# Topaz Apollo

Apollo transforms source video into smooth slow motion or higher-frame-rate output for retiming, frame conversion, and cleaner motion workflows.

## API Information

- **Model Slug:** topaz-apollo
- **Branded URL:** https://www.eachlabs.ai/topaz/topaz/topaz-apollo
- **Provider:** topaz
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** Pricing is based on the credits used for each execution, at $0.10 per credit.
- **Estimated Processing Time:** 35 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/topaz-apollo

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Pricing is based on the credits used for each execution, at $0.10 per credit.

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Pricing is based on the credits used for each execution, at $0.10 per credit. |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | - | URL of the source video. The file is re-hosted before Topaz receives it. |
| size | integer | No | - | 1–99999999999 | Optional source size in bytes. Topaz recalculates it on receipt; omit if unknown. |
| container | string | No | mp4 | 3gp, avi, dv, flv, m1v, m2t, m2ts, m2v, m4v, mkv, mov, mp4, mpeg, mpg, mts, mxf, ser, ts, vob, webm, wmv | Source container. Defaults to mp4. |
| output_width | integer | No | 1920 | 1–8192 | Output video width in pixels. Defaults to 1920. |
| output_height | integer | No | 1080 | 1–8192 | Output video height in pixels. Defaults to 1080. |
| output_frame_rate | number | No | - | 1–240 | Output video frame rate. Defaults to the source frame rate unless a frame interpolation model overrides it. |
| slowmo | integer | No | 2 | 1–16 | Slow motion factor. Range: 1-16. Default: 2. |
| fps | number | No | 60 | 15–240 | Target output frame rate for interpolation. Range: 15-240. Default: 60. |
| duplicate | boolean | No | false | - | Analyze input for duplicate frames and remove them. Default: false. |
| duplicate_threshold | number | No | 0.1 | 0.001–0.1 | Duplicate detection sensitivity. Range: 0.001-0.1. Default: 0.1. |
| audio_transfer | string | No | Copy | Copy, Convert, None | How Topaz handles source audio. Default: Copy. |
| audio_codec | string | No | AAC | AAC, AC3, PCM | Audio codec used when audio is copied or converted. Default: AAC. |
| video_encoder | string | No | H265 | AV1, H264, H265, ProRes, VP9 | Output video encoder. Default: H265. |
| video_profile | string | No | - | - | Codec profile accepted by the selected Topaz encoder, such as Main10 for H265 or 422 HQ for ProRes. |
| container_out | string | No | mp4 | mp4, mov, mkv, avi, webm | Desired output container. Topaz may override this for some encoders. |
| dynamic_compression_level | string | No | High | Low, Mid, High | Automatic compression level for AV1, H264, and H265. Default: High. |

## 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": "topaz-apollo",
  "input": {
    "video_url": "https://cdn-us.eachlabs.ai/defaults/4835fa0dfa4a4e0e86836be1fee8c0a4.mp4"
  }
}'
```

## Output Schema

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

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "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 |

## 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.