2026.07 Deprecation announcement · 2026-07-30

Deprecation announcement: The gemini-robotics-er-1.6-preview model will be shut down on August 31, 2026.

2026.07 Gemini 3.6 Flash and Gemini 3.5 Flash-Lite... · 2026-07-21

Gemini 3.6 Flash and Gemini 3.5 Flash-Lite generally available (GA): Released stable, production-ready versions of our latest 3.x Flash models: - Gemini 3.6 Flash (gemini-3.6-flash): Features improved token efficiency and code/agentic planning capabilities at a lower price point than 3.5 Flash, resolving developer feedback around output verbosity. - Gemini 3.5 Flash-Lite (gemini-3.5-flash-lite): Offers a...

2026.07 Deprecated parameters · 2026-07-21

Deprecated parameters: The sampling parameters temperature, top_p and top_k are now deprecated. See the Latest Gemini Model for details.

2026.07 Developer logs support for the Interactions API:... · 2026-07-06

Developer logs support for the Interactions API: logs for supported Interactions API calls are now viewable in the AI Studio dashboard.

2026.06 Gemini Omni Flash in public preview · 2026-06-30

Gemini Omni Flash in public preview: Released gemini-omni-flash-preview, a high-performance multimodal model designed for high-speed video generation and conversational video editing. Using the Interactions API, you can generate 3–10 second videos at 720p from text descriptions or animate still images, and then conversationally edit and refine the outputs. To get started, see the Gemini Omni Flash guide and the...

2026.06 Released gemini-3.1-flash-lite-image (Nano Banana 2... · 2026-06-30

Released gemini-3.1-flash-lite-image (Nano Banana 2 Lite) to general availability (GA), our built-in multimodal model optimized for ultra-low latency and cost-effective image generation and editing. See the Gemini 3.1 Flash Lite Image model card and the Image generation guide.

2026.06 Computer Use · 2026-06-24

Computer Use: Launched public preview support for the Computer Use tool in Gemini 3.5 Flash. This release includes simplified actions with intents, built-in support for browser, mobile, and desktop environments, configurable safety policies, and advanced prompt injection detection.

2026.06 Streaming support for speech generation · 2026-06-17

Streaming support for speech generation: Streaming via streamGenerateContent (and stream: true in the Interactions API) is now supported for the gemini-3.1-flash-tts-preview model. To learn more, see the Text-to-Speech guide.

2026.06 Deprecation announcement · 2026-06-15

Deprecation announcement: The following image generation models are being deprecated and will be shut down on August 17, 2026: - Imagen 4 and Gemini 3 Image models: - imagen-4.0-generate-001 - imagen-4.0-ultra-generate-001 - imagen-4.0-fast-generate-001 To migrate your code to newer stable or preview endpoints, refer to the Gemini deprecations page.

2026.06 Deprecation announcement · 2026-06-15

Deprecation announcement: The following video generation models are being deprecated and will be shut down on June 30, 2026: - Veo models: - veo-2.0-generate-001 - veo-3.0-generate-001 - veo-3.0-fast-generate-001 Update your integration to either use the Veo 3.1 preview model IDs (veo-3.1-generate-preview, veo-3.1-fast-generate-preview) or the 3.1 GA models available through the Gemini Enterprise Agent Platform...

2026.06 Deprecation announcement · 2026-06-15

Deprecation announcement: The experimental GMP Contextual View tool (a fixed interface for Grounding with Google Maps outputs) will shut down on June 15, 2026

2026.06 The following Gemini 2.0 models are now shut down · 2026-06-01

The following Gemini 2.0 models are now shut down: - gemini-2.0-flash - gemini-2.0-flash-001 - gemini-2.0-flash-lite - gemini-2.0-flash-lite-001 Use gemini-3.5-flash or gemini-3.1-flash-lite instead.

2026.05 Released gemini-3.1-flash-image (Nano Banana 2) and... · 2026-05-28

Released gemini-3.1-flash-image (Nano Banana 2) and gemini-3-pro-image (Nano Banana Pro), the generally available (GA) versions of our native visual models, Gemini 3.1 Flash Image and Gemini 3 Pro Image.

2026.05 Video-to-image generation support · 2026-05-28

Video-to-image generation support: You can now pass a video file (via direct upload or as a public YouTube URL) as multimodal context alongside a text prompt to generate high-quality thumbnails, cinematic movie posters, or summary infographics. This feature is supported exclusively on the gemini-3.1-flash-image model. To learn more, see the Video-to-image generation guide.

2026.05 Deprecation announcement: The... · 2026-05-28

Deprecation announcement: The gemini-3.1-flash-image-preview and gemini-3-pro-image-preview models are deprecated and will be shut down on June 25, 2026.

2026.05 The gemini-3.1-flash-lite-preview model has been... · 2026-05-25

The gemini-3.1-flash-lite-preview model has been shut down. Use gemini-3.1-flash-lite instead.

