Google Gemini
Google · source page ↗ · last checked Nov 16, 2026, 12:00 PM
Current pricing
captured Nov 2, 2026, 12:00 PM| Model / item | Input | Output |
|---|---|---|
| Gemini 3.1 Pro Preview | $2.00 / 1M tokens (prompts ≤200k), $4.00 / 1M tokens (>200k) | $12.00 / 1M tokens (≤200k), $18.00 / 1M tokens (>200k) · Batch 50% off ($1.00/$6.00 ≤200k). Context caching $0.20/1M (≤200k), $0.40/1M (>200k) + $4.50/1M/hr storage. Free tier available. |
| Gemini 3.5 Flash | $1.50 / 1M tokens | $9.00 / 1M tokens · Batch/Flex 50% off ($0.75/$4.50). Priority $2.70/$16.20. Context caching $0.15/1M + $1.00/1M/hr storage. Free tier available. |
| Gemini 3 Flash Preview | $0.50 / 1M tokens (text/image/video), $1.00 / 1M tokens (audio) | $3.00 / 1M tokens · Batch/Flex 50% off. Priority $0.90 (text/image/video)/$1.80 (audio) input, $5.40 output. Free tier available. |
| Gemini 3.1 Flash-Lite | $0.25 / 1M tokens (text/image/video), $0.50 / 1M tokens (audio) | $1.50 / 1M tokens · Batch/Flex 50% off. Priority $0.45 (text/image/video)/$0.90 (audio) input, $2.70 output. Free tier available. |
| Gemini 2.5 Pro | $1.25 / 1M tokens (prompts ≤200k), $2.50 / 1M tokens (>200k) | $10.00 / 1M tokens (≤200k), $15.00 / 1M tokens (>200k) · Batch/Flex 50% off ($0.625/$5.00 ≤200k). Priority $2.25/$18.00 (≤200k). Free tier available. |
| Gemini 2.5 Flash | $0.30 / 1M tokens (text/image/video), $1.00 / 1M tokens (audio) | $2.50 / 1M tokens · Batch/Flex 50% off ($0.15/$1.25). Priority $0.54 (text/image/video)/$1.80 (audio) input, $4.50 output. Context caching $0.03/1M + $1.00/1M/hr storage. Free tier available. |
| Gemini 2.5 Flash-Lite | $0.10 / 1M tokens (text/image/video), $0.30 / 1M tokens (audio) | $0.40 / 1M tokens · Batch/Flex 50% off ($0.05/$0.20). Priority $0.18 (text/image/video)/$0.54 (audio) input, $0.72 output. Free tier available. |
| Gemini 2.0 Flash (deprecated) | $0.10 / 1M tokens (text/image/video), $0.70 / 1M tokens (audio) | $0.40 / 1M tokens · Deprecated — shut down June 1, 2026. Batch 50% off. Context caching $0.025/1M + $1.00/1M/hr storage. Free tier available. |
| Gemini 2.0 Flash-Lite (deprecated) | $0.075 / 1M tokens | $0.30 / 1M tokens · Deprecated — shut down June 1, 2026. Batch 50% off ($0.0375/$0.15). Free tier available. |
| Gemini Embedding 2 | $0.20 / 1M tokens (text); image $0.45/1M; audio $6.50/1M; video $12.00/1M | N/A (embeddings model) · Batch 50% off (text $0.10/1M). Free tier available. |
| Gemini Embedding (001) | $0.15 / 1M tokens (text) | N/A (embeddings model) · Batch 50% off ($0.075/1M). Free tier available (text only). |
| Imagen 4 | Per-image pricing | $0.02/image (Fast), $0.04/image (Standard), $0.06/image (Ultra) · Paid tier only. |
| Veo 3.1 | Per-second of video | Standard $0.40/sec (720p/1080p), $0.60/sec (4K); Fast $0.10–$0.30/sec; Lite $0.05–$0.08/sec · Charged only on successful generation. Paid tier only. |
| Google Search Grounding (tool) | Per grounded query | Gemini 3: 5,000 free prompts/mo, then $14 / 1,000 queries. Gemini 2.5: 1,500 free RPD, then $35 / 1,000 grounded prompts · Retrieved context tokens excluded from billing. |
Usage/token-based API pricing (no subscription tiers). Prices in USD per 1M tokens unless noted. All models offer Standard, and most offer Batch (~50% off), Flex, and Priority service tiers. Many models have context length tiers (prompts ≤200k vs >200k tokens), separate audio rates, and context caching. Free tier (lower rate limits; data may be used to improve products) vs paid tier (data not used without consent). Enterprise/Vertex AI prices may differ. Preview models may change before stabilization. Page last updated June 9, 2026; prices subject to change. Source returned via WebFetch; additional models on page include Gemini 3 Pro Image, Gemini 2.5 Flash Image, TTS/Live audio models, Lyria 3 music, and Computer Use / Robotics specialized models.
