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

Pruna AI: P-Image-Ideogram

P-Image-Ideogram is a Pruna AI text-to-image model built in collaboration with Ideogram for fast, high-quality visual generation across product, people, and brand-oriented creative work. It offers four generation modes, from Very Low to High, so teams can choose the right balance of speed, cost, and image quality for each workflow while retaining strong prompt following and unusually capable text rendering. The model supports both natural-language prompting and more structured JSON-style prompting for tighter control over layout, color palettes, bounding boxes, and typography-heavy compositions.
Compare models
p-image-ideogram
AvailablePruna AIImageSync
Price
From $0.003
Modalities
Image

About P-Image-Ideogram

P-Image-Ideogram is a Pruna AI text-to-image model built in collaboration with Ideogram, focused on typography, layout, and brand-oriented images. It offers several reasoning levels, starting at very low, to trade speed against quality. Prompts can be plain language or structured JSON to specify layout, colour palettes, and bounding boxes.

Where it works well

  • Typography-heavy compositions are a stated focus, with strong text rendering and prompt following.
  • Structured JSON prompts let you control layout, colour palettes, and bounding boxes.
  • Reasoning levels let one workflow run cheap drafts and high-effort finals.
  • Prompt upsampling is on by default and can improve short prompts.

When to choose another model

  • Higher reasoning levels take more time per image, so it is not the pick for sub-second previews.
  • It is text-to-image only; editing a supplied picture needs P-Image-Edit.

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-ideogram",
      "prompt": "A minimalist product photo of matte black headphones on a soft blue background."
    }'

Parameters

Text to image

ParameterValues and limitsDefaultNotes
height≥ 64, ≤ 25601024Use 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: 2 characters. Maximum length: 7000 characters.
seed≥ 0, ≤ 9007199254740991Not providedUse an integer.
width≥ 64, ≤ 25601024Use 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
$0.003
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-Ideogram in Console with a prompt ready to edit or send.

Help me create an image with p-image-ideogram 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
  • Brand creatives

    Create social graphics and ads with a headline, logo area, and set palette laid out as specified.

  • Packaging mock-ups

    Lay out label text and product imagery with JSON bounding boxes. Text and product placement can be set per region.

  • People and product photography

    Produce realistic portraits and product shots at selectable effort. Choose the effort level to match the shot.

Prompt examples

A bakery menu board: 'FRESH TODAY' in hand-painted cream letters, three pastries below, warm wood background.

{"scene":"skincare ad","palette":["#F4E9DD","#2F5D50"],"headline":"Quiet Mornings","layout":"text left, bottle right"}

Photorealistic portrait of a chef in a steel kitchen, shallow depth of field, natural window light.

FAQ

What exactly is P-Image-Ideogram?

A Pruna AI text-to-image model built with Ideogram for typography-driven and brand-oriented work. It combines strong prompt following with unusually capable text rendering. It sits beside P-Image and P-Image-Edit in the same family.

What are the reasoning levels?

Pruna's guide describes a range of thinking levels that starts at very low and rises through low and medium to high. Lower levels favour speed; higher ones favour quality, so draft low and render finals high.

Can I prompt with JSON?

Yes. Besides natural language, it accepts structured JSON-style prompts that describe layout, colour palettes, bounding boxes, and typography for tighter control. Pruna lists this as a way to specify layout directly.

What sizes can I request?

Preset ratios from 1:1 to 16:9 and portrait variants, or custom width and height up to a documented maximum. A 1K or 2K resolution budget can be chosen.

Which is better, P-Image-Ideogram or P-Image?

Pick Ideogram for text-heavy or layout-specific images where you will spend time on quality. Pick P-Image when speed matters most and the text is short.

How much does P-Image-Ideogram cost?

On TokenLab, P-Image-Ideogram costs $0.003 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-Ideogram use?

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

Which operations does P-Image-Ideogram support?

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

Compare P-Image-Ideogram

Sources

Reviewed Oct 2, 2026

More from Pruna AI

Related models