API Release Notes

The Gemini 3 Pro Preview model has been shut down. The gemini-3-pro-preview now points to gemini-3.1-pro-preview.

The Gemini 3 Pro Preview model has been shut down. The gemini-3-pro-preview alias now points to gemini-3.1-pro-preview.

Launched Gemini 3.1 Flash-Lite Preview, the first Flash-Lite model in the Gemini 3 series. See the model page for specs and developer guidance.

Launched Nano Banana 2, Gemini 3.1 Flash Image Preview, a high-efficiency model optimized for speed and high-volume use cases.

Deprecation: Gemini 3 Pro Preview (gemini-3-pro-preview) will be shut down March 9, 2026.

• Launched Nano Banana 2, Gemini 3.1 Flash Image Preview, a high-efficiency model optimized for speed and high-volume use cases.
• Deprecation: Gemini 3 Pro Preview (gemini-3-pro-preview) will be shut down March 9, 2026.

• Released Gemini 3.1 Pro Preview, the latest iteration in the Gemini 3 series family.
• Launched a separate endpoint gemini-3.1-pro-preview-customtools, which is better at prioritizing custom tools.

Deprecation announcement: The following models will be shut down June 1, 2026:

• gemini-2.0-flash
• gemini-2.0-flash-001
• gemini-2.0-flash-lite
• gemini-2.0-flash-lite-001

The following models are shut down:

• gemini-2.5-flash-preview-09-25
• imagen-4.0-generate-preview-06-06
• imagen-4.0-ultra-generate-preview-06-06

Launched support for the Computer Use tool in gemini-3-pro-preview and gemini-3-flash-preview.

Changed the latest aliases:

• gemini-pro-latest switched to gemini-3-pro-preview
• gemini-flash-latest switched to gemini-3-flash-preview

• Deprecation: The following models will be shut down February 17, 2026:
  • gemini-2.5-flash-preview-09-25
  • imagen-4.0-generate-preview-06-06
  • imagen-4.0-ultra-generate-preview-06-06
• gemini-2.5-flash-image-preview has been shut down.

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 Model stages for details.

Launched support for Cloud Storage buckets and public/private DB pre-signed URLs as data input sources for the Gemini API. The file size limit has increased from 20MB to 100MB. See the File input methods guide.

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 rivaling larger models at a fraction of the cost. Includes upgraded visual/spatial reasoning and agentic coding capabilities. New features include:

• 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 with improved handling of complex workflows. See the Live API guide and Gemini 2.5 Flash Native Audio.

• Launched the Interactions API in Beta, providing a unified interface for interacting with Gemini models and agents. 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.

Launched enhancements to text-to-speech models, including Gemini 2.5 Flash TTS Preview (low latency) and Gemini 2.5 Pro TTS Preview (quality), with enhanced expressivity, precision pacing, and seamless dialogue.