# Replicate HTTP API on looot

Replicate HTTP API gives your agent 3 jobs through looot: generate an image from a prompt, generate a video from a prompt, generate music from a prompt. 4 endpoints run today, from $0.003 per result.

## At a glance

- Category: Generative AI
- Access: Runs on looot's platform key: you do not need your own Replicate HTTP API account
- Price: from $0.003

## Choose it when

- You need to generate an image from a prompt: Replicate HTTP API is the only provider on looot that runs this job today.
- You need to generate a video from a prompt: Replicate HTTP API is the only provider on looot that runs this job today.
- You need to generate music from a prompt: Replicate HTTP API is the only provider on looot that runs this job today.

## Endpoints and jobs

| Endpoint | Job | Price | Runs (30 days) | Benchmark |
|---|---|---|---|---|
| [Generate an image](/public-catalog/replicate-models-predictions) | `image.generate` | $0.003 per result | 87.9% of 124 runs without an error, median 6.7 s | no benchmark yet |
| [Google Veo 3.1 video](/public-catalog/replicate-veo-generate) | `video.generate` | $0.40 per result | 47.1% of 17 runs without an error, median 37.3 s | no benchmark yet |
| [Generate music](/public-catalog/replicate-music-generate) | `music.generate` | $0.035 per result | not enough runs to rank | no benchmark yet |
| [Generate a video](/public-catalog/replicate-video-generate) | `video.generate` | $0.50 per result | not enough runs to rank | no benchmark yet |

## How the numbers are measured

Run numbers are looot's own runs of each endpoint over the last 30 days: the share that completed without an error, and the median time to answer. An endpoint with fewer than 10 runs in that window shows "not enough runs to rank" and is never ranked. Prices are what looot charges per call or per result, fee included, read from the live catalog; you prepay credit and each call is charged when it runs.

Read 2026-11-10 23:22 UTC.

## For agents

The minimal request for Generate an image (`replicate-models-predictions`). Replace each <placeholder> with your value and send a new idempotency key per run.

### MCP

```json
{
  "endpointId": "replicate-models-predictions",
  "input": {
    "model_owner": "<model_owner>",
    "model_name": "<model_name>",
    "input": "<input>"
  },
  "idempotencyKey": "<a new id per run>"
}
```

### REST

```bash
curl -X POST https://api.looot.ai/v1/runs \
  -H "Authorization: Bearer $LOOOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"endpointId":"replicate-models-predictions","input":{"model_owner":"<model_owner>","model_name":"<model_name>","input":"<input>"},"idempotencyKey":"<a new id per run>"}'
```

### CLI

```bash
looot run replicate-models-predictions --input '{"model_owner":"<model_owner>","model_name":"<model_name>","input":"<input>"}'
```