impulse

GPT Image 2 Edit

Frontier labImage
API id edit
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
19 listings
Released
-
date not published

Where to run it

1 host serve GPT Image 2 Edit. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
falInference
edit
-
Show 18 more listings: regions, snapshots and variants
fal
low · 1024×768
edit
-
low · 1024×1024
edit
-
low · 1024×1536
edit
-
low · 1920×1080
edit
-
low · 2560×1440
edit
-
low · 3840×2160
edit
-
medium · 1024×768
edit
-
medium · 1024×1024
edit
-
medium · 1024×1536
edit
-
medium · 1920×1080
edit
-
medium · 2560×1440
edit
-
medium · 3840×2160
edit
-
high · 1024×768
edit
-
high · 1024×1024
edit
-
high · 1024×1536
edit
-
high · 1920×1080
edit
-
high · 2560×1440
edit
-
high · 3840×2160
edit
-

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
TextImages
Produces
Images

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller OpenAI models

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using fal's API.

Python
from litellm import completion

response = completion(
    model="fal_ai/edit",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

Which APIs offer GPT Image 2 Edit?

GPT Image 2 Edit runs on 1 API: fal.

Is GPT Image 2 Edit being retired?

No retirement date is scheduled for it on any API we track.

What is GPT Image 2 Edit's API model id?

Use edit with fal.

Sources

Raw catalog entry for edit on fal
{
  "litellm_provider": "fal_ai",
  "metadata": {
    "notes": "Editing endpoint of gpt-image-2 on fal.ai, reached through the image generation path with fal's image_urls param since /v1/images/edits is not wired for fal_ai. Prices include one input image and live in keyed entries fal_ai/{quality}/{width}-x-{height}/openai/gpt-image-2/edit. This flat entry is the fallback for the default edit request (quality=high, image_size=auto, inferred from the input image, priced as 1024x768 high)"
  },
  "mode": "image_generation",
  "output_cost_per_image": 0.151,
  "source": "https://fal.ai/models/openai/gpt-image-2/edit",
  "supported_endpoints": [
    "/v1/images/generations"
  ],
  "supports_vision": true
}