Pruna AI P Image Ideogram API Documentation

Pruna AI P Image Ideogram API Documentation

Playground

Try it on WaveSpeedAI!

Pruna P-Image Ideogram generates high-quality images from text prompts, including layout-driven visuals with accurately rendered text. It supports controllable levels of detail to balance speed and quality, along with 1K/2 K resolution, aspect ratio selection, and flexible output formats. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

P-Image-Ideogram Text-to-Image generates images from text prompts with selectable aspect ratio, resolution tier, reasoning effort, output format, and prompt upsampling. It is designed for fast image creation workflows where users need simple controls and predictable pricing across 1k and 2k outputs.


Why Choose This?

  • Text-to-image generation
    Generate images directly from natural-language prompts.

  • Flexible aspect ratios
    Choose from square, landscape, portrait, and common social media layouts.

  • Resolution tiers
    Select 1k for lower-cost generation or 2k for higher-resolution output.

  • Thinking level control
    Choose the reasoning effort used before image generation, from very low to very high.

  • Prompt upsampling
    Expand the prompt before generation for additional detail when needed.

  • Multiple output formats
    Generate images in png, jpeg, or webp format.


Parameters

ParameterRequiredDescription
promptYesText prompt describing the image to generate. Minimum length: 1 character.
aspect_ratioNoAspect ratio of the generated image. Supported values: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.
resolutionNoOutput resolution tier: 1k or 2k.
thinkingNoReasoning effort used before image generation. Supported values: very low, low, medium, high and very high.
output_formatNoOutput image format: png, jpeg, or webp.
prompt_upsamplingNoExpand the prompt before generation for additional detail.

How to Use

  1. Write your prompt — Describe the image you want to generate.
  2. Choose aspect ratio — Select the layout that matches your target format.
  3. Choose resolution — Use 1k for lower-cost generation or 2k for higher-resolution output.
  4. Set thinking level — Select the reasoning effort used before image generation.
  5. Choose output format — Select png, jpeg, or webp.
  6. Submit — Generate the final image and retrieve the output URL.

Pricing

Pricing depends on selected resolution and thinking.

Resolutionvery lowlowmediumhighvery high
1K$0.003$0.0075$0.010$0.015$0.033
2K$0.006$0.015$0.020$0.030$0.066

Best Use Cases

  • Prompt-based image generation — Create images directly from text prompts.
  • Marketing visuals — Generate campaign images, social graphics, and promotional assets.
  • Concept exploration — Quickly test visual ideas, styles, layouts, and creative directions.
  • Design drafts — Create early-stage visuals before moving into final design production.
  • Layout-specific images — Generate square, portrait, and landscape images for different use cases.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "1:1",
  "resolution": "1k",
  "thinking": "high",
  "output_format": "jpeg",
  "prompt_upsampling": true
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/pruna-ai/p-image/ideogram" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-Text prompt describing the image to generate.
aspect_ratiostringNo1:11:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3Aspect ratio of the generated image.
resolutionstringNo1k1k, 2kOutput resolution tier.
thinkingstringNohighvery low, low, medium, high, very highReasoning effort used before image generation.
output_formatstringNojpegpng, jpeg, webpOutput image format.
prompt_upsamplingbooleanNotrue-Expand the prompt before generation for additional detail.
enable_sync_modebooleanNofalse-If set to `true`, the request attempts to wait for the generated result and return outputs in the same response. If the result is not ready within the sync wait window, the API can return a timeout body while the task continues processing. This option is only available via the API and is supported only by some models.
enable_base64_outputbooleanNofalse-If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayOutput values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.statusstringTask status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses.
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction
data.modelstringModel ID used for the prediction
data.outputsarray<string | object>Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model.
data.urlsobjectObject containing related API endpoints
data.statusstringStatus: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses
data.created_atstringISO timestamp of when the request was created
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2026 WaveSpeedAI. All rights reserved.