Skip to content
Codemetry

Google AI

Google’s Gemini models offer strong reasoning capabilities with good integration into Google Cloud environments.

Setup

  1. Get an API Key

    Visit aistudio.google.com/apikey to create an API key.

    Alternatively, use Google Cloud’s Vertex AI for enterprise deployments.

  2. Set Environment Variable

    Terminal window
    export GOOGLE_AI_API_KEY=AIza...

    Or add to your .env file:

    GOOGLE_AI_API_KEY=AIza...

  3. Configure Codemetry

    config/codemetry.php
    'ai' => [
        'enabled' => true,
        'engine' => 'google',
        'model' => null,  // Uses gemini-1.5-flash by default
    ],

  4. Run Analysis

    Terminal window
    php artisan codemetry:analyze --days=7 --ai=1 --ai-engine=google

Available Models

ModelDefaultCostQualitySpeed
gemini-1.5-flash✓LowGoodVery Fast
gemini-1.5-proMediumExcellentMedium
gemini-2.0-flash-expLowBetterVery Fast

Choosing a Model

For routine analysis: Use gemini-1.5-flash (default)

  • Very fast response times
  • Cost-effective
  • Good quality for metric explanations

For detailed investigation: Use gemini-1.5-pro

  • Better reasoning capabilities
  • More thorough explanations
  • Worth the extra cost for deep dives

For experimental features: Use gemini-2.0-flash-exp

  • Latest capabilities
  • May have improved quality
  • Subject to change as it’s experimental
Terminal window
# Override model for single run
php artisan codemetry:analyze --days=7 --ai=1 --ai-engine=google --ai-model=gemini-1.5-pro

Or in configuration:

'ai' => [
    'engine' => 'google',
    'model' => 'gemini-1.5-pro',
],

API Key Options

Codemetry checks for API keys in this order:

  1. CODEMETRY_AI_API_KEY — Unified key for any engine
  2. GOOGLE_AI_API_KEY — Google AI-specific key
Terminal window
# Option 1: Unified
export CODEMETRY_AI_API_KEY=AIza...


# Option 2: Engine-specific
export GOOGLE_AI_API_KEY=AIza...

Cost Management

Google AI Studio offers generous free tiers and competitive pricing:

Free Tier (AI Studio):

  • 15 requests per minute for Flash models
  • 2 requests per minute for Pro models
  • No cost for moderate usage

Estimated costs per 30-day analysis (beyond free tier):

ModelInputOutputTotal
gemini-1.5-flash~$0.002~$0.003~$0.005
gemini-1.5-pro~$0.01~$0.03~$0.04

Google Cloud Integration

For enterprise deployments, consider using Vertex AI:

  1. Enable Vertex AI API in Google Cloud Console
  2. Set up authentication (service account or ADC)
  3. Use Vertex AI endpoints instead of AI Studio

This provides:

  • Enterprise SLAs
  • VPC integration
  • Compliance certifications
  • Centralized billing

Troubleshooting

”Invalid API key”

Cause: API key is incorrect or not enabled.

Solution:

”Quota exceeded”

Cause: Free tier limits reached.

Solution:

  • Wait for quota reset (resets periodically)
  • Enable billing for higher limits
  • Use Flash models for lower quota consumption

”Model not found”

Cause: Model name incorrect or model deprecated.

Solution:

  • Check current model names in Google AI documentation
  • Model names may change as versions update
  • Use a different model variant

”Region not supported”

Cause: Google AI not available in your region.

Solution:

  • Check Google AI availability for your region
  • Consider using a VPN for development
  • Use a different AI engine

Slow Responses with Pro Model

Symptom: gemini-1.5-pro takes longer than expected.

Solution:

  • This is normal; Pro models prioritize quality over speed
  • Use gemini-1.5-flash for faster responses
  • Consider Pro only for detailed investigations