2026.05 Released gemini-3.5-flash, the generally available... · 2026-05-19

Released gemini-3.5-flash, the generally available (GA) version of Gemini 3.5 Flash, our most intelligent model for sustained frontier performance on agentic and coding tasks. This is now the model behind gemini-flash-latest.

2026.05 Launched the Managed Agents in the Gemini API in... · 2026-05-19

Launched the Managed Agents in the Gemini API in public preview. This enables developers to build and deploy autonomous, stateful agents that run in secure, isolated Google-hosted Linux sandbox environments. To learn more, see the Agents overview page and the Quickstart.

2026.05 Released the general-purpose Antigravity Agent... · 2026-05-19

Released the general-purpose Antigravity Agent managed agent, antigravity-preview-05-2026, in public preview. The Antigravity agent can autonomously plan, reason, write and execute code, manage files, and browse the web inside its sandbox container. See the Antigravity Agent guide for code samples and specifications.

2026.05 Released gemini-3.1-flash-lite, the generally... · 2026-05-07

Released gemini-3.1-flash-lite, the generally available (GA) version of Gemini 3.1 Flash-Lite, optimized for speed, scale, and cost efficiency.

2026.05 Deprecation announcement: The... · 2026-05-07

Deprecation announcement: The gemini-3.1-flash-lite-preview model is deprecating on 5/11/26 and will be shut down on May 25, 2026.

2026.05 Upcoming breaking change · 2026-05-06

Upcoming breaking change: The Interactions API request and response schema (outputs → steps) and output format configuration (response_format) are changing. The new schema becomes the default on May 26 and the legacy schema will be removed on June 8. See the migration guide for details.

2026.05 Updated File Search to support multimodal search · 2026-05-05

Updated File Search to support multimodal search. You can now natively embed and search through images using the gemini-embedding-2 model. Grounding metadata now includes media_id for visual citations and page_numbers that indicate where information is found. To learn more, see the File Search guide.

2026.05 Launched event-driven Webhooks support in the... · 2026-05-04

Launched event-driven Webhooks support in the Gemini API to replace polling workflows for the Batch API and long-running operations.

2026.04 The gemini-robotics-er-1.5-preview model has been... · 2026-04-30

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

2026.04 Released gemini-embedding-2 as generally available... · 2026-04-22

Released gemini-embedding-2 as generally available (GA). To learn more, see the Embeddings page.

2026.04 Released new versions of the Deep Research agent... · 2026-04-21

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.

2026.04 Launched Gemini 3.1 Flash TTS Preview, our... · 2026-04-15

Launched Gemini 3.1 Flash TTS Preview, our cost-efficient, expressive, and steerable text to speech model. Read the Text-to-Speech docs to learn more.

2026.04 Released gemini-robotics-er-1.6-preview, our... · 2026-04-14

Released gemini-robotics-er-1.6-preview, our updated robotics model. It now has new capabilities like instrument reading, improved spatial and physical reasoning capabilities. To learn more, see Gemini Robotics ER page and the blog.

2026.04 Deprecation announcement: The... · 2026-04-14

Deprecation announcement: The gemini-robotics-er-1.5-preview model will be shut down on April 30, 2026 at 9AM PST.

2026.04 Released gemma-4-26b-a4b-it and gemma-4-31b-it,... · 2026-04-02

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.

2026.04 Introduced the new Flex and Priority inference... · 2026-04-01

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

2026.03 Launched Veo 3.1 Lite Preview,... · 2026-03-31

Launched Veo 3.1 Lite Preview, veo-3.1-lite-generate-preview, our most cost-efficient video generation model, designed for rapid iteration and building high-volume applications.

2026.03 The gemini-2.5-flash-lite-preview-09-2025 model has... · 2026-03-31

The gemini-2.5-flash-lite-preview-09-2025 model has been shut down. Use gemini-3.1-flash-lite-preview instead.

2026.03 Released gemini-3.1-flash-live-preview, the latest... · 2026-03-26

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

2026.03 Launched Lyria 3 music generation models:... · 2026-03-25

Launched Lyria 3 music generation models: lyria-3-clip-preview (30-second clips) and 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 and code samples.

2026.03 Rolled out Prepay and Postpay billing plans in AI... · 2026-03-23

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

2026.03 Released the new Built-in Tools and Function... · 2026-03-18

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.

2026.03 Grounding with Google Maps is now supported for... · 2026-03-18

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

2026.03 Introduced revamped Usage Tiers and Billing Account... · 2026-03-16

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

2026.03 Introduced project-level spend caps to billing in... · 2026-03-12

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

2026.03 Released gemini-embedding-2-preview, our first... · 2026-03-10

Released gemini-embedding-2-preview, our first multimodal embedding model. It supports text, image, video, audio, and PDF inputs, mapping all modalities into a unified embedding space. To learn more, see Embeddings.