Curated snapshot · as of 2026-06-15. Live diffs are recorded in the change history below.
Rate & usage limits ● livestructure only
This provider doesn't publish numeric request/token limits on its docs — only the usage-tier structure below. Your actual limits appear in your account dashboard.
| Tier | Notes |
|---|---|
| Free | Rate limits viewable only in AI Studio dashboard; Free tier not supported for Gemini Omni Flash; Gemini Decision 1 Free tier: RPM 200, TPM 50,000, RPD 10,000 |
| Tier 1 | $10 spend-based rate limit per 10 minutes; qualification: active billing account; Gemini Omni Flash: RPM 8, RPD 40; Gemini Decision 1: RPM 1,500, TPM 1,000,000, RPD 50,000 |
| Tier 2 | $200 spend-based rate limit per 10 minutes; qualification: $100+ spend + 3 days; tier cap $2,000; Gemini Omni Flash: RPM 16, RPD 200; Gemini Decision 1: RPM 5,000, TPM 4,000,000, RPD Unlimited |
| Tier 3 | $200 spend-based rate limit per 10 minutes; qualification: $1,000+ spend + 30 days; tier cap $20,000-$100,000+; Gemini Omni Flash: RPM 40, RPD 2,000; Gemini Decision 1: RPM 15,000, TPM 10,000,000, RPD Unlimited |
Rate limits are model-specific and viewable in AI Studio dashboard; actual capacity may vary; limits also vary by API (interactive vs. batch); shown examples are for Gemini Omni Flash and Gemini Decision 1 only
Deprecations
Gemini 3 models
Gemini 2.5 Pro models
Gemini 2.5 Flash models
Gemini 2.0 models
Live API models
Audio models
Embedding models
Imagen models
Veo models
Lyria models
Robotics models
Per the page: a "deprecation" is the announcement that a model is no longer supported and will be "shut down" soon; once "shutdown", the endpoint is completely turned off and no longer available. Shutdown dates are the earliest possible retirement dates; exact dates are communicated separately. Status here reflects the page's version label (GA / Preview / Experimental); items with a shutdown/retirement date are marked Deprecated, and those with "No shutdown announced" are Active. Dates printed exactly as on the page; release dates given as "Released On". Some preview/experimental rows have no release date listed on the page.
Curated snapshot · as of 2026-06-15. Detected page changes are in the change history below.
Changelog
- June 1, 2026 Gemini 2.0 models shut downFour Gemini 2.0 Flash models discontinued; users directed to Gemini 3.5 alternatives.
- May 28, 2026 Native visual models GA & video-to-image supportTwo native image generation models released as GA; video files now usable as context.
- May 25, 2026 Flash-Lite preview model shut downgemini-3.1-flash-lite-preview discontinued; GA version available as replacement.
- May 19, 2026 Gemini 3.5 Flash GA & managed agents previewGemini 3.5 Flash released for sustained frontier performance; autonomous sandboxed agents launched in preview.
