Skip to main content
Shannon supports Google Vertex AI as an alternative to using Anthropic API keys directly.

​
Setup Instructions

1

Create a GCP service account

  1. Navigate to the GCP Console
  2. Create a service account with the roles/aiplatform.user role
  3. Download the JSON key file for the service account
2

Place the key file in the credentials directory

mkdir -p ./credentials
cp /path/to/your-sa-key.json ./credentials/gcp-sa-key.json
3

Add GCP configuration to .env

Create or edit your .env file:
CLAUDE_CODE_USE_VERTEX=1
CLOUD_ML_REGION=us-east5
ANTHROPIC_VERTEX_PROJECT_ID=your-gcp-project-id
GOOGLE_APPLICATION_CREDENTIALS=./credentials/gcp-sa-key.json

# Set models with Vertex AI model IDs
ANTHROPIC_SMALL_MODEL=claude-haiku-4-5@20251001
ANTHROPIC_MEDIUM_MODEL=claude-sonnet-4-6
ANTHROPIC_LARGE_MODEL=claude-opus-4-6
4

Run Shannon

Run Shannon as usual — it will automatically use Vertex AI:
./shannon start URL=https://example.com REPO=repo-name

​
Environment Variables

VariableRequiredDescription
CLAUDE_CODE_USE_VERTEXYesSet to 1 to enable Vertex AI mode
CLOUD_ML_REGIONYesGCP region (e.g., us-east5) or global
ANTHROPIC_VERTEX_PROJECT_IDYesYour GCP project ID
GOOGLE_APPLICATION_CREDENTIALSYesPath to service account JSON key file
ANTHROPIC_SMALL_MODELYesVertex AI model ID for small tasks (Haiku)
ANTHROPIC_MEDIUM_MODELYesVertex AI model ID for medium tasks (Sonnet)
ANTHROPIC_LARGE_MODELYesVertex AI model ID for large tasks (Opus)

​
Model Tiers

Shannon uses three model tiers optimized for different tasks:
  • Small (claude-haiku-4-5@20251001) — Used for summarization and lightweight tasks
  • Medium (claude-sonnet-4-6) — Used for security analysis and vulnerability detection
  • Large (claude-opus-4-6) — Used for deep reasoning and complex exploitation

​
Region Configuration

  • Set CLOUD_ML_REGION=global for global endpoints
  • Or use a specific region like us-east5 for regional endpoints
Some models may not be available on global endpoints. Check the Vertex AI Model Garden for region availability.

​
Service Account Permissions

Your service account needs the following IAM role:
  • roles/aiplatform.user — Required for accessing Vertex AI models
To assign this role:
  1. Go to the IAM page in GCP Console
  2. Find your service account
  3. Click “Edit”
  4. Add the AI Platform User role
  5. Save changes

​
Example Configuration

Here’s a complete .env example for Google Vertex AI: 
# Google Vertex AI Configuration
CLAUDE_CODE_USE_VERTEX=1
CLOUD_ML_REGION=us-east5
ANTHROPIC_VERTEX_PROJECT_ID=my-gcp-project
GOOGLE_APPLICATION_CREDENTIALS=./credentials/gcp-sa-key.json

# Model Configuration
ANTHROPIC_SMALL_MODEL=claude-haiku-4-5@20251001
ANTHROPIC_MEDIUM_MODEL=claude-sonnet-4-6
ANTHROPIC_LARGE_MODEL=claude-opus-4-6

# Optional: Increase output tokens for better results
CLAUDE_CODE_MAX_OUTPUT_TOKENS=64000

Build docs developers (and LLMs) love

Get started for freeTalk to us