2026.03 Deprecation announcement: The... · 2026-03-10

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

2026.03 The Gemini 3 Pro Preview model has been shut down · 2026-03-09

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

2026.03 Launched Gemini 3.1 Flash-Lite Preview, the first... · 2026-03-03

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

2026.02 Launched Nano Banana 2, Gemini 3.1 Flash Image... · 2026-02-26

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

2026.02 Deprecation announcement: Gemini 3 Pro Preview... · 2026-02-26

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

2026.02 Released Gemini 3.1 Pro Preview, our latest... · 2026-02-19

Released Gemini 3.1 Pro Preview, our latest iteration in the new Gemini 3 series family.

2026.02 Launched a separate endpoint... · 2026-02-19

Launched a separate endpoint gemini-3.1-pro-preview-customtools, which is better at prioritizing custom tools, for users building with a mix of bash and tools.

2026.02 Deprecation announcement: The following models will... · 2026-02-18

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

2026.02 The following models are shut down · 2026-02-17

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

2026.01 Launched support for the Computer Use tool in... · 2026-01-29

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

2026.01 Changed the latest aliases · 2026-01-21

Changed the latest aliases: - gemini-pro-latest switched to gemini-3-pro-preview - gemini-flash-latest switched to gemini-3-flash-preview

2026.01 Deprecation announcement: The following models will... · 2026-01-15

Deprecation announcement: 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

2026.01 The gemini-2.5-flash-image-preview model has been... · 2026-01-15

The gemini-2.5-flash-image-preview model has been shut down.

2026.01 The text-embedding-004 model has been shut down. · 2026-01-14

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

2026.01 Added 4k output resolutions for Veo and more... · 2026-01-13

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

2026.01 Launched model lifecycle feature · 2026-01-12

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

2026.01 Launched support for Cloud Storage buckets and any... · 2026-01-08

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.

2025.12 Introduced a breaking change to the Interactions... · 2025-12-19

Introduced a breaking change to the Interactions API 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.

2025.12 Launched Gemini 3 Flash Preview,... · 2025-12-17

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

2025.12 Released... · 2025-12-12

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.

2025.12 Launched the Interactions API · 2025-12-11

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

2025.12 Launched the Gemini Deep Research agent in preview · 2025-12-11

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.

2025.12 Launched enhancements to our text-to-speech models,... · 2025-12-10

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.

2025.12 The following Gemini Live API models are now shut down · 2025-12-09

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

2025.12 Gemini 3 billing for Grounding with Google Search... · 2025-12-05

Gemini 3 billing for Grounding with Google Search will begin on January 5, 2026.

2025.12 Deprecation announcement: The... · 2025-12-04

Deprecation announcement: The gemini-2.5-flash-image-preview model will be shut down January 15, 2026.

2025.12 Deprecation announcement: The text-embedding-004... · 2025-12-03

Deprecation announcement: The text-embedding-004 model will be shut down January 14, 2026.

2025.11 Released Gemini 3 Pro Image Preview,... · 2025-11-20

Released Gemini 3 Pro Image Preview, gemini-3-pro-image-preview, the next iteration to the Nano Banana model. Read the Image generation page for more details.

2025.11 Launched the first Gemini 3 series model,... · 2025-11-18

Launched the first Gemini 3 series model, gemini-3-pro-preview, our state-of-the-art reasoning and multimodal understanding model with powerful agentic and coding capabilities. In addition to improvements in intelligence and performance, Gemini 3 Pro Preview introduces new behavior around: - Media resolution - Thought signatures - Thinking levels Read the Gemini 3 Developer Guide for migration, new features, and...

2025.11 Deprecation announcement: The following models will... · 2025-11-11

Deprecation announcement: The following models will be shut down: - November 12: - veo-3.0-fast-generate-preview - veo-3.0-generate-preview - November 14: - gemini-2.0-flash-exp-image-generation - gemini-2.0-flash-preview-image-generation

2025.11 The following model is shut down · 2025-11-10

The following model is shut down: - imagen-3.0-generate-002 Use Imagen 4 instead. Refer to the Gemini deprecations table for more details.

2025.11 Launched the File Search API to public preview,... · 2025-11-06

Launched the File Search API to public preview, enabling developers to ground responses in their own data. Read the new File Search page for more info.

2025.11 For Gemini 2.5 Flash Image, the input token count... · 2025-11-04

For Gemini 2.5 Flash Image, the input token count for images has been reduced from 1290 to 258, lowering the cost of image editing.

