Features
Access to PaLM 2 and Gemini models
Text generation and completion
Classification and sentiment analysis
Code generation and explanation
Chat and conversational AI
Safety controls and content filtering
Integration with Google Cloud and Workspace
MakerSuite prototyping environment
Support for fine-tuning with custom data
Scalable via Google Cloud infrastructure
Unified API for 400+ models across 70+ providers
Automatic failover routing when a provider goes down
Model Fusion: combine budget models to rival frontier performance
Subagent delegation: frontier models hand off tasks to cheaper workers
Speech/transcription APIs (May 2026)
Unified Image API with capability discovery across 30+ models (June 2026)
OpenAI SDK compatible out of the box
Server-side presets to survive model deprecation
Edge-deployed for minimal latency
Budget controls and spend limits
Credit-based pricing with no subscriptions
Model routing visualization for latency and cost
Private model support for enterprise deployments
Data policy-based routing and enforcement
MCP server for coding agents (June 2026)
