OpenAI · fal.ai · Image edit
GPT Image 1.5
GPT Image 1.5 (OpenAI), image edit, served by fal.ai. The OpenAPI schema for the fal-ai/gpt-image-1.5/edit queue. Price: Same per-image table as text-to-image; image_size auto priced as the larger size. Input image tokens $0.008 per 1k: $0.012 allowance per call.
Usage based fal.aiImagefal/gpt-image-1-5-editListed
Activation pending; your agent will see it as unavailable until then.
Use this tool with your agent
Give this to your agent
Use my connected Agentik MCP server. I want to use the tool fal/gpt-image-1-5-edit (GPT Image 1.5 (OpenAI), image edit). Call inspect_tool with {"tool_id": "fal/gpt-image-1-5-edit"} first and tell me the price before anything runs. Ask me for the inputs it needs; never invent values, IDs or file URLs. When I confirm, call run_tool with tool_id "fal/gpt-image-1-5-edit" and my inputs, follow it with get_run if it is still running, and give me the result and the price Agentik reports. If the tool is unavailable, say so and use discover_tools to propose an alternative.Show the prompt
Paste it into Claude, ChatGPT or Codex: your agent takes it from there, and shows the price before it runs.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
image_size | string | No | Aspect ratio for the generated image Options: auto, 1024x1024, 1536x1024, 1024x1536. |
quality | string | No | Quality for the generated image Options: low, medium, high. |
mask_image_url | string | No | The URL of the mask image to use for the generation. This indicates what part of the image to edit. |
num_images | integer | No | Number of images to generate |
input_fidelity | string | No | Input fidelity for the generated image Options: low, high. |
prompt | string | Yes | The prompt for image generation |
background | string | No | Background for the generated image Options: auto, transparent, opaque. |
image_urls | string[] | Yes | The URLs of the images to use as a reference for the generation. |
output_format | string | No | Output format for the images Options: jpeg, png, webp. |
How your agent calls it
First inspect_tool for the current schema and price, then run_tool with the published example after confirming your inputs:
{
"tool_id": "fal/gpt-image-1-5-edit",
"input": {
"prompt": "make the cube blue, keep everything else",
"image_urls": [
"https://storage.googleapis.com/falserverless/example_outputs/nano-banana-2-t2i-output.png"
],
"quality": "low",
"image_size": "1024x1024",
"input_fidelity": "low",
"num_images": 1
}
}Price and billing
- Price
- Usage based
- Model
- Per unit
- Detail
- The provider’s price, with no markup. Billed for measured usage.
- The provider’s price, 0% markup.
- One prepaid balance for every provider; your agent sees the price before it runs.
- Pay for measured usage; unused reservations are released.