Gemini API Release Notes

• The text-embedding-004 model has been shut down.

• Added 4k output resolutions for Veo and more support for portrait videos in all resolutions.

• Launched model lifecycle feature. Some models will now specify the lifecycle stage and deprecation timeline. See the following documentation for more information:

  • Model stages

• Launched support for Cloud Storage buckets and any public and private DB pre-signed URL as data input source for the Gemini API. The file size limit has also increased from 20MB to 100MB. For details, see File input methods guide.

Breaking Changes

• Introduced a breaking change to the Interactions API public preview in v1beta. The total_reasoning_tokens field has been renamed to total_thought_tokens to better align with the concept of "thoughts" in thinking models.

• Launched Gemini 3 Flash Preview, gemini-3-flash-preview, delivering fast frontier-class performance that rivals larger models at a fraction of the cost. With upgraded visual and spatial reasoning, and agentic coding capabilities. Read the documentation on some new features, including:
  • Multimodal function responses
  • Code execution with images

• Released gemini-2.5-flash-native-audio-preview-12-2025, a new native audio model for the Live API. This update improves the model's ability to handle complex workflows. To learn more, see the Live API guide and Gemini 2.5 Flash Native Audio.

• Launched the Interactions API in Beta. This API provides a unified interface for interacting with Gemini models and agents. To learn more, see the Interactions API guide.

• Launched the Gemini Deep Research Agent in preview. It can autonomously plan, execute, and synthesize results for multi-step research tasks. See the Deep Research guide for details.

• Launched enhancements to our text-to-speech models, Gemini 2.5 Flash TTS preview (optimized for low latency) and Gemini 2.5 Pro TTS preview (optimized for quality), including enhanced expressivity, precision pacing, and seamless dialogue.

Gemini Live API models shutdown

• The following Gemini Live API models are now shut down:
  • gemini-2.0-flash-live-001
  • gemini-live-2.5-flash-preview