Gemini 3.1 Flash Image

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "gemini-3.1-flash-image",
  "prompt": "A crystal sword icon on a transparent background, game UI art",
  "batch_size": 4,
  "width": 1024,
  "height": 1024
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/google-gemini-3-1-flash-image/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A crystal sword icon on a transparent background, game UI art"
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

prompt

stringrequired

Describe what to generate, or the change to make.

aspect_ratio

enumdefault SQUARE_1K40 options

The shape and size of the output.

thinking_level

enumdefault OFFOFF, MINIMAL, HIGH

How much the model reasons about the prompt before generating. More is slower.

use_web_search

booleandefault false

Let the model look things up on the web to get real subjects and facts right.

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

transparency

booleandefault false

Output the subject alone, with no backdrop behind it.

guidance_file_init_image

file[]

The image to modify

guidance_file_reference_image

file[]

Guides the edit

tile_grid

any

The grid's shape (isometric or hex), the camera, and the tile's footprint and size, shared by every tile of a set.

output_fit

any

Trim the transparent margin, and place the image on a canvas of a fixed size.

prompt_language

string

The language the prompt is written in, so it reaches the model as you meant it.