GET

/v1/schemas/fal/image/fal-ai/gemini-3.1-flash-image-preview

Accept:

kind inputactivity imagehash 22a8ad22…extracted Nov 10, 2026version currentsource upstream spec ↗

field	recorded source
schema	Source linked above. upstream-spec Source trace `6c791ccbea45decaebc188757d82a5ae7182fbe1f9f67024f8d5945db4bcd9b7` { "fetchedAt": 1794286801, "extractorVersion": "2", "verifiedAt": null }

Request body

20 properties · 1 required · 7 $defs

property	type	description	constraints
prompt*	string	The text prompt to generate an image from.	length ≥ 3 · length ≤ 50000
limit_generations	boolean	Experimental parameter to limit the number of generations from each round of prompting to 1. Set to `True` to to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This…	default: true
enable_web_search	boolean	Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image.	default: false
seed	integer	The seed for the random number generator.	nullable
output_format	enum	The format of the generated image.	jpeg \| png \| webp · default: "png"
sync_mode	boolean	If `True`, the media will be returned as a data URI and the output data won't be available in the request history.	default: false
return_history	boolean	Return reusable native conversations with original image parts and provider thought signatures. Uses a native provider. Each generated conversation is independent; send its messages as history for the next turn.	default: false
temperature	number	Sampling temperature. Omit to use the provider default of 1. Explicit values use a direct Google or Vertex API.	0 ≤ n ≤ 2 · nullable
max_output_tokens	integer	Maximum output tokens for the generation. Omit to retain the provider default. Explicit values use a direct Google or Vertex API.	1 ≤ n ≤ 32768 · nullable
resolution	enum	The resolution of the image to generate.	0.5K \| 1K \| 2K \| 4K · default: "1K"
top_p	number	Nucleus sampling probability. Omit to use the provider default of 0.95. Explicit values use a direct Google or Vertex API.	0 ≤ n ≤ 1 · nullable
include_thoughts	boolean	Whether to include thought summaries. Omit to preserve the existing behavior: an explicit thinking_level requests summaries. Set limit_generations=false to return summary text in description. This does not disable thinking or return intermediate thought images.	nullable
system_prompt	string	Optional system instruction that steers the model's persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers).	length ≤ 50000 · default: ""
safety_tolerance	enum	The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict.	1 \| 2 \| 3 \| 4 \| 5 \| 6 · default: "4"
aspect_ratio	enum	The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use "auto" to let the model decide based on the prompt.	auto \| 21:9 \| 16:9 \| 3:2 \| 4:3 \| 5:4 · +9 more · nullable
num_images	integer	The number of images to generate.	1 ≤ n ≤ 4 · default: 1
history	GeminiVideoMessage[]	Previous native Gemini turns, including original parts and thought signatures from conversations. The current prompt starts a new user turn.
context	GeminiTextPart \| GeminiImagePart \| GeminiDocumentPart[]	Ordered text, image, PDF, UTF-8 text-file or video parts appended to the current prompt. Original media bytes are preserved; images count toward the total 14-reference limit.
enable_image_search	boolean	Ground image generation with Google Image Search. Can be combined with enable_web_search; source attribution is returned in grounding_metadata. Uses direct Google or Vertex APIs.	default: false
thinking_level	enum	Controls thinking effort ('minimal' or 'high') and requests thought summaries. Omit to use the provider default ('minimal'); thinking cannot be disabled.	minimal \| high · nullable

Types

7 $defs

GeminiAudioPartobject

thought_signature	string	Opaque provider-issued thought signature. Replay it unchanged on its original part.	length ≥ 1 · nullable
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
audio_url*	string	Original audio URL or data URI from a previous Flash Image request (up to 15 MB).
type*	const	The audio part discriminator.	"audio"

GeminiDocumentPartobject

thought_signature	string	Opaque provider-issued thought signature. Replay it unchanged on its original part.	length ≥ 1 · nullable
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
file_url*	string	PDF or UTF-8 plain-text document URL or data URI (up to 15 MB).
mime_type*	enum	The document's media type.	application/pdf \| text/plain
type*	const	The document part discriminator.	"document"

GeminiImagePartobject

thought_signature	string	Opaque provider-issued thought signature. Replay it unchanged on its original part.	length ≥ 1 · nullable
type*	const	The image part discriminator.	"image"
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
image_url*	string	Original image URL or data URI. Replayed without resizing or re-encoding.

GeminiSignaturePartobject

thought_signature*	string	Provider-issued signature-only part, replayed unchanged.	length ≥ 1
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
type*	const	The signature part discriminator.	"signature"

GeminiTextPartobject

text*	string	Text at this position in the conversation.
thought_signature	string	Opaque provider-issued thought signature. Replay it unchanged on its original part.	length ≥ 1 · nullable
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
type*	const	The text part discriminator.	"text"

GeminiVideoMessageobject

parts*	GeminiTextPart \| GeminiImagePart \| GeminiDocumentPart[]	Ordered text, image, document, video, audio, and signature parts.	items ≥ 1
role*	enum	Native Gemini conversation role.	user \| model

GeminiVideoPartobject

thought_signature	string	Opaque provider-issued thought signature. Replay it unchanged on its original part.	length ≥ 1 · nullable
thought	boolean	Provider thought marker, preserved when replaying a returned conversation.	nullable
video_url*	string	Video URL or data URI (up to 15 MB and 120 seconds), or a YouTube URL. Supported by Flash Image only.
type*	const	The video part discriminator.	"video"

Validate a payload

before you spend tokens

shell

$ curl -X POST https://modelschemas.com/v1/validate \
    -d '{"provider":"fal","endpointId":"fal-ai/gemini-3.1-flash-image-preview","payload":{…}}'
→ {"valid": false, "errors": [{"path": "#", "keyword": "required", …}]}