List generation history

GET
/generations
 
import { FloraClient } from '@flora-ai/flora';


const client = new FloraClient({ apiKey: process.env['FLORA_API_KEY'] });


// Paginated lists are async iterables; further pages are fetched as needed.
for await (const generation of await client.generations.list()) {
  console.log(generation);
}

Lists generation history for the authenticated caller, including pending, running, completed, and failed generations. Results are newest first and can be filtered by workspace_id, project_id, and status. Each item includes poll_url; use it to poll pending/running generations and to fetch completed or failed run details and outputs.

Error responses use the standard error body.

Authorizations

Section titled “Authorizations ”

Parameters

Section titled “ Parameters ”

Query Parameters

Section titled “Query Parameters ”
limit

Maximum number of results to return

integer
>= 1 <= 100

Maximum number of results to return

cursor

Opaque cursor for fetching the next page

string

Opaque cursor for fetching the next page

workspace_id

Workspace identifier

string
/^ws_\S+$/

Workspace identifier

project_id

Project identifier

string
/^prj_\S+$/

Project identifier

status

Run status filter

string
Allowed values: pending running completed failed

Run status filter

include_inputs

Include each generation’s submitted inputs (prompt and input references) on the item. Off by default; the inputs block can be large.

boolean

Include each generation’s submitted inputs (prompt and input references) on the item. Off by default; the inputs block can be large.

Responses

Section titled “ Responses ”

200

Section titled “200 ”

Generation history returned.

Media type application/json
object
generations
required
Array<object>
object
run_id
required

Run identifier

string
/^run_\S+$/
status
required
string
Allowed values: pending running completed failed
progress
required
number
created_at
required
number
started_at
number
completed_at
number
error_code

Machine-readable run error code

string
error_message

Human-readable run error message

string
charged_cost

Cost charged in USD

number
outputs
Array<object>
object
output_id
required

Run output identifier

string
type
required

Run output media type

string
Allowed values: imageUrl videoUrl audioUrl text documentUrl model3dUrl
url
required

Run output URL or text content

string
>= 1 characters
asset_id

Asset identifier for durable media outputs

string
/^asset_\S+$/
label

Optional output label

string
tri_count

Triangle count for model3d outputs

integer
bbox

Axis-aligned local bounds for model3d outputs

object
min
required
array
max
required
array
textured

Whether the model3d output carries textures

boolean
poll_url

URL to poll pending/running runs or fetch completed/failed run details.

string format: uri
generation_id
required

Run identifier

string
/^run_\S+$/
workspace_id
required

Workspace identifier

string
/^ws_\S+$/
project_id
required

Project identifier

string
/^prj_\S+$/
model
object
model_id
required
Any of:

Model identifier

string
>= 1 characters
inputs

The submitted inputs this run launched with; present only when include_inputs=true

object
prompt
required

Prompt the run executed

string
raw_prompt

Prompt as originally submitted, when it differs from the executed prompt

string
elements

Canvas input elements wired into the run, as the model saw them

Array<object>
object
element_id
required

Canvas element identifier

string
element_name
required

Name of the input element

string
parent_node_id
required

Canvas node the element belongs to

string
prompt_extension
required

Text this element contributed to the prompt

string
tag
required

How the element was referenced in the prompt

string
image_ordinal

Ordinal for “image N” prompt references, counting image inputs only

number
asset_ids

Ordered reference input assets (images first, then video, audio, documents, 3D); “image N” ordinals index into the image subset

Array<string>
meta
required
object
next_cursor
required
Any of:

Opaque cursor for fetching the next page

string
total_estimate
Any of:

Estimated total matching items

integer
Example 
{
  "generations": [
    {
      "run_id": "run_abc123",
      "status": "pending",
      "error_code": "provider_error",
      "error_message": "The provider failed to complete the generation.",
      "outputs": [
        {
          "output_id": "output_1",
          "type": "imageUrl",
          "url": "https://media.flora.ai/output.png",
          "asset_id": "asset_abc123",
          "label": "preview"
        }
      ],
      "generation_id": "run_abc123",
      "workspace_id": "ws_abc123",
      "project_id": "prj_abc123",
      "model": {
        "model_id": "t2i-flux-2-pro"
      },
      "inputs": {
        "asset_ids": [
          "asset_abc123"
        ]
      }
    }
  ],
  "meta": {
    "next_cursor": "eyJvZmZzZXQiOjIwfQ"
  }
}