# Create Prediction — Replicate

> Create a new prediction See the documentation

- Key: `replicate-create-prediction`
- Type: Action (Write)
- Version: 0.0.2
- App: Replicate (`replicate`) — https://pipedream.com/apps/replicate.md
- This page (HTML): https://pipedream.com/apps/replicate/actions/create-prediction
- Hints: open-world
- Source: https://github.com/PipedreamHQ/pipedream/blob/master/components/replicate/actions/create-prediction/create-prediction.mjs

## Description

Create a new prediction [See the documentation](https://replicate.com/docs/reference/http#predictions.create)

## Props

| Prop | Type | Required | Description |
|---|---|---|---|
| `collectionSlug` | `string` | Yes | The ID of the collection that you want to use. Options are loaded from the connected account. |
| `modelId` | `string` | Yes | The ID of the model version that you want to run. Options are loaded from the connected account. |
| `version` | `string` | Yes | The version of the model version that you want to use. Options are loaded from the connected account. |
| `input` | `string` | Yes | The model's input as a JSON object. The input depends on what model you are running. To see the available inputs, click the "Run with API" tab on the model you are running. For example, stability-ai/stable-diffusion takes prompt as an input. |
| `webhook` | `string` | No | An HTTPS URL for receiving a webhook when the prediction has new output. |
| `webhookEventsFilter` | `string[]` | No | By default, we will send requests to your webhook URL whenever there are new logs, new outputs, or the prediction has finished. See de documentartion here for more details. |

## Run it

**MCP**

```ts
import { Client } from "@modelcontextprotocol/sdk/client/index.js"
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp.js"
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const accessToken = await pd.rawAccessToken

const transport = new StreamableHTTPClientTransport(
  new URL("https://remote.mcp.pipedream.net/v3"),
  {
    requestInit: {
      headers: {
        Authorization: `Bearer ${accessToken}`,
        "x-pd-project-id": process.env.PIPEDREAM_PROJECT_ID!,
        "x-pd-environment": "production",
        "x-pd-external-user-id": "{external_user_id}", // any stable ID for this user in your system
        "x-pd-app-slug": "replicate",
      },
    },
  },
)

const mcp = new Client({ name: "my-agent", version: "1.0.0" })
await mcp.connect(transport)

const { tools } = await mcp.listTools()

// listTools() hands your model this tool's input schema, so it can
// fill the arguments itself:
const result = await mcp.callTool({
  name: "replicate-create-prediction",
  arguments: {
    collectionSlug: "Collection Id",
    modelId: "Model Id",
  },
})
```

**TypeScript**

```ts
import { PipedreamClient } from "@pipedream/sdk"

const pd = new PipedreamClient({
  projectId: process.env.PIPEDREAM_PROJECT_ID!,
  clientId: process.env.PIPEDREAM_CLIENT_ID!,
  clientSecret: process.env.PIPEDREAM_CLIENT_SECRET!,
  projectEnvironment: "production",
})

const result = await pd.actions.run({
  id: "replicate-create-prediction",
  externalUserId: "{external_user_id}", // any stable ID for this user in your system
  configuredProps: {
    replicate: { authProvisionId: "apn_xxxxxxx" },
    collectionSlug: "Collection Id",
    modelId: "Model Id",
  },
})

console.log(result)
```

**cURL**

```bash
curl -X POST https://api.pipedream.com/v1/connect/{project_id}/actions/run \
  -H "Content-Type: application/json" \
  -H "X-PD-Environment: production" \
  -H "Authorization: Bearer {access_token}" \
  -d '{
    "external_user_id": "{external_user_id}",
    "id": "replicate-create-prediction",
    "configured_props": {
      "replicate": { "authProvisionId": "apn_xxxxxxx" },
      "collectionSlug": "Collection Id",
      "modelId": "Model Id"
    }
  }'
```

---

- App: https://pipedream.com/apps/replicate.md · All apps: https://pipedream.com/apps