- May 7, 2026 Flash-Lite GA & deprecation noticeCost-efficient Gemini 3.1 Flash-Lite released as stable; preview version deprecating May 25.
- May 6, 2026 Interactions API breaking change noticeRequest/response schema and output format configuration changing; migration guide provided.
- May 5, 2026 File Search multimodal supportFile Search now supports image embedding and search via the gemini-embedding-2 model.
- May 4, 2026 Webhooks support launchedEvent-driven webhooks replace polling for the Batch API and long-running operations.
- April 30, 2026 Robotics model shut downgemini-robotics-er-1.5-preview discontinued; newer 1.6 version available.
- April 22, 2026 Embedding model GAgemini-embedding-2 released as generally available.
- April 21, 2026 Deep Research agent updatedTwo new versions add collaborative planning, visualization, MCP, and File Search support.
- April 15, 2026 Text-to-speech model launchedGemini 3.1 Flash TTS Preview released as a cost-efficient speech generation model.
- April 14, 2026 Robotics model update & deprecationVersion 1.6 adds instrument reading and spatial reasoning; 1.5 retiring April 30.
- April 2, 2026 Gemma 4 models releasedTwo new Gemma 4 models available via AI Studio and the Gemini API.
- April 1, 2026 Flex & Priority inference tiers introducedNew inference tiers offering more options for optimizing cost or latency.
- March 31, 2026 Veo 3.1 Lite & model shutdownCost-efficient video generation model released; older Flash-Lite model discontinued.
- March 26, 2026 Audio-to-audio model releasedLatest A2A model for real-time dialogue and voice-first AI applications launched.
- March 25, 2026 Lyria 3 music generation launchTwo music models released supporting text and image inputs; 30-second and full-length options.
- March 23, 2026 Billing plans rolloutPrepay and Postpay billing options introduced in AI Studio.
- March 18, 2026 Tools & function combination featureBuilt-in tools now work alongside custom function calling in a single API request.
- March 16, 2026 Usage tiers & spend caps revampedRevamped billing structure with updated usage tiers and account spend limits.
- March 12, 2026 Project-level spend caps addedProject-specific spending limits now available in billing configuration.
- March 10, 2026 Multimodal embedding model & deprecationFirst multimodal embedding model supports five modalities; older embedding model retiring.
- March 9, 2026 Gemini 3 Pro redirectOriginal Gemini 3 Pro Preview shut down; model name now aliases to the 3.1 version.
- March 3, 2026 Flash-Lite preview launchedFirst Flash-Lite model in the Gemini 3 series released in preview.
- February 26, 2026 Nano Banana 2 & deprecation noticeHigh-efficiency image generation model released; older Pro version retiring March 9.
- February 19, 2026 Gemini 3.1 Pro & custom tools endpointLatest iteration released with new media resolution behavior; specialized tools endpoint added.
- February 18, 2026 Gemini 2.0 models deprecation announcedFour Flash models scheduled for June 1 shutdown; replacement models recommended.
- February 17, 2026 Model shutdownsThree models discontinued; users directed to newer alternatives.
- January 29, 2026 Computer Use tool supportComputer Use tool now supported on two Gemini 3 preview models.
- January 21, 2026 Latest alias updatesModel aliases updated to point to Gemini 3 preview versions.
- January 15, 2026 Model shutdowns & deprecationsThree models retiring February 17; future deprecations announced.
- January 14, 2026 Embedding model shutdowntext-embedding-004 discontinued.
- January 13, 2026 Video output resolution enhancement4K output added for Veo; portrait video support expanded across resolutions.
- January 12, 2026 Model lifecycle feature launchedModels now specify lifecycle stage and deprecation timeline for clarity.
- January 8, 2026 File input expansionCloud Storage buckets and pre-signed URLs supported; file size limit raised to 100MB.
