Pruna AI: P-Image-Edit
p-image-edit- Price
- From $0.01
- Modalities
- Image
About P-Image-Edit
P-Image-Edit is Pruna AI's image editing model, taking a text instruction and one to five reference images and returning a new image. It handles targeted edits, style transfer, and compositions that merge several inputs. A turbo setting, on by default, speeds it up and can be switched off for complicated tasks. It is the editing counterpart to P-Image.
Where it works well
- Accepts one to five reference images in a single call, enabling multi-image composition.
- You can pick a primary reference or let the model combine all inputs.
- The output ratio can follow the input image, avoiding crops after an edit.
- Turbo mode trades some fidelity for speed and can be disabled on difficult edits.
When to choose another model
- Complex edits may need turbo mode turned off, which makes them slower.
- It edits and composes from images; creating a picture from text alone is the job of P-Image.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
Image editingTokenLab endpointPOST/v1/images/generationscurl -X POST "https://api.tokenlab.sh/v1/images/generations" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "operation": "image-to-image", "model": "p-image-edit", "prompt": "A minimalist product photo of matte black headphones on a soft blue background.", "image_url": "https://example.com/source.png" }'
Parameters
Image editing
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
height | Not provided | 1024 | Use an integer. |
image | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_url | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
image_urls | Not provided | Not provided | Alias of the combined images input. See input_limits.images for the total input image count. |
images | Inputs: ≥ 1, ≤ 4 | Not provided | Limits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list. |
n | 1 | 1 | Use an integer. |
operation | Not provided | Not provided | Not provided |
output_format | jpeg, png, webp | Not provided | Default encoding is shared by these equivalent values: jpg, jpeg. |
prompt | Not provided | Not provided | Minimum length: 1 characters. Maximum length: 2000 characters. |
width | Not provided | 1024 | Use an integer. |
Fields outside this contract are rejected.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Image editing
per image- Official price
- $0.01
- Verified price
- —
- Discount
- —
| Official priceper image | Verified priceper image | Discount | |
|---|---|---|---|
| Image editing | $0.01 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open P-Image-Edit in Console with a prompt ready to edit or send.
Help me create an image with p-image-edit using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.
Use cases
Product restyling
Change the background, lighting, or colourway of a product photo while keeping the item itself.
Composite scenes
Place a person from one photo into a setting from another using multi-image input.
Style transfer
Repaint a photo in the look of a reference illustration. Keep the style words explicit in the prompt.
Prompt examples
Replace the plain wall behind the sofa with exposed brick, keep the sofa and lighting unchanged.
Put the woman from image 1 on the beach from image 2, matching the evening light.
Make this sneaker photo look like a pencil sketch on cream paper.
FAQ
What exactly is P-Image-Edit?
It is Pruna AI's real-time image editing model. You give it an instruction plus reference images, and it returns an edited or combined picture while following the prompt closely.
How many images can I send?
One to five reference images at once. With several, you can name the primary one or ask the model to blend them, which is how multi-image composites are made.
What does turbo mode do?
Turbo is on by default and makes edits faster. Pruna advises turning it off for complicated tasks, accepting slower runs for better handling of difficult instructions.
Which output ratios are possible?
Matching the input image, or fixed ratios such as 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3. Matching the input is the safest choice for retouching.
Which is better, P-Image-Edit or P-Image?
Use P-Image-Edit when the result must start from an existing picture. Use P-Image when you only have text and want a new image from scratch.
How much does P-Image-Edit cost?
On TokenLab, P-Image-Edit costs $0.01 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.
Which endpoint should P-Image-Edit use?
Use https://api.tokenlab.sh/v1/images/edits for P-Image-Edit. The request example below shows the matching code shape.
Which operations does P-Image-Edit support?
P-Image-Edit supports Image editing. Select an operation above to see its endpoint and request example.
Compare P-Image-Edit
Guides that use P-Image-Edit
Sources
Reviewed Oct 2, 2026