Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Pruna AI: P-Image

P-Image is a real-time text-to-image model from Pruna. It delivers sub-second image generation with strong text rendering and tight prompt adherence. It targets production workloads that need fast inference, predictable output control, and efficient scaling through simple API integration.
Compare models
p-image
AvailablePruna AIImageSync
Price
From $0.005
Modalities
Image

About P-Image

P-Image is Pruna AI's text-to-image model tuned for speed: Pruna describes images in under a second, with accurate prompt following and controlled text rendering. You send a prompt and an optional aspect ratio, custom size, or seed. It is the base of Pruna's image family, with separate models for editing, Ideogram-style typography, and upscaling.

Where it works well

  • Pruna describes generation in under one second, which makes interactive previews and bulk jobs practical.
  • Text inside images is rendered with controlled placement, useful for posters, ads, and labels.
  • A seed parameter allows reproducible output when you iterate on a prompt.
  • Preset ratios cover square, landscape, portrait, and 3:2 or 4:3 formats, plus custom sizes in 16-pixel steps.

When to choose another model

  • Maximum custom dimensions are modest, so print-size output needs a separate upscaling step.
  • It generates from text only; editing an existing picture requires the P-Image-Edit model instead.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Text to imageTokenLab endpoint
    POST/v1/images/generations
    curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "operation": "text-to-image",
      "model": "p-image",
      "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
    }'

Parameters

Text to image

ParameterValues and limitsDefaultNotes
height≥ 256, ≤ 14401024Use an integer. Use multiples of 16.
n11Use an integer.
operationNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.
promptNot providedNot providedMinimum length: 1 characters. Maximum length: 2000 characters.
width≥ 256, ≤ 14401024Use an integer. Use multiples of 16.

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.

Text to image

per image
Official price
$0.005
Verified price
—
Discount
—

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
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open P-Image in Console with a prompt ready to edit or send.

Help me create an image with p-image using text-to-image at /v1/images/generations. Show the result, cost, and any limits I should know.

Use cases

Best for
  • Text to Image
  • Live image previews

    Show a picture in an app while a user is still typing, using the sub-second response.

  • Ad and banner drafts

    Generate headline-bearing creatives with readable lettering for quick A/B testing. Test several headline variants cheaply before choosing one.

  • Seed frames for video

    Produce a starting image that a video or avatar model then animates.

Prompt examples

A red fox wearing a yellow raincoat, standing in a puddle on a cobbled street, watercolor style, overcast morning.

Poster for a jazz night: the words 'BLUE ROOM' in large cream letters on a dark teal background, a saxophone silhouette below.

Product photo of a matte black water bottle on a concrete ledge, soft side light, shallow depth of field.

FAQ

What exactly is P-Image?

P-Image is a text-to-image model from Pruna AI. It is built for low latency, generating a picture from a prompt in around a second while keeping prompts followed closely and text legible.

What inputs does it take?

A text prompt is required. Optional inputs are the aspect ratio, custom width and height, a seed, and a toggle for the safety checker. There is no image input; for edits use P-Image-Edit.

Which aspect ratios are supported?

Pruna lists 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3, with 16:9 as the default. Custom sizes are allowed within a documented range in 16-pixel increments.

How does it handle text in images?

Pruna highlights controlled text generation, so short headlines and labels come out readable. For layouts dominated by typography, the Ideogram-based variant gives more control through structured prompts.

How do I get a sharper final image?

Generate fast drafts with P-Image, then run the keeper through P-Image-Upscale. Pruna describes the upscaler as improving detail without changing the composition. This two-step flow keeps the draft stage fast.

How much does P-Image cost?

On TokenLab, P-Image costs $0.005 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 use?

Use https://api.tokenlab.sh/v1/images/generations for P-Image. The request example below shows the matching code shape.

Which operations does P-Image support?

P-Image supports Text to image. Select an operation above to see its endpoint and request example.

Compare P-Image

Sources

Reviewed Oct 2, 2026

More from Pruna AI

Related models