- December 19, 2025 Interactions API field renametotal_reasoning_tokens renamed to total_thought_tokens in a breaking change.
- December 17, 2025 Gemini 3 Flash Preview releasedFast frontier-class model launched with upgraded reasoning and new multimodal features.
- December 12, 2025 Native audio model releasedNew audio model for the Live API with improved complex workflow handling.
- December 11, 2025 Interactions API beta & Deep Research agentUnified API interface launched; autonomous research agent in preview.
Google Gemini API release notes. Page last updated 2026-06-01 UTC. Entries are summarized from the official changelog; dates and model/version names are reproduced as printed on the page.
Curated snapshot · as of 2026-06-15. Detected page changes are in the change history below.
In the news · Google
- DeepMind Opens Free AI Rain Data: Five-Hour Latency, Claimed Win Over NASA's IMERG-Final
- Google Gemini Launches Orchestrator to Enhance Multi-Model Workflows
- Google DeepMind launches Gemini Robotics 2.5 with improved dexterity and industrial capabilities
- Google Gemini Launches Artificial Analysis for Model Evaluation and Benchmarking
- Google's Gemini 4 Hydrogen is free — here are 5 impressive things you can do with it
- GOOG Stock Reverses $300 Recovery as Google Gemini Launch and Anthropic Deal Raise Spending Questions
- Google’s Gemini Glasses Start at $395, With Preorders Open Ahead of December Launch
- Google: Gemini 4 Hydrogen Launches With Faster Agentic AI, 1 Million-Token Context Window, And New Multi-Model Orchestration
Importance-filtered press coverage (Google News) mentioning Google. Headlines link to the original; verify before acting.
Change history
- Update Nov 13, 2026, 6:00 PM
Google Gemini deprecations changed
Multiple date entries updated from November 17, 2026 to December 18, 2026 and March 31, 2027
- November 17, 2026 changed to December 18, 2026
- One date changed to March 31, 2027
View raw diff +4 −5
- November 17, 2026 - November 17, 2026 - November 17, 2026 - November 17, 2026 - November 17, 2026 + December 18, 2026 + March 31, 2027 + December 18, 2026 + December 18, 2026
- Update Nov 12, 2026, 6:00 PM
Google Gemini API changelog changed
Gemini 4 Hydrogen (gemini-4-hydrogen) model released as generally available with pricing of $1.50 per 1M input tokens and $7.50 per 1M output tokens, featuring a new xhigh thinking level.
now$1.50$7.50View raw diff +13 −0
+ November 12, 2026 {% id="11-12-2026" %} + Gemini 4 Hydrogen (gemini-4-hydrogen) generally available (GA): Released + Gemini 4 Hydrogen (gemini-4-hydrogen), + bringing cutting-edge intelligence to everyone, with speed and efficiency + for everyday coding and agentic workflows. + Available on the free tier and at paid-tier + pricing of $1.50 per 1M input tokens and + $7.50 per 1M output tokens, gemini-4-hydrogen introduces a fourth + xhigh thinking level alongside low, + medium, and default high, and is now the default model for the + Antigravity agent in Gemini Managed Agents. See + What's new in Gemini 4 Hydrogen for API + changes and migration guidance from Gemini 3.8 Flash.
- Update Nov 12, 2026, 6:00 PM
Google Gemini deprecations changed
Added new Gemini model gemini-4-hydrogen available as of November 12, 2026.
- gemini-4-hydrogen
- November 12, 2026
View raw diff +2 −0
+ gemini-4-hydrogen + November 12, 2026
- Update Nov 12, 2026, 12:00 AM
Google Gemini API changelog changed
Gemini Decision model (gemini-decision-1) and Decisions API released for fast binary, categorical, and rubric decisions with zero output tokens.
