# Ideogram 4.5 — API Reference

Model ID: `model_ideogram-v4-5`

---

## Authentication

- **API_KEY** and **API_SECRET** are found in your [Scenario Project Settings](https://app.scenario.com/team&tab=api_keys) under API Keys.
- Set them as environment variables `SCENARIO_SDK_API_KEY` and `SCENARIO_SDK_API_SECRET` — both SDKs pick them up by default.
- For raw HTTP (cURL), use Basic Auth: `Authorization: Basic base64("<API_KEY>:<API_SECRET>")`.

### Install the SDK

- JavaScript / TypeScript: `npm install @scenario-labs/sdk`
- Python: `pip install scenario-sdk`

---

## Generate

**Endpoint:** `POST https://api.cloud.scenario.com/v1/generate/custom/model_ideogram-v4-5`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Describe the image you want to generate, or the edit to apply, including any text that should appear in it. Refer to input images by position: image 1 is the source, image 2 the first reference, and so on. |
| `referenceImages` | assetId[] | - | - | Optional images to edit (up to 5, or 4 with a mask). The first is the source image to edit, the others are references. Leave empty to create from your prompt alone. |
| `mask` | assetId | - | - | Optional mask over the first reference image. White marks the region to edit, black the region to keep. Requires Aspect Ratio to stay on Auto. |
| `aspectRatio` | string | - | `auto` | The shape of the image. Auto lets the model choose from the prompt and images; Source keeps the first reference image's shape. |
| `resolution` | string | - | `2K` | The output resolution when an explicit aspect ratio is set. 1K exists only for 1:1, 4:5, 3:4, 2:3, 5:8, 9:16, 1:2 and their landscape counterparts. |
| `quality` | string | - | `high` | The quality-versus-speed tradeoff. Higher quality takes longer and costs more. Very Low requires a reference image. |
| `magicPrompt` | string | - | `auto` | Whether the model enriches your prompt before generating. Applies to text-to-image only: edits are always turned into structured instructions. |
| `numOutputs` | number | - | `1` | How many images to generate (1-8). Each additional image adds to the cost. |
| `seed` | number | - | - | A number that locks in the randomness of the generation. Leave blank for a new result each time. |
| `enableCopyrightDetection` | boolean | - | `false` | Screens outputs for copyrighted content. Flagged images are withheld. Adds latency. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_ideogram-v4-5" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "aspectRatio": "auto",
  "resolution": "2K",
  "quality": "high",
  "magicPrompt": "auto",
  "numOutputs": 1,
  "enableCopyrightDetection": false
}
EOF
```

**Python**

```python
import os
from scenario_sdk import Scenario

client = Scenario(
    api_key=os.environ.get("SCENARIO_SDK_API_KEY"),
    api_secret=os.environ.get("SCENARIO_SDK_API_SECRET"),
)

body = {
    "prompt": "A fantasy landscape",
    "aspectRatio": "auto",
    "resolution": "2K",
    "quality": "high",
    "magicPrompt": "auto",
    "numOutputs": 1,
    "enableCopyrightDetection": False
}

response = client.generate.run_model(
    model_id="model_ideogram-v4-5",
    body=body,
)
print(response)
```

**JavaScript**

```javascript
import Scenario from "@scenario-labs/sdk";

const client = new Scenario({
  apiKey: process.env["SCENARIO_SDK_API_KEY"],
  apiSecret: process.env["SCENARIO_SDK_API_SECRET"],
});

const body = {
  "prompt": "A fantasy landscape",
  "aspectRatio": "auto",
  "resolution": "2K",
  "quality": "high",
  "magicPrompt": "auto",
  "numOutputs": 1,
  "enableCopyrightDetection": false
};

const response = await client.generate.runModel("model_ideogram-v4-5", { body });
console.info(response);
```

---

## Retrieve Results

After submitting a generation request, you receive a `jobId`. Poll the job until `job.status` is `"success"`. The generated asset IDs are in `job.metadata.assetIds`.

**Endpoint:** `GET https://api.cloud.scenario.com/v1/jobs/{jobId}`

### Example Requests

**cURL**

```bash
curl -X GET "https://api.cloud.scenario.com/v1/jobs/<JOB_ID>" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)"
```

**Python**

```python
job = client.jobs.retrieve(job_id="<JOB_ID>")
print(job.status)
print(job.metadata.asset_ids)
```

**JavaScript**

```javascript
// Option 1 — wait on the response from runModel using the SDK helper
const completed = await response.job.wait();
console.info(completed.status);
console.info(completed.metadata?.assetIds);

// Option 2 — retrieve a job by its ID
const job = await client.jobs.retrieve("<JOB_ID>");
console.info(job.status);
console.info(job.metadata?.assetIds);
```

**Example response:**

```json
{
  "job": {
    "jobId": "job_abc123",
    "status": "success",
    "metadata": {
      "assetIds": [
        "asset_abc123"
      ]
    }
  }
}
```

> **Important:** Generated asset URLs are **temporary** and expire after a short period. Download and store any images you wish to keep before the URL expires. More info: [Content Delivery Network (CDN)](https://docs.scenario.com/get-started/documentation/content-delivery-network-cdn).

---

*Generated by [Scenario](https://app.scenario.com)*