Imagineart 2.0 Preview API Reference

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to imagineart/imagineart-2.0-preview/text-to-image.

Default: imagineart/imagineart-2.0-preview/text-to-image

stringpromptrequired

Text prompt describing the desired image

Optional<string>aspect_ratio

The aspect ratio of the generated image.

Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16

Optional<string>resolution

Output resolution: '1K' targets ~1024px and will be faster. '2K' targets ~2048px image size and will be slower but with higher quality.

Allowed values: 1K, 2K

Default: 2K

Optional<integer>seed

Default is random (0 and -1 are treated as random)

Optional<string>reasoning

Visual Understanding Level: low (default) or high. High reasoning takes more time but generates better images.

Allowed values: high, low

Default: low

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

Allowed values: pending, running, completed, failed, timeout

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: text-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request curl -X POST https://api.sandbase.ai/v1/run \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "imagineart/imagineart-2.0-preview/text-to-image", "prompt": "Photorealistic cinematic portrait of a stressed young woman with dark skin and long brown dreadlocks styled in a messy high bun, wearing black-rimmed glasses and a peach-colored collared shirt. She is sitting at a desk, sipping coffee from a white ceramic mug held in her right hand, with a focused and slightly overwhelmed expression while looking at a silver laptop in front of her.\n\nHer face, hair, glasses, and entire upper body are completely covered with dozens of colorful sticky notes in yellow, pink, blue, orange, red, and green, many with no written text. Sticky notes are stuck to her forehead, cheeks, dreadlocks, and all over her shirt.\n\nThe scene is set in a modern office with soft cool blue-toned natural lighting coming from the side. Blurred green plants are visible in the background and \"ImagineArt\" is written on the Wall. On the desk in the foreground there is another white mug, scattered papers, and more sticky notes.\n\nHighly detailed, sharp focus on the woman, shallow depth of field, realistic skin texture, natural fabric folds, cinematic lighting, moody atmosphere capturing information overload and multitasking, 8k resolution, photorealistic.", "aspect_ratio": "21:9" }' # 2. If the response is still running, poll the returned id curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \ -H "Authorization: Bearer $SANDBASE_API_KEY"