2025.11 Deprecation announcement: The following models will... · 2025-11-04

Deprecation announcement: The following models will be shut down: - November 18th: - gemini-2.5-flash-lite-preview-06-17 - gemini-2.5-flash-preview-05-20 - December 2nd: - gemini-2.0-flash-thinking-exp - gemini-2.0-flash-thinking-exp-01-21 - gemini-2.0-flash-thinking-exp-1219 - gemini-2.5-pro-preview-03-25 - gemini-2.5-pro-preview-05-06 - gemini-2.5-pro-preview-06-05 - December 9th: -...

2025.10 Launched the new logging and datasets tool for the... · 2025-10-29

Launched the new logging and datasets tool for the Gemini API.

2025.10 The following Gemini Live API models are now shut down · 2025-10-20

The following Gemini Live API models are now shut down: - gemini-2.5-flash-preview-native-audio-dialog - gemini-2.5-flash-exp-native-audio-thinking-dialog You can use gemini-2.5-flash-native-audio-preview-09-2025 instead.

2025.10 Deprecation announcement: Shut down for... · 2025-10-20

Deprecation announcement: Shut down for gemini-2.0-flash-live-001 and gemini-live-2.5-flash-preview coming December 09, 2025.

2025.10 Grounding with Google Maps is now generally available · 2025-10-17

Grounding with Google Maps is now generally available. For more information, see Grounding with Google Maps documentation.

2025.10 Released Veo 3.1 and 3.1 Fast models in public... · 2025-10-15

Released Veo 3.1 and 3.1 Fast models in public preview, with new features including: - Extending Veo-created videos. - Referencing up to three images to generate a video. - Providing first and last frame images to generate videos from. This launch also added more options for Veo 3 output video durations: 4, 6, and 8 seconds.

2025.10 Deprecation announcement: Shut down for... · 2025-10-15

Deprecation announcement: Shut down for veo-3.0-generate-preview and veo-3.0-fast-generate-preview coming November 12, 2025.

2025.10 Launched Gemini 2.5 Computer Use Preview · 2025-10-07

Launched Gemini 2.5 Computer Use Preview

2025.10 Launched Gemini 2.5 Flash Image GA: Image... · 2025-10-02

Launched Gemini 2.5 Flash Image GA: Image Generation with Gemini

2025.09 The following Gemini 1.5 models are now shut down · 2025-09-29

The following Gemini 1.5 models are now shut down: - gemini-1.5-pro - gemini-1.5-flash-8b - gemini-1.5-flash

2025.09 Released Gemini Robotics ER 1.5 model in preview · 2025-09-25

Released Gemini Robotics ER 1.5 model in preview. See the Robotics overview to learn about how to use the model for your robotics application.

2025.09 Launched following preview models · 2025-09-25

Launched following preview models: - gemini-2.5-flash-preview-09-2025 - gemini-2.5-flash-lite-preview-09-2025 See the Models page for details.

2025.09 Released... · 2025-09-23

Released gemini-2.5-flash-native-audio-preview-09-2025, a new native audio model for the Live API with improved function calling and speech cut off handling. To learn more, see the Live API guide and Gemini 2.5 Flash Native Audio.

2025.09 Deprecation announcement: The following models will... · 2025-09-16

Deprecation announcement: The following models will be shut down in October 2025: - embedding-001 - embedding-gecko-001 - gemini-embedding-exp-03-07 (gemini-embedding-exp) See the Embeddings page for details on the latest embeddings model.

2025.09 Released support for the Embeddings model in Batch... · 2025-09-10

Released support for the Embeddings model in Batch API, and added Batch API to the OpenAI compatibility library for even easier ways to get started with batch queries.

2025.09 Launched Veo 3 and Veo 3 Fast GA, with lower... · 2025-09-09

Launched Veo 3 and Veo 3 Fast GA, with lower pricing and new options for aspect ratios, resolution, and seeding. Read the Veo documentation for more information.

2025.08 Launched Gemini 2.5 Image Preview, our latest... · 2025-08-26

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

2025.08 Released URL context tool to general availability... · 2025-08-18

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

2025.08 Released Imagen 4 Ultra, Standard and Fast models... · 2025-08-14

Released Imagen 4 Ultra, Standard and Fast models as generally available (GA). To learn more, see the Imagen page.

2025.08 allow_adult setting in Image to Video generation... · 2025-08-07

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

2025.07 Launched image-to-video generation for the Veo 3... · 2025-07-31

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

2025.07 Released Veo 3 Fast Preview model. · 2025-07-31

Released Veo 3 Fast Preview model.

2025.07 To learn more about Veo 3, visit the Veo page. · 2025-07-31

To learn more about Veo 3, visit the Veo page.

2025.07 Released gemini-2.5-flash-lite, our fast, low-cost,... · 2025-07-22

Released gemini-2.5-flash-lite, our fast, low-cost, high-performance Gemini 2.5 model. To learn more, see Gemini 2.5 Flash-Lite.

