API Release Notes

Released support for the Embeddings model in Batch API, and added Batch API to the OpenAI compatibility library.

Launched Veo 3 and Veo 3 Fast as GA with lower pricing and new options for aspect ratios, resolution, and seeding. See Veo documentation.

Launched Gemini 2.5 Image Preview, the latest native image generation model.

Released URL context tool to general availability (GA). Support for using URL context with the gemini-2.0-flash model (available during experimental release) will be discontinued in one week.

Released Imagen 4 Ultra, Standard, and Fast models as generally available (GA). See the Imagen page.

allow_adult setting in Image to Video generation is now available in restricted regions. See the Veo page for details.

• Launched image-to-video generation for the Veo 3 Preview model.
• Released Veo 3 Fast Preview model.

See the Veo page for more details.

Released gemini-2.5-flash-lite, a fast, low-cost, high-performance Gemini 2.5 model. See Gemini 2.5 Flash-Lite.

• Launched veo-3.0-generate-preview, the latest Veo update introducing video with audio generation. See the Veo page.
• Increased rate limits for Imagen 4 Standard and Ultra. See Rate limits.

Released gemini-embedding-001, the stable version of our text embedding model. See Embeddings. The gemini-embedding-exp-03-07 model will be deprecated on August 14, 2025.

Launched Gemini API Batch Mode. Batch up requests and send them to process asynchronously. See Batch Mode.

• gemini-2.5-pro-preview-05-06 and gemini-2.5-pro-preview-03-25 now redirect to the stable version gemini-2.5-pro.
• gemini-2.5-pro-exp-03-25 is shut down.

Released Imagen 4 Ultra and Standard Preview models. See the Image generation page.

• Released gemini-2.5-pro, the stable version of the most powerful model, with adaptive thinking. See Gemini 2.5 Pro and Thinking. gemini-2.5-pro-preview-05-06 will redirect to gemini-2.5-pro on June 26, 2025.
• Released gemini-2.5-flash, the first stable 2.5 Flash model. See Gemini 2.5 Flash. gemini-2.5-flash-preview-04-17 will be deprecated July 15, 2025.
• Released gemini-2.5-flash-lite-preview-06-17, a low-cost, high-performance model. See Gemini 2.5 Flash-Lite Preview.

Released gemini-2.5-pro-preview-06-05, a new version of the most powerful model with adaptive thinking. See Gemini 2.5 Pro Preview and Thinking. gemini-2.5-pro-preview-05-06 will redirect to gemini-2.5-pro on June 26, 2025.

The last available tuning model, Gemini 1.5 Flash 001, has been shut down. Tuning is no longer supported on any models. See Fine tuning with the Gemini API.

API updates:

• Launched support for custom video preprocessing using clipping intervals and configurable frame rate sampling.
• Launched multi-tool use, supporting code execution and Grounding with Google Search in the same generateContent request.
• Launched support for asynchronous function calls in the Live API.
• Launched an experimental URL context tool.

Model updates:

• Released gemini-2.5-flash-preview-05-20, optimized for price-performance and adaptive thinking.
• Released gemini-2.5-pro-preview-tts and gemini-2.5-flash-preview-tts for speech generation with one or two speakers.
• Released lyria-realtime-exp for real-time music generation.
• Released gemini-2.5-flash-preview-native-audio-dialog and gemini-2.5-flash-exp-native-audio-thinking-dialog for the Live API with native audio output.
• Released gemma-3n-e4b-it preview as part of the Gemma 3n launch.

Released gemini-2.0-flash-preview-image-generation, a preview model for generating and editing images. See Image generation and Gemini 2.0 Flash Preview Image Generation.

Released gemini-2.5-pro-preview-05-06, a new version of the most powerful model with improvements in code and function calling. gemini-2.5-pro-preview-03-25 will automatically point to the new version.

Released gemini-2.5-flash-preview-04-17, a Gemini preview model optimized for price-performance and adaptive thinking. See Gemini 2.5 Flash Preview and Thinking.