Skip to content

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

NameTypeRequiredDescription
image_sizestringNoAspect ratio for the generated image Options: auto, 1024x1024, 1536x1024, 1024x1536.
qualitystringNoQuality for the generated image Options: low, medium, high.
mask_image_urlstringNoThe URL of the mask image to use for the generation. This indicates what part of the image to edit.
num_imagesintegerNoNumber of images to generate
input_fidelitystringNoInput fidelity for the generated image Options: low, high.
promptstringYesThe prompt for image generation
backgroundstringNoBackground for the generated image Options: auto, transparent, opaque.
image_urlsstring[]YesThe URLs of the images to use as a reference for the generation.
output_formatstringNoOutput 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.