- gemini-decision-1 model released
- Decisions API released
- supports text, images, audio, video, and PDFs
View raw diff +8 −0
+ November 11, 2026 {% id="11-11-2026" %} + Gemini Decision and the Decisions API: Released + Gemini Decision (gemini-decision-1) and + the Decisions API for fast, calibrated binary, + categorical, and rubric decisions across text, images, audio, video, and + PDFs with zero output tokens. View pricing + and rate limits, or see the + Decisions API guide to get started.
- Update Nov 12, 2026, 12:00 AM
Google Gemini deprecations changed
New Gemini Decision model gemini-decision-1 announced for November 11, 2026.
- New model: gemini-decision-1
- Available: November 11, 2026
View raw diff +3 −0
+ Gemini Decision models {% id="gemini-decision-models" %} + gemini-decision-1 + November 11, 2026
- Update Nov 10, 2026, 6:00 PM
Google Gemini API changelog changed
Gemini 4 Carbon model is now generally available with introductory pricing of $2.00 per 1M input tokens and $10.00 per 1M output tokens through November 30, 2026.
now$2.00$10.00View raw diff +8 −0
+ November 10, 2026 {% id="11-10-2026" %} + Gemini 4 Carbon (gemini-4-carbon) generally available (GA): Released + Gemini 4 Carbon (gemini-4-carbon), our + most capable reasoning model built for sustained agentic coding, multimodal + knowledge work, scientific reasoning, and cybersecurity defense, available + at introductory pricing of $2.00 per 1M + input tokens and $10.00 per 1M output tokens through November 30, 2026. See + What's new in Gemini 4 Carbon to get started.
- Update Nov 10, 2026, 6:00 PM
Google Gemini deprecations changed
Two new Gemini 4 models added: gemini-4-carbon and gemini-4-argon with release dates.
- gemini-4-carbon released November 10, 2026
- gemini-4-argon released October 13, 2026
View raw diff +5 −0
+ Gemini 4 models {% id="gemini-4-models" %} + gemini-4-carbon + November 10, 2026 + gemini-4-argon + October 13, 2026
- Update Nov 7, 2026, 12:00 AM
Google Gemini API changelog changed
gemini-embedding-2-preview is deprecated and requests now route to gemini-embedding-2 at Gemini Embedding 2 rates effective November 6, 2026.
- gemini-embedding-2-preview is deprecated effective November 6, 2026
- API requests to gemini-embedding-2-preview route to gemini-embedding-2 at Gemini Embedding 2 rates
- gemini-embedding-2 uses the same API schema, pricing, and embedding space with no code changes or vector re-indexing needed
View raw diff +12 −2
- 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 + November 6, 2026 {% id="11-06-2026" %} + Gemini Embedding 2 Preview deprecation: + gemini-embedding-2-preview is + deprecated. Effective + November 6, 2026, API requests to gemini-embedding-2-preview route to + gemini-embedding-2 at + Gemini Embedding 2 rates. 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. + 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
- Update Nov 6, 2026, 6:00 PM
Google Gemini deprecations changed
gemini-embedding-2 model released on November 6, 2026 with gemini-embedding-2-preview requests routing to the new model
- November 6, 2026 release date
- gemini-embedding-2 model availability
- gemini-embedding-2-preview requests route to gemini-embedding-2
View raw diff +2 −1
- August 10, 2026 + November 6, 2026 + gemini-embedding-2 (effective November 6, 2026, API requests to gemini-embedding-2-preview route to gemini-embedding-2)
- Update Nov 5, 2026, 6:00 PM
Google Gemini API changelog changed
Gemini Omni 1.2 Flash released as GA with improved video generation capabilities, 30% lower pricing at $12.00 per 1M tokens, and doubled rate limits; Gemini Omni 1.1 Flash will auto-route to 1.2 Flash starting December 3, 2026.
now$12.00View raw diff +14 −0
+ Gemini Omni 1.2 Flash generally available (GA): Released + Gemini Omni 1.2 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 ($12.00 per 1M tokens), and + doubled paid-tier rate limits. + See the Gemini Omni Flash guide 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.