2025.07 Launched veo-3.0-generate-preview, the latest... · 2025-07-17

Launched veo-3.0-generate-preview, the latest update to Veo introducing video with audio generation. To learn more about Veo 3, visit the Veo page.

2025.07 Increased rate limits for Imagen 4 Standard and... · 2025-07-17

Increased rate limits for Imagen 4 Standard and Ultra. Visit the Rate limits page for more details.

2025.07 Released gemini-embedding-001, the stable version... · 2025-07-14

Released gemini-embedding-001, the stable version of our text embedding model. To learn more, see embeddings. The gemini-embedding-exp-03-07 model will be deprecated on August 14, 2025.

2025.07 Launched Gemini API Batch Mode · 2025-07-07

Launched Gemini API Batch Mode. Batch up requests and send them to process asynchronously. To learn more, see Batch Mode.

2025.06 The preview models gemini-2.5-pro-preview-05-06 and... · 2025-06-26

The preview models gemini-2.5-pro-preview-05-06 and gemini-2.5-pro-preview-03-25 are now redirecting to the latest stable version gemini-2.5-pro.

2025.06 gemini-2.5-pro-exp-03-25 is shut down. · 2025-06-26

gemini-2.5-pro-exp-03-25 is shut down.

2025.06 Released Imagen 4 Ultra and Standard Preview... · 2025-06-24

Released Imagen 4 Ultra and Standard Preview models. To learn more, see the Image generation page.

2025.06 Released gemini-2.5-pro, the stable version of our... · 2025-06-17

Released gemini-2.5-pro, the stable version of our most powerful model, now with adaptive thinking. To learn more, see Gemini 2.5 Pro and Thinking. gemini-2.5-pro-preview-05-06 will be redirected to gemini-2.5-pro on June 26, 2025.

2025.06 Released gemini-2.5-flash, our first stable 2.5... · 2025-06-17

Released gemini-2.5-flash, our first stable 2.5 Flash model. To learn more, see Gemini 2.5 Flash. gemini-2.5-flash-preview-04-17 will be deprecated on July 15, 2025.

2025.06 Released gemini-2.5-flash-lite-preview-06-17, a... · 2025-06-17

Released gemini-2.5-flash-lite-preview-06-17, a low-cost, high-performance Gemini 2.5 model. To learn more, see Gemini 2.5 Flash-Lite Preview.

2025.06 Released gemini-2.5-pro-preview-06-05, a new... · 2025-06-05

Released gemini-2.5-pro-preview-06-05, a new version of our most powerful model, now with adaptive thinking. To learn more, see Gemini 2.5 Pro Preview and Thinking. gemini-2.5-pro-preview-05-06 will be redirected to gemini-2.5-pro on June 26, 2025.

2025.05 The last available tuning model, Gemini 1.5 Flash... · 2025-05-27

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.

2025.05 Launched support for custom video preprocessing... · 2025-05-20

Launched support for custom video preprocessing using clipping intervals and configurable frame rate sampling.

2025.05 Launched multi-tool use, which supports configuring... · 2025-05-20

Launched multi-tool use, which supports configuring code execution and Grounding with Google Search on the same generateContent request.

2025.05 Launched support for asynchronous function calls in... · 2025-05-20

Launched support for asynchronous function calls in the Live API.

2025.05 Launched an experimental URL context tool for... · 2025-05-20

Launched an experimental URL context tool for providing URLs as additional context to prompts. Model updates

2025.05 Released gemini-2.5-flash-preview-05-20, a Gemini... · 2025-05-20

Released gemini-2.5-flash-preview-05-20, a Gemini preview model optimized for price-performance and adaptive thinking. To learn more, see Gemini 2.5 Flash Preview and Thinking.

2025.05 Released the gemini-2.5-pro-preview-tts and... · 2025-05-20

Released the gemini-2.5-pro-preview-tts and gemini-2.5-flash-preview-tts models, which are capable of generating speech with one or two speakers.

2025.05 Released the lyria-realtime-exp model, which... · 2025-05-20

Released the lyria-realtime-exp model, which generates music in real time.

2025.05 Released... · 2025-05-20

Released gemini-2.5-flash-preview-native-audio-dialog and gemini-2.5-flash-exp-native-audio-thinking-dialog, new Gemini models for the Live API with native audio output capabilities. To learn more, see the Live API guide and Gemini 2.5 Flash Native Audio.

2025.05 Released gemma-3n-e4b-it preview, available on AI... · 2025-05-20

Released gemma-3n-e4b-it preview, available on AI Studio and through the Gemini API, as part of the Gemma 3n launch.

2025.05 Released gemini-2.0-flash-preview-image-generation,... · 2025-05-07

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

2025.05 Released gemini-2.5-pro-preview-05-06, a new... · 2025-05-06

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

2025.04 Released gemini-2.5-flash-preview-04-17, a Gemini... · 2025-04-17

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

2025.04 Launched context caching for Gemini 2.0 Flash. · 2025-04-16

Launched context caching for Gemini 2.0 Flash.

