Gemini hosted APIs and Gemma open-weight models. Keep the product families, licenses and API formats separate.
Official documentation ↗A September 2026 generally available Gemini release for software engineering, agents and enterprise workflows.
The provider announcement describes intended uses, not an independent result in your application. Check accepted inputs, thinking controls and current pricing on the selected Gemini endpoint.
An October 2026 image generation and conversational editing model in the Gemini family.
Use image-specific quality criteria. The announcement supports wide and panoramic aspect ratios at 1K, 2K and 4K; output quality and billing still need checks on the real endpoint.
An instruction-tuned open-weight model with text and image inputs.
Gemma and Gemini are separate products. Check Gemma license terms and the runtime used for image inputs.
A hosted Gemini thinking model for complex and multimodal tasks.
Gemini API formats and thinking controls differ from other providers. Check current pricing and availability directly.
The publisher identifies the model family or checkpoint. An inference operator selects a runtime, quantization and service configuration. The API endpoint defines the accepted request shape and operational limits. Compare all three when planning a migration.
Official release notes can announce previews, general availability, retirement and alias changes. A model appearing in an API list is an observation of access, not necessarily a new public release.
Open the release radar →