- Update Nov 5, 2026, 6:00 PM
Google Gemini deprecations changed
Model name updated from gemini-omni-1.1-flash to gemini-omni-1.2-flash with automatic routing starting December 3, 2026.
- gemini-omni-1.1-flash replaced with gemini-omni-1.2-flash
- Automatic endpoint routing to gemini-omni-1.2-flash effective December 3, 2026
- November 5, 2026 and December 3, 2026 dates introduced
View raw diff +15 −3
- gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform - gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform - gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform + gemini-omni-1.2-flash + gemini-omni-1.2-flash + gemini-omni-1.2-flash + gemini-omni-1.2-flash or the GA models on the Gemini Enterprise Agent Platform + gemini-omni-1.2-flash or the GA models on the Gemini Enterprise Agent Platform + gemini-omni-1.2-flash or the GA models on the Gemini Enterprise Agent Platform + gemini-omni-1.2-flash + gemini-omni-1.2-flash + gemini-omni-1.2-flash + November 5, 2026 + December 3, 2026 + gemini-omni-1.2-flash (Effective December 3, 2026, the endpoint is + automatically routing API requests to + gemini-omni-1.2-flash) + gemini-omni-1.2-flash
- Update Nov 5, 2026, 12:00 PM
Google Gemini API changelog changed
Gemini API now accepts PowerPoint 97-2003 (PPT), OpenDocument Presentation (ODP), and OpenDocument Spreadsheet (ODS) files as input, and supports returning Office/OpenDocument files, audio, and video in function responses.
- Gemini API accepts PPT, ODP, and ODS files as input with page-image processing for DOC files
- Tools can return Office and OpenDocument files, audio, and video to the model via function responses
- GenerateContent API function response parts now accept audio, video, Office and OpenDocument files, and fileData URIs
View raw diff +24 −0
+ November 5, 2026 {% id="11-05-2026" %} + 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 + 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 + for details.
- Update Nov 4, 2026, 6:00 PM
Google Gemini API changelog changed
Voice remixing feature released for Gemini 3.8 TTS, enabling voice modification via POST /v1beta/voices endpoint with natural-language instructions.
- Voice remixing available for gemini-3.8-flash-tts model
- POST /v1beta/voices endpoint used to generate voice_... ID
- Works with Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS models
View raw diff +11 −0
+ November 4, 2026 {% id="11-04-2026" %} + Voice remixing for Gemini 3.8 TTS: Released + Voice remixing, which lets you modify an existing + prebuilt or designed 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 ) to generate + a voice_... ID, then synthesize speech with + Gemini 3.8 Flash TTS or + Gemini 3.8 Flash-Lite TTS. See the + Voice remixing guide to get started.
- Update Nov 3, 2026, 6:00 PM
Google Gemini API changelog changed
Multiple Gemini API models and tools were released or deprecated between September 3 and October 30, 2026, including Computer Use GA, new TTS models, Live audio models, and several model deprecations.
