> ## Documentation Index
> Fetch the complete documentation index at: https://cerebrium-kyle-phase0-docs-fixes.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Cerebrium's documentation MCP server is available at https://cerebrium.ai/docs/mcp for searching and querying these docs directly. Install the Cerebrium agent skill with `npx skills add https://cerebrium.ai/docs`. Append .md to any docs page URL to fetch that page as plain Markdown. API keys and authentication tokens are created in the Cerebrium dashboard at https://dashboard.cerebrium.ai.

# Run App

> Execute code on a deployed app.



## OpenAPI

````yaml https://s3.eu-west-1.amazonaws.com/www.cerebrium.ai/openapi_spec.json post /v3/projects/{project_id}/apps/{app_id}/run
openapi: 3.0.0
info:
  title: Cerebrium REST API
  description: >-
    REST API for interacting with Cerebrium. This API is mainly used by the
    Cerebrium CLI client, please run `pip install cerebrium` to install it.
  version: 1.0.0
  license:
    name: Proprietary
    url: https://www.cerebrium.ai/terms-of-service
servers:
  - url: https://rest.cerebrium.ai
security: []
paths:
  /v3/projects/{project_id}/apps/{app_id}/run:
    post:
      tags:
        - Cerebrium Run
      summary: Run App
      description: Execute code on a deployed app.
      operationId: runCommand
      parameters:
        - name: project_id
          in: path
          required: true
          schema:
            type: string
        - name: app_id
          in: path
          required: true
          schema:
            type: string
        - name: appName
          in: query
          required: true
          description: Name of the app to run against
          schema:
            type: string
        - name: filename
          in: query
          required: true
          description: Path of the Python file to execute. Must have a .py extension
          schema:
            type: string
        - name: functionName
          in: query
          required: false
          description: Name of the function to call within the file
          schema:
            type: string
        - name: computeType
          in: query
          required: false
          description: >-
            Compute type to run on. One of ADA_L4, ADA_L40, AMPERE_A10,
            AMPERE_A100_40GB, AMPERE_A100_80GB, HOPPER_H100, CPU, INF2, TRN1,
            TURING_T4. Defaults to CPU
          schema:
            type: string
        - name: cpu
          in: query
          required: false
          description: Number of CPU cores (0.1-12). Defaults to 2
          schema:
            type: number
        - name: memoryGb
          in: query
          required: false
          description: Memory in GB (0.5-64). Defaults to 2
          schema:
            type: number
        - name: gpuCount
          in: query
          required: false
          description: Number of GPUs (0-8). Defaults to 0
          schema:
            type: integer
        - name: imageDigest
          in: query
          required: false
          description: >-
            Base image digest to run on, as returned by the base-image endpoint.
            Defaults to the standard Python base image
          schema:
            type: string
        - name: region
          in: query
          required: false
          description: Region to run in. Defaults to the app's deployed region
          schema:
            type: string
      requestBody:
        required: true
        content:
          application/json:
            schema:
              properties:
                data:
                  description: >-
                    Multipart form field containing a JSON string of arguments
                    passed to the function
                  type: string
                file:
                  description: >-
                    Multipart form field containing a tar archive of the code
                    files to run
                  type: string
              required:
                - file
              type: object
      responses:
        '200':
          description: >-
            Details of the run that was created. Run output is not returned by
            this endpoint; it is delivered asynchronously via the run's logs.
          content:
            application/json:
              schema:
                properties:
                  message:
                    description: Human-readable confirmation message.
                    type: string
                  runId:
                    description: Unique identifier of the created run.
                    type: string
                type: object
        '400':
          description: >-
            Bad request. The request was malformed or contained invalid
            parameters.
          content:
            application/json:
              schema:
                properties:
                  message:
                    description: Human-readable description of the error.
                    type: string
                type: object
        '401':
          description: >-
            Unauthorized. The Authorization header is missing or the token is
            invalid.
          content:
            application/json:
              schema:
                properties:
                  message:
                    description: Human-readable description of the error.
                    type: string
                type: object
      security:
        - BearerAuth: []
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: >-
        Service Account Token authentication. To authenticate API requests:


        1. **Create a Service Account Token:**
           - Go to the [Cerebrium Dashboard](https://dashboard.cerebrium.ai/) and open the **API Keys** page
           - Click **Create Service Account**, name it (e.g., "GitHub Actions CI/CD"), choose an expiry date, and click **Create**
           - **Copy the token** generated for the desired service account

        2. **Use the Token:**
           Include the service account token in the Authorization header of API requests:
           `Authorization: Bearer <your-service-account-token>`

        3. **Best Practices:**
           - Create separate service accounts for different environments (dev, staging, prod)
           - Store tokens securely as secrets in consuming applications or workflows
           - Set appropriate expiry dates and rotate tokens regularly
           - Never commit tokens to source control

        For CI/CD integration examples, see the [CI/CD
        documentation](https://docs.cerebrium.ai/cerebrium/deployments/ci-cd).

````