2025.04 Released veo-2.0-generate-001, a generally... · 2025-04-09

Released veo-2.0-generate-001, a generally available (GA) text- and image-to-video model, capable of generating detailed and artistically nuanced videos. To learn more, see the Veo docs.

2025.04 Released gemini-2.0-flash-live-001, a public... · 2025-04-09

Released gemini-2.0-flash-live-001, a public preview version of the Live API model with billing enabled. - Enhanced Session Management and Reliability - Session Resumption: Keep sessions alive across temporary network disruptions. The API now supports server-side session state storage (for up to 24 hours) and provides handles (session\_resumption) to reconnect and resume where you left off. - Longer Sessions via...

2025.04 Released gemini-2.5-pro-preview-03-25, a public... · 2025-04-04

Released gemini-2.5-pro-preview-03-25, a public preview Gemini 2.5 Pro version with billing enabled. You can continue to use gemini-2.5-pro-exp-03-25 on the free tier.

2025.03 Released gemini-2.5-pro-exp-03-25, a public... · 2025-03-25

Released gemini-2.5-pro-exp-03-25, a public experimental Gemini model with thinking mode always on by default. To learn more, see Gemini 2.5 Pro Experimental.

2025.03 Launched an experimental Gemini 2.0 Flash model... · 2025-03-12

Launched an experimental Gemini 2.0 Flash model capable of image generation and editing.

2025.03 Released gemma-3-27b-it, available on AI Studio and... · 2025-03-12

Released gemma-3-27b-it, available on AI Studio and through the Gemini API, as part of the Gemma 3 launch. API updates

2025.03 Added support for YouTube URLs as a media source. · 2025-03-12

Added support for YouTube URLs as a media source.

2025.03 Added support for including an inline video of less... · 2025-03-12

Added support for including an inline video of less than 20MB.

2025.03 Released the Google Gen AI SDK for TypeScript and... · 2025-03-11

Released the Google Gen AI SDK for TypeScript and JavaScript to public preview.

2025.03 Released gemini-embedding-exp-03-07, an... · 2025-03-07

Released gemini-embedding-exp-03-07, an experimental Gemini-based embeddings model in public preview.

2025.02 Support for Search as a tool added to... · 2025-02-28

Support for Search as a tool added to gemini-2.0-pro-exp-02-05, an experimental model based on Gemini 2.0 Pro.

2025.02 Released gemini-2.0-flash-lite, a generally... · 2025-02-25

Released gemini-2.0-flash-lite, a generally available (GA) version of Gemini 2.0 Flash-Lite, which is optimized for speed, scale, and cost efficiency.

2025.02 Support for additional regions (Kosovo, Greenland... · 2025-02-19

Support for additional regions (Kosovo, Greenland and Faroe Islands). API updates

2025.02 Support for additional regions (Kosovo, Greenland... · 2025-02-19

Support for additional regions (Kosovo, Greenland and Faroe Islands).

2025.02 Gemini 1.0 Pro is no longer supported. For the list... · 2025-02-18

Gemini 1.0 Pro is no longer supported. For the list of supported models, see Gemini models.

2025.02 Updates on the OpenAI libraries compatibility. · 2025-02-11

Updates on the OpenAI libraries compatibility.

2025.02 Released imagen-3.0-generate-002, a generally... · 2025-02-06

Released imagen-3.0-generate-002, a generally available (GA) version of Imagen 3 in the Gemini API. SDK updates

2025.02 Released the Google Gen AI SDK for Java for public... · 2025-02-06

Released the Google Gen AI SDK for Java for public preview.

2025.02 Released gemini-2.0-flash-001, a generally... · 2025-02-05

Released gemini-2.0-flash-001, a generally available (GA) version of Gemini 2.0 Flash that supports text-only output.

2025.02 Released gemini-2.0-pro-exp-02-05, an experimental... · 2025-02-05

Released gemini-2.0-pro-exp-02-05, an experimental public preview version of Gemini 2.0 Pro.

2025.02 Released gemini-2.0-flash-lite-preview-02-05, an... · 2025-02-05

Released gemini-2.0-flash-lite-preview-02-05, an experimental public preview model optimized for cost efficiency. API updates

2025.02 Added file input and graph output support to code... · 2025-02-05

Added file input and graph output support to code execution. SDK updates

2025.02 Released the Google Gen AI SDK for Python to... · 2025-02-05

Released the Google Gen AI SDK for Python to general availability (GA).

2025.01 Released gemini-2.0-flash-thinking-exp-01-21, the... · 2025-01-21

Released gemini-2.0-flash-thinking-exp-01-21, the latest preview version of the model behind the Gemini 2.0 Flash Thinking Model.