- Computer Use released to GA on October 30, 2026 across Interactions and GenerateContent APIs
- Gemini 4 Argon (gemini-4-argon) released as GA on October 13, 2026 for complex coding and agentic tasks
- Gemini 3.7 Flash and Gemini 3.5 Flash deprecated on October 8, 2026 with automatic routing to newer versions
View raw diff +926 −602
- October 30, 2026 - Computer Use generally available (GA): Released the Computer Use tool to general availability (GA) across the Interactions and GenerateContent APIs. - October 27, 2026 - Gemini API CLI (gemini-api) beta: Released the [Gemini API - CLI](https://ai.google.dev/gemini-api/docs/cli) (gemini-api), a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines. Use gemini-api on the Interactions API to generate text and media, analyze files, and run [Gemini managed - agents](https://ai.google.dev/gemini-api/docs/agents). See the [Gemini API CLI - guide](https://ai.google.dev/gemini-api/docs/cli) to get started. - October 26, 2026 - Generate Content API storage on by default: New projects using the Generate Content API (generateContent, streamGenerateContent, and batchGenerateContent) on the paid tier now store requests by default (store=true), matching the Interactions API. Existing projects keep their current setting. To opt out, set store=false on individual requests or turn off Generate Content API logging in the Settings panel of the Logs and Datasets dashboard. See Logs and datasets for details. - October 13, 2026 - Gemini 4 Argon (gemini-4-argon) generally available (GA): Released - Gemini 4 Argon (gemini-4-argon), - our most capable model built for complex coding, agentic, math, and science - tasks. - What's new in Gemini 4 Argon. - October 8, 2026 - Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. - Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide. - Deep Research Agent deep-research-pro-preview-12-2025 deprecation: - shut down on **October 23, - 2026**. - Research](https://ai.google.dev/gemini-api/docs/deep-research) agent versions: - 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. - October 6, 2026 - Gemini Nano Banana 2.1 generally available (GA): Released - Gemini Nano Banana 2.1 - (gemini-3.1-flash-image ), - it maintains Flash-level speed and cost efficiency while delivering - significant improvements in visual quality, prompt adherence, multi-turn - character consistency, text rendering, and wide and panoramic aspect ratio - generation (1:4, 4:1, 1:8, 8:1) across 1K, 2K, and 4K - resolutions. - See the Image generation guide to get - Deprecation announcement: The gemini-3.1-flash-image model is - gemini-nano-banana-2.1. - September 22, 2026 - **Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available - (GA)**: Released our next-generation text-to-speech (TTS) audio models and - **Gemini 3.8 Flash TTS - (gemini-3.8-flash-tts)**: Flagship creative TTS model engineered for studio-grade voice fidelity, nuanced acting, regional dialects, and long-form multi-turn stability. - **Gemini 3.8 Flash-Lite TTS - (gemini-3.8-flash-lite-tts)**: Fast, cost-efficient TTS model built to replace gemini-3.1-flash-tts-preview for high-throughput production and real-time voice agent cascades. - **Voice design, - Voice replication, and the - Extended Voice Library **: Create persistent custom vocal personas from text prompts, replicate voices with consent verification, and query 150+ prebuilt and custom voices. - See the Text-to-speech guide to get - September 18, 2026 - Gemini 2.5 models access update: To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications. - September 17, 2026 - Antigravity Agent 09-2026: Released antigravity-preview-09-2026, - |---|---|---| - See the Antigravity Agent guide. - deprecations page. - September 15, 2026 - **Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking generally available - (GA)**: Released two new audio-to-audio models for real-time voice - applications using the Live API: - Gemini 3.8 Live (gemini-3.8-live ): The default option for most low-latency voice agent experiences and real-time dialogue without reasoning delays. Features interleaved reasoning, default asynchronous function calling, and full session client content updates. - Gemini 3.8 Live Extended Thinking (gemini-3.8-live-extended-thinking ): High-reasoning audio-to-audio model supporting background reasoning during live audio interactions, recommended when higher background reasoning is required.
- Pricing Oct 31, 2026, 12:00 AM
Google Gemini API pricing changed
Gemini API pricing reduced across multiple tiers: input tokens from $1.00 to $0.375 per 1M, output tokens from $5.00 to $1.875 per 1M, and a new $0.0375 per 1M tier added.
now$1.00$5.00$0.37$1.87$0.03View raw diff +9 −0
+ Paid Tier, per 1M tokens in USD* + $1.00 + $5.00 + Paid Tier, per 1M tokens in USD* + $0.375 + $1.875 + $0.0375 + Paid Tier, per 1M tokens in USD* + Paid Tier, per 1M tokens in USD*
- Update Oct 30, 2026, 6:00 PM
Google Gemini API changelog changed
Computer Use tool released to general availability (GA) across Interactions and GenerateContent APIs.
