Skip to main content
POST
Transform reference images with a prompt (img2img)
Transform 1–14 source images with a prompt. The call returns 202 Accepted with a job id; poll GET /images/img2img/{id} for the result. Each entry in images is a source object taking exactly one of image_id, url, or base64 + mime_type; order is preserved. Requires the images.edit scope.

Example: one source per mode

Example: blend multiple sources

Pass several sources — mixing modes is allowed — and tune the engine, aspect ratio, and resolution:
Body
The 202 response is the async job handle:
202 Accepted
images holds 1–14 sources; each is exactly one of image_id, an https url, or base64 + mime_type. prompt is required. engine is nano_banana_pro (default) or nano_banana_2; an unknown engine returns 422. aspect_ratio is validated against the engine’s supported list (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9; nano_banana_2 also 4:1, 1:4, 8:1, 1:8); omitted preserves the source shape. resolution is 1K (default), 2K, or 4K. num_outputs (1–4) defaults to 1 and each output is billed. output_format is png only in v1.

Credits

Each output costs 5 credits at 1K, scaling with resolution (1K ×1, 2K ×2, 4K ×4) and multiplied by num_outputs. See Pricing.

Errors

Authorizations

Authorization
string
header
required

Organization API key as a bearer token: Authorization: Bearer samsa_sk_....

Body

application/json

POST /images/img2img body (SAM-815 / S8.3 — ADR §8, §10).

Transform 1-14 source images with a prompt (the app's Edit-tab img2img flow). Each source is exactly one of image_id (an image in your organization's context), an https url, or base64+mime_type. engine is a public-safe alias of the internal edit model (nano_banana_pro default, nano_banana_2); num_outputs defaults to 1 (the app default is 4). Each output is billed at 5 x resolution_multiplier credits (1K:1x, 2K:2x, 4K:4x).

images
PublicImageEditSource · object[]
required

1-14 source images; each exactly one of image_id, an https url, or base64+mime_type. Order is preserved.

Required array length: 1 - 14 elements
prompt
string
required

Text prompt describing the transformation. Runs the same validation as the app (rejects empty / malformed / policy-violating prompts with a 422).

Minimum string length: 1
Example:

"Combine the products into one cohesive lifestyle scene"

engine
string | null

Img2img engine — one of nano_banana_pro (default) or nano_banana_2. Omit to use the default. Unknown engines return 422.

Example:

"nano_banana_pro"

aspect_ratio
string | null

Optional aspect ratio for the generated image(s), validated against the engine's supported list (1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9; nano_banana_2 additionally 4:1, 1:4, 8:1, 1:8). Omitted = the engine preserves the source shape.

Example:

"1:1"

resolution
string
default:1K

Output resolution — 1K (default), 2K, or 4K. Credits scale 1K:1x, 2K:2x, 4K:4x per output.

Example:

"1K"

num_outputs
integer
default:1

Number of images to generate (1-4). Defaults to 1 (the app default is 4); each output is billed.

Required range: 1 <= x <= 4
Example:

1

output_format
enum<string>
default:png

Encoding of the returned images. v1 supports png only.

Available options:
png
Example:

"png"

webhook_url
string | null

Optional https webhook notified once on terminal status (signed per the webhook signature scheme; see the webhooks docs).

Example:

"https://example.com/webhooks/samsa"

Response

Successful Response

Shared 202 body for the transform-op submits (SAM-813 / S8 wave).

Every POST /images/<op> returns the async job handle {id, status, estimated_credits}. The initial status is pending (the job is queued), with ONE exception: background-removals and vectorizations answer an owned-image_id cache hit (a ready result already exists for that image) with status: "completed" and estimated_credits: 0 — no new job is queued, the completed webhook event is emitted immediately for a supplied webhook_url, and the result is already available from the op's GET .../{id} endpoint. The other transform ops (img2img, variations, resizes, upscales) always start pending.

id
string<uuid>
required

The job id — poll the op's GET .../{id} endpoint.

status
enum<string>
required

Initial status: pending (job queued — enter the polling flow), or completed with estimated_credits: 0 when background-removals / vectorizations serve an owned-image cache hit (the result is immediately available).

Available options:
pending,
processing,
completed,
failed,
cancelled
Example:

"pending"

estimated_credits
integer
required

Credits this job is expected to cost — 0 on a cache-hit completed response.

Example:

5