Nano Banana 2.1 image edit with image, video or PDF context

Needs prompt. Served by fal.ai.

Inputs

1 required

Prompt: The prompt for image editingRequired · prompt
Output format: The format of the generated image (jpeg, png or webp)Optional · output_format
Resolution: The resolution of the image to generate (1K, 2K or 4K)Optional · resolution
Pdf URL: Optional PDF document to use as input contextOptional · pdf_url
Thinking level: How much the model reasons before generating (minimal, medium or high)Optional · thinking_level
Enable web search: Enable web search for the image generation taskOptional · enable_web_search
Image URLs: The URLs of the images to use for image-to-image generation or image editingOptional · image_urls
Seed: The seed for the random number generatorOptional · seed
Safety tolerance: The safety tolerance level for content moderationOptional · safety_tolerance
Video URL: Optional video to use as input contextOptional · video_url
Aspect ratio: The aspect ratio of the generated imageOptional · aspect_ratio
System prompt: Optional system instruction that steers the model's persona and output style across the requestOptional · system_prompt
Limit generations: Experimental parameter to limit the number of generations from each round of prompting to 1Optional · limit_generations
Num images: The number of images to generateOptional · num_images

Price: Usage based, at the cost the provider reports for the call
Billing: Billed at the cost the provider reports for the call, never above $5.5509. Your agent sees the maximum before running.
Price checked: 7 October 2026

Your agent reads the schema and the price with inspect_tool before it runs the tool.

Nano Banana