2024.12 Released Gemini 2.0 Flash Thinking Mode for public... · 2024-12-19

Released Gemini 2.0 Flash Thinking Mode for public preview. Thinking Mode is a test-time compute model that lets you see the model's thought process while it generates a response, and produces responses with stronger reasoning capabilities. Read more about Gemini 2.0 Flash Thinking Mode in our overview page.

2024.12 Released Gemini 2.0 Flash Experimental for public... · 2024-12-11

Released Gemini 2.0 Flash Experimental for public preview. Gemini 2.0 Flash Experimental's partial list of features includes: - Twice as fast as Gemini 1.5 Pro - Bidirectional streaming with our Live API - Multimodal response generation in the form of text, images, and speech - Built-in tool use with multi-turn reasoning to use features like code execution, Search, function calling, and more Read more about...

2024.11 Released gemini-exp-1121, an even more powerful... · 2024-11-21

Released gemini-exp-1121, an even more powerful experimental Gemini API model. Model updates

2024.11 Updated the gemini-1.5-flash-latest and... · 2024-11-21

Updated the gemini-1.5-flash-latest and gemini-1.5-flash model aliases to use gemini-1.5-flash-002. - Change to top_k parameter: The gemini-1.5-flash-002 model supports top_k values between 1 and 41 (exclusive). Values greater than 40 will be changed to 40.

2024.11 Released gemini-exp-1114, a powerful experimental... · 2024-11-14

Released gemini-exp-1114, a powerful experimental Gemini API model.

2024.11 Added support for Gemini in the OpenAI libraries /... · 2024-11-08

Added support for Gemini in the OpenAI libraries / REST API.

2024.10 Added support for Grounding with Google Search. · 2024-10-31

Added support for Grounding with Google Search.

2024.10 Released gemini-1.5-flash-8b-001, a stable version... · 2024-10-03

Released gemini-1.5-flash-8b-001, a stable version of our smallest Gemini API model.

2024.09 Released gemini-1.5-pro-002 and... · 2024-09-24

Released gemini-1.5-pro-002 and gemini-1.5-flash-002, two new stable versions of Gemini 1.5 Pro and 1.5 Flash, for general availability.

2024.09 Updated the gemini-1.5-pro-latest model code to use... · 2024-09-24

Updated the gemini-1.5-pro-latest model code to use gemini-1.5-pro-002 and the gemini-1.5-flash-latest model code to use gemini-1.5-flash-002.

2024.09 Released gemini-1.5-flash-8b-exp-0924 to replace... · 2024-09-24

Released gemini-1.5-flash-8b-exp-0924 to replace gemini-1.5-flash-8b-exp-0827.

2024.09 Released the civic integrity safety filter for the... · 2024-09-24

Released the civic integrity safety filter for the Gemini API and AI Studio.

2024.09 Released support for two new parameters for Gemini... · 2024-09-24

Released support for two new parameters for Gemini 1.5 Pro and 1.5 Flash in Python and NodeJS: frequencyPenalty and presencePenalty.

2024.09 Added thumb-up and thumb-down buttons to model... · 2024-09-19

Added thumb-up and thumb-down buttons to model responses, to enable users to provide feedback on the quality of a response. API updates

2024.09 Added support for Google Cloud credits, which can... · 2024-09-19

Added support for Google Cloud credits, which can now be used towards Gemini API usage.

2024.09 Added an Open in Colab button that exports a prompt... · 2024-09-17

Added an Open in Colab button that exports a prompt – and the code to run it – to a Colab notebook. The feature doesn't yet support prompting with tools (JSON mode, function calling, or code execution).

2024.09 Added support for compare mode, which lets you... · 2024-09-13

Added support for compare mode, which lets you compare responses across models and prompts to find the best fit for your use case.

2024.08 Gemini 1.5 Flash supports supplying JSON schema... · 2024-08-30

Gemini 1.5 Flash supports supplying JSON schema through model configuration.

2024.08 Released the following experimental models · 2024-08-27

Released the following experimental models: - gemini-1.5-pro-exp-0827 - gemini-1.5-flash-exp-0827 - gemini-1.5-flash-8b-exp-0827

2024.08 Added support for PDF processing. · 2024-08-09

Added support for PDF processing.

2024.08 Fine-tuning support released for Gemini 1.5 Flash. · 2024-08-05

Fine-tuning support released for Gemini 1.5 Flash.

2024.08 Released gemini-1.5-pro-exp-0801, a new... · 2024-08-01

Released gemini-1.5-pro-exp-0801, a new experimental version of Gemini 1.5 Pro.

2024.07 Support for Gemini 1.0 Pro Vision removed from... · 2024-07-12

Support for Gemini 1.0 Pro Vision removed from Google AI services and tools.

2024.06 General availability release for Gemini 1.5 Pro's... · 2024-06-27

General availability release for Gemini 1.5 Pro's 2M context window. API updates

2024.06 Added support for code execution. · 2024-06-27

Added support for code execution.

