# P-Image Ideogram

P-Image-Ideogram turns text prompts into detailed 1K or 2K images, including layouts with rendered text for posters, ads, and social graphics.

## API Information

- **Model Slug:** p-image-ideogram
- **Branded URL:** https://www.eachlabs.ai/pruna/p-image/p-image-ideogram
- **Provider:** Pruna AI
- **Category:** Text to Image
- **Output Type:** image
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** high 1K image: $0.015
- **Estimated Processing Time:** 15 seconds
- **Last Updated:** 2026-07-31
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/p-image-ideogram

## Pricing

- **Charge Type:** dynamic
- **Estimated Price (default example):** $0.0150
- **Pricing Details:** high 1K image: $0.015

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| width > "0" AND height > "0" AND thinking eq_i "very low" | very low width/height custom dimensions: width*height below 2.62M pixels bills 1K ($0.003); above bills 2K ($0.006) |
| thinking eq_i "very low" AND image_size eq_i "2K" | very low 2K image: $0.006 |
| thinking eq_i "very low" | very low 1K image: $0.003 |
| width > "0" AND height > "0" AND thinking eq_i "low" | low width/height custom dimensions: width*height below 2.62M pixels bills 1K ($0.0075); above bills 2K ($0.015) |
| thinking eq_i "low" AND image_size eq_i "2K" | low 2K image: $0.015 |
| thinking eq_i "low" | low 1K image: $0.0075 |
| width > "0" AND height > "0" AND thinking eq_i "medium" | medium width/height custom dimensions: width*height below 2.62M pixels bills 1K ($0.01); above bills 2K ($0.02) |
| thinking eq_i "medium" AND image_size eq_i "2K" | medium 2K image: $0.02 |
| thinking eq_i "medium" | medium 1K image: $0.01 |
| width > "0" AND height > "0" AND thinking eq_i "high" | high width/height custom dimensions: width*height below 2.62M pixels bills 1K ($0.015); above bills 2K ($0.03) |
| thinking eq_i "high" AND image_size eq_i "2K" | high 2K image: $0.03 |
| thinking eq_i "high" | high 1K image: $0.015 |
| Default (fallback) | Default high 1K image: $0.015 |

## Input Schema

No input parameters documented.

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "p-image-ideogram",
  "input": {}
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated image)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**P-Image Ideogram Overview**

P-Image Ideogram is a **Pruna AI text-to-image** model built specifically for design work where in-image text, layout, and branding must be precise. It turns natural language prompts into detailed 1K or 2K images, including posters, ads, and social graphics with correctly rendered typography and tight prompt adherence. The model is part of the Pruna AI **P-Image** family, optimized for fast, production-grade generation and high-volume workflows. Its primary differentiator is accurate, controllable text rendering inside images: users can quote text in the prompt and get clean, correctly spelled, well-placed lettering suitable for real campaigns and marketing assets. On each::labs, the P-Image Ideogram API makes this capability accessible through a simple, scalable integration for creative and product teams.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.