* **Gemini Embedding 2 Preview deprecation**: [`gemini-embedding-2-preview`](/docs/models/gemini-embedding-2-preview) is [deprecated](/docs/deprecations#embedding-deprecated-models). Effective November 6, 2026, API requests to `gemini-embedding-2-preview` route to [`gemini-embedding-2`](/docs/models/gemini-embedding-2) at [Gemini Embedding 2 rates](/docs/pricing#gemini-embedding-2). Update your model string to `gemini-embedding-2`. `gemini-embedding-2` uses the same API schema, pricing, and embedding space, so no other code changes or vector re-indexing are needed.
Use GPT-6-Cyber to investigate vulnerabilities, reproduce them in an authorized test environment, and verify fixes. See Daybreak setup before sending your first request.
* **Gemini Omni 1.2 Flash generally available (GA)**: Released [Gemini Omni 1.2 Flash](/docs/models/gemini-omni-flash) (`gemini-omni-1.2-flash`), featuring up to 15-second video generation and conversational editing (3 to 10 seconds for first and last frame interpolation, and 3 to 10 seconds per-turn video extension up to 30 seconds total length), improved character and subject consistency across up to 6 reference images, 30% lower video output [pricing](/docs/pricing#gemini-omni-1.2-flash) ($12.00 per 1M tokens), and doubled paid-tier [rate limits](/docs/rate-limits#gemini-omni-flash-rate-limits). See the [Gemini Omni Flash guide](/docs/omni) to get started. * **Gemini Omni 1.1 Flash automatic routing notice**: Effective **December 3, 2026**, API requests to `gemini-omni-1.1-flash` will automatically route to `gemini-omni-1.2-flash` at [Gemini Omni 1.2 Flash rates](/docs/pricing#gemini-omni-1.2-flash). * **Expanded Office and OpenDocument file support**: The Gemini API now accepts PowerPoint 97-2003 (PPT), OpenDocument Presentation (ODP), and OpenDocument Spreadsheet (ODS) files as input, and adds page-image processing for Word 97-2003 (DOC) files. DOC, PPT, and ODP files are rendered as page images. For ODS files, the model receives the data and formulas from the first sheet. Processing for DOCX, DOTX, ODT, PPTX, XLSX, and XLS files is unchanged. See [Office and OpenDocument files](/docs/document-processing#office-documents) for how each format is processed. * **More file types and file URIs in function responses**: Tools can now return Office and OpenDocument files, audio, and video to the model. * **GenerateContent API**: Function response parts now accept audio, video, and Office and OpenDocument files, in addition to images, PDFs, and plain text. They also accept `fileData`, so tools can return a Files API URI instead of inline bytes. `displayName` is now available on both `inlineData` and `fileData`, and video parts accept `mediaProcessing` (`STATIC` or `AGENTIC`). * **Interactions API**: `function_result` steps now accept `document`, `audio`, and `video` content blocks, in addition to `text` and `image`, by inline `data` or `uri`. Video blocks are available in `v1beta` and `v1alpha` and accept `processing`. See [Multimodal function responses](/docs/function-calling#multimodal) for details.
Released GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare for image generation and editing, with adjustable complexity, SVG generation, and animated GIF generation. Added markup-guided editing for supported GPT Image 2.5 and 2.6 models. See the image generation guide.
* **Voice remixing for Gemini 3.8 TTS**: Released [Voice remixing](/docs/voice-remixing), which lets you modify an existing prebuilt or [designed](/docs/voice-design) voice using natural-language instructions to create a new, independent stored voice. Use `POST /v1beta/voices` with `gemini-3.8-flash-tts` (or remix interactively in [Google AI Studio](https://aistudio.google.com/generate-speech)) to generate a `voice_...` ID, then synthesize speech with [Gemini 3.8 Flash TTS](/docs/models/gemini-3.8-flash-tts) or [Gemini 3.8 Flash-Lite TTS](/docs/models/gemini-3.8-flash-lite-tts). See the [Voice remixing guide](/docs/voice-remixing) to get started.
Released GPT-Image-2.6 Sunburst and GPT-Image-2.6 Flare for image generation and editing, with adjustable complexity, SVG generation, and animated GIF generation. Added markup-guided editing for supported GPT-Image-2.5 and GPT-Image-2.6 models. See the image generation guide.
Outbound SIP calling is now available to all organizations through the Live API. Connect GPT-Live to a phone number through your SIP provider. See the SIP guide.
* **Gemini 2.5 Pro deprecation**: [`gemini-2.5-pro`](/docs/models/gemini-2.5-pro) is [deprecated](/docs/deprecations#gemini-2.5-pro-models) and is no longer available to select in Google AI Studio. Effective December 1, 2026, all API requests to `gemini-2.5-pro` will automatically route to [`gemini-3.8-flash`](/docs/models/gemini-3.8-flash) and be billed at [Gemini 3.8 Flash rates](/docs/pricing#gemini-3.8-flash). Before December 1, 2026, update your model string to `gemini-3.8-flash` and review the [Gemini 3.8 Flash migration guide](/docs/whats-new-gemini-3.8#migrate-to-gemini-3-8-flash). Breaking API changes include function calling and `thought_signature` validation, `thinking_level` replacing `thinking_budget`, and removed sampling parameters and prefilled model turns. * **Gemini 2.5 Flash deprecation**: [`gemini-2.5-flash`](/docs/models/gemini-2.5-flash) is [deprecated](/docs/deprecations#gemini-2.5-flash-models) and is no longer available to select in Google AI Studio. Effective December 1, 2026, all API requests to `gemini-2.5-flash` will automatically route to [`gemini-3.5-flash-lite`](/docs/models/gemini-3.5-flash-lite) and be billed at [Gemini 3.5 Flash-Lite rates](/docs/pricing#gemini-3.5-flash-lite). Before December 1, 2026, update your model string to `gemini-3.5-flash-lite` and review the [Gemini 3.5 Flash-Lite migration guide](/docs/whats-new-gemini-3.6#migrate-to-gemini-3-5-flash-lite). Breaking API changes include function calling and `thought_signature` validation, `thinking_level` replacing `thinking_budget`, and removed sampling parameters and prefilled model turns.
Added automatic review for eligible Agents API projects. Set the session's review field to "auto_review" to have a model approve or deny supported tool and permission requests based on conversation intent and risk. See the automatic review guide for supported requests, limitations, and additional token billing.
Released GPT-6 Rosalind, bringing specialized biological reasoning with scientific tool use to complex life sciences research. Access is available to organizations approved for Rosalind Research through the trusted-access program for internal research by authorized users.
You can now update the tools in an existing session in the Agents API public beta. Updates replace the full tool list. Function tools and MCP servers change on the next model call; built-in tools change by the next turn. Context compaction now runs in the background by default. Set compaction.async to false for blocking compaction. Background compaction may increase token usage. Added opt-in experimental time awareness. Set experimental.time_awareness to true to give the model periodic current-time reminders. It is disabled by default. See the agent configuration reference for compaction and experimental settings.