2024.06 Added support for context caching. · 2024-06-18

Added support for context caching.

2024.06 Gemini 1.0 Pro Vision deprecated. · 2024-06-12

Gemini 1.0 Pro Vision deprecated.

2024.05 Gemini 1.5 Pro (gemini-1.5-pro-001) is generally... · 2024-05-23

Gemini 1.5 Pro (gemini-1.5-pro-001) is generally available (GA).

2024.05 Gemini 1.5 Flash (gemini-1.5-flash-001) is... · 2024-05-23

Gemini 1.5 Flash (gemini-1.5-flash-001) is generally available (GA).

2024.05 Introduced a 2M context window for Gemini 1.5 Pro... · 2024-05-14

Introduced a 2M context window for Gemini 1.5 Pro (waitlist).

2024.05 Introduced pay-as-you-go billing for Gemini 1.0... · 2024-05-14

Introduced pay-as-you-go billing for Gemini 1.0 Pro, with Gemini 1.5 Pro and Gemini 1.5 Flash billing coming soon.

2024.05 Introduced increased rate limits for the upcoming... · 2024-05-14

Introduced increased rate limits for the upcoming paid tier of Gemini 1.5 Pro.

2024.05 Added built-in video support to the File API. · 2024-05-14

Added built-in video support to the File API.

2024.05 Added plain text support to the File API. · 2024-05-14

Added plain text support to the File API.

2024.05 Added support for parallel function calling, which... · 2024-05-14

Added support for parallel function calling, which returns more than one call at a time.

2024.05 Released Gemini 1.5 Flash (gemini-1.5-flash-latest)... · 2024-05-10

Released Gemini 1.5 Flash (gemini-1.5-flash-latest) in preview.

2024.04 Released Gemini 1.5 Pro (gemini-1.5-pro-latest) in... · 2024-04-09

Released Gemini 1.5 Pro (gemini-1.5-pro-latest) in preview.

2024.04 Released a new text embedding model,... · 2024-04-09

Released a new text embedding model, text-embeddings-004, which supports elastic embedding sizes under 768. API updates

2024.04 Released the File API for temporarily storing media... · 2024-04-09

Released the File API for temporarily storing media files for use in prompting.

2024.04 Added support for prompting with text, image, and... · 2024-04-09

Added support for prompting with text, image, and audio data, also known as multimodal prompting. To learn more, see Prompting with media.

2024.04 Released System instructions in beta. · 2024-04-09

Released System instructions in beta.

2024.04 Added Function calling mode, which defines the... · 2024-04-09

Added Function calling mode, which defines the execution behavior for function calling.

2024.04 Added support for the response_mime_type... · 2024-04-09

Added support for the response_mime_type configuration option, which lets you request responses in JSON format.

2024.03 Added support for tuning Gemini 1.0 Pro in Google... · 2024-03-19

Added support for tuning Gemini 1.0 Pro in Google AI Studio or with the Gemini API.

2023.12 gemini-pro: New text model for a wide variety of... · 2023-12-13

gemini-pro: New text model for a wide variety of tasks. Balances capability and efficiency.

2023.12 gemini-pro-vision: New multimodal model for a wide... · 2023-12-13

gemini-pro-vision: New multimodal model for a wide variety of tasks. Balances capability and efficiency.

2023.12 embedding-001: New embeddings model. · 2023-12-13

embedding-001: New embeddings model.

2023.12 aqa: A new specially tuned model that is trained to... · 2023-12-13

aqa: A new specially tuned model that is trained to answer questions using text passages for grounding generated answers. See Gemini models for more details. API version updates

2023.12 v1: The stable API channel. · 2023-12-13

v1: The stable API channel.

2023.12 v1beta: Beta channel. This channel has features... · 2023-12-13

v1beta: Beta channel. This channel has features that may be under development. See the API versions topic for more details. API updates

2023.12 GenerateContent is a single unified endpoint for... · 2023-12-13

GenerateContent is a single unified endpoint for chat and text.

2023.12 Streaming available through the... · 2023-12-13

Streaming available through the StreamGenerateContent method.

2023.12 Multimodal capability: Image is a new supported... · 2023-12-13

Multimodal capability: Image is a new supported modality

2023.12 New beta features · 2023-12-13

New beta features: - Function Calling - Semantic Retriever - Attributed Question Answering (AQA)

2023.12 Updated candidate count: Gemini models only return... · 2023-12-13

Updated candidate count: Gemini models only return 1 candidate.

2023.12 Different Safety Settings and SafetyRating... · 2023-12-13

Different Safety Settings and SafetyRating categories. See safety settings for more details.

2023.12 Tuning models is not yet supported for Gemini... · 2023-12-13

Tuning models is not yet supported for Gemini models (Work in progress).