# Riverflow 2.5 Fast — API Reference

Model ID: `model_sourceful-riverflow-2-5-fast`

---

## 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_sourceful-riverflow-2-5-fast`

### Parameters

| Parameter | Type | Required | Default | Description |
|-----------|------|----------|---------|-------------|
| `prompt` | string | yes | - | Describe what to create or how to edit your reference images. At least 2 characters. |
| `referenceImages` | assetId[] | - | - | Optional images to edit or build from. Add up to 4. |
| `resolution` | string | - | `1K` | The output detail level. 2K is sharper but costs more than 1K. |
| `aspectRatio` | string | - | `auto` | The shape of the output. Auto picks a fitting ratio for you. |
| `thinkingLevel` | string | - | `medium` | How much effort the model spends refining the result. Higher levels improve quality but take longer. |
| `fontUrls` | string[] | - | - | Optional links to your own font files (TTF, OTF, WOFF, or WOFF2) to use for text in the image. Add up to 2. Each font adds to the cost. |
| `fontTexts` | string[] | - | - | The text to render in each font above, in the same order. The first entry uses the first font, and so on (up to 300 characters each). |
| `background` | string | - | `original` | How to handle the background. Original keeps it as-is, Transparent removes it, or Solid fills it with a color you choose. |
| `backgroundColor` | string | - | `#ffffff` | The fill color when Background is set to Solid, as a hex code (for example, #ffffff for white). |
| `scoringPrompt` | string | - | - | Optional instructions telling the model how to judge and pick the best result among its candidates. |
| `scoringRubric` | string | - | - | Optional detailed scoring criteria, given as a JSON list of 1–8 dimensions (each with a key, label, description, and weight). |
| `enhancePrompt` | boolean | - | `false` | Lets the model expand and improve your instruction before generating. |

### Example Requests

**cURL**

```bash
curl -X POST "https://api.cloud.scenario.com/v1/generate/custom/model_sourceful-riverflow-2-5-fast" \
  -H "Authorization: Basic $(echo -n '<API_KEY>:<API_SECRET>' | base64)" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'EOF'
{
  "prompt": "A fantasy landscape",
  "resolution": "1K",
  "aspectRatio": "auto",
  "thinkingLevel": "medium",
  "background": "original",
  "backgroundColor": "#ffffff",
  "enhancePrompt": 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",
    "resolution": "1K",
    "aspectRatio": "auto",
    "thinkingLevel": "medium",
    "background": "original",
    "backgroundColor": "#ffffff",
    "enhancePrompt": False
}

response = client.generate.run_model(
    model_id="model_sourceful-riverflow-2-5-fast",
    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",
  "resolution": "1K",
  "aspectRatio": "auto",
  "thinkingLevel": "medium",
  "background": "original",
  "backgroundColor": "#ffffff",
  "enhancePrompt": false
};

const response = await client.generate.runModel("model_sourceful-riverflow-2-5-fast", { 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)*