API Release Notes

The gemini-robotics-er-1.5-preview model has been shut down. Use gemini-robotics-er-1.6-preview instead.

Released gemini-embedding-2 as generally available (GA). See the Embeddings page for more details.

Released new versions of the Deep Research agent with collaborative planning, visualization support, MCP server integration, and File Search:

• deep-research-preview-04-2026: Designed for speed and efficiency, ideal to be streamed back to a client UI.
• deep-research-max-preview-04-2026: Maximum comprehensiveness for automated context gathering and synthesis.

Launched Gemini 3.1 Flash TTS Preview, a cost-efficient, expressive, and steerable text-to-speech model. See the Text-to-Speech docs for more.

Released gemini-robotics-er-1.6-preview, an updated robotics model with new capabilities including instrument reading and improved spatial and physical reasoning. See the Gemini Robotics-ER page and the blog.

Deprecation: gemini-robotics-er-1.5-preview will be shut down April 30, 2026.

Released gemma-4-26b-a4b-it and gemma-4-31b-it, available on AI Studio and through the Gemini API, as part of the Gemma 4 launch.

Introduced the new Flex and Priority inference tiers, offering more options for optimizing cost or latency.

• Launched Veo 3.1 Lite Preview, veo-3.1-lite-generate-preview, the most cost-efficient video generation model for rapid iteration and high-volume applications.
• The gemini-2.5-flash-lite-preview-09-2025 model has been shut down. Use gemini-3.1-flash-lite-preview instead.

Released gemini-3.1-flash-live-preview, the latest audio-to-audio (A2A) model designed for real-time dialogue and voice-first AI applications. See the Live API docs to get started.

Launched Lyria 3 music generation models:

• lyria-3-clip-preview: 30-second clips
• lyria-3-pro-preview: Full-length songs

Both models accept text and image inputs and generate high-quality 48kHz stereo audio. See the Music generation guide for details.

Rolled out Prepay and Postpay billing plans in AI Studio. Existing accounts may be affected; read the Billing documentation for more information.

Rolled out Prepay and Postpay billing plans in AI Studio. Existing accounts may be affected; read the Billing documentation for more information.

Released the new Built-in Tools and Function Calling Combination feature, making it possible to use Gemini's built-in tools alongside custom function calling tools in a single API call.

Grounding with Google Maps is now supported for Gemini 3 models going forward.

• Released the new Built-in Tools and Function Calling Combination feature, enabling use of Gemini's built-in tools alongside custom function calling tools in a single API call.
• Grounding with Google Maps is now supported for Gemini 3 models.

Introduced revamped Usage Tiers and Billing Account spend caps for a better user billing experience.

Introduced revamped Usage Tiers and Billing Account spend caps for a better user billing experience.

Introduced project-level spend caps to billing in AI Studio.

Introduced project-level spend caps to billing in AI Studio.

Released gemini-embedding-2-preview, the first multimodal embedding model. It supports text, image, video, audio, and PDF inputs, mapping all modalities into a unified embedding space.

Deprecation: The gemini-2.5-flash-lite-preview-09-2025 model will be shut down on March 31, 2026.

• Released gemini-embedding-2-preview, the first multimodal embedding model. Supports text, image, video, audio, and PDF inputs in a unified embedding space. See Embeddings.
• Deprecation: gemini-2.5-flash-lite-preview-09-2025 will be shut down March 31, 2026.