- Computer Use tool moved to GA
- Available across Interactions and GenerateContent APIs
- Released October 30, 2026
View raw diff +2 −0
+ October 30, 2026 + Computer Use generally available (GA): Released the Computer Use tool to general availability (GA) across the Interactions and GenerateContent APIs.
- Pricing Oct 29, 2026, 12:00 AM
Google Gemini API pricing changed
Added daily rate cap of 1,500 search requests/day to grounding feature across all models
rate_limitSearch grounding rate limit: added explicit daily cap of 1,500 requests/day across all Gemini 3+ modelsView raw diff +40 −34
- 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests for text and image-based grounding. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests for text and image-based grounding. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests. - Charged for embeddings at $0.15 / 1M tokens. + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests for text and image-based grounding (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests for text and image-based grounding (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day). + 5,000 free search requests per month (shared across all Gemini 3 and newer models), then $14 per 1,000 requests (subject to a daily cap of 1,500 requests per day).
- Update Oct 28, 2026, 6:00 AM
Google Gemini API changelog changed
Released Gemini API CLI (gemini-api), a new command-line client for the Interactions API supporting text/media generation, file analysis, and managed agents.
- Gemini API CLI (gemini-api) is a stateless, zero-dependency command-line client
- Supports Interactions API for generating text and media, analyzing files, and running Gemini managed agents
- Available as beta as of October 27, 2026
View raw diff +5 −0
+ October 27, 2026 + Gemini API CLI (gemini-api) beta: Released the [Gemini API + CLI](https://ai.google.dev/gemini-api/docs/cli) (gemini-api), a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines. Use gemini-api on the Interactions API to generate text and media, analyze files, and run [Gemini managed + agents](https://ai.google.dev/gemini-api/docs/agents). See the [Gemini API CLI + guide](https://ai.google.dev/gemini-api/docs/cli) to get started.
- Pricing Oct 27, 2026, 12:00 PM
Google Gemini API pricing changed
Gemini 4 Argon billing clarification: thinking tokens and grounding instructions explicitly billed
Gemini 4 Argon note clarified: now specifies thinking tokens and grounding instructions are billedView raw diff +1 −1
- Note: Gemini 4 Argon is not available on the Free tier. + Note: Gemini 4 Argon is not available on the Free tier. Every token the model processes is counted and billed, including thinking tokens and internal tool system instructions and function declarations when using grounding.
- Update Oct 26, 2026, 6:00 PM
Google Gemini API changelog changed
Generate Content API now stores requests by default (store=true) for new paid-tier projects, requiring explicit opt-out via store=false parameter or Settings panel.
- Generate Content API (generateContent, streamGenerateContent, batchGenerateContent) storage enabled by default for new projects on paid tier
- Existing projects retain their current setting
- Opt out by setting store=false on individual requests or disabling logging in Settings panel of Logs and Datasets dashboard
View raw diff +2 −0
+ October 26, 2026 + Generate Content API storage on by default: New projects using the Generate Content API (generateContent, streamGenerateContent, and batchGenerateContent) on the paid tier now store requests by default (store=true), matching the Interactions API. Existing projects keep their current setting. To opt out, set store=false on individual requests or turn off Generate Content API logging in the Settings panel of the Logs and Datasets dashboard. See Logs and datasets for details.
- Pricing Oct 22, 2026, 6:00 PM
Google Gemini API pricing changed
Veo 3.1 video models deprecated and removed from pricing; multiple Gemini models with future price increases scheduled for 2026-2027.
Veo 3.1 models (Standard, Fast, Lite) and related video generation features deprecated and removed from pricing; will shutdown October 22, 2026View raw diff +0 −12
- Billing is based on total output token consumption, calculated at a rate of 5,792 tokens per second of 720p video. Under Standard pricing, this equates to an effective price of approximately $0.10 per second. - Warning: Veo 3.1 Preview (veo-3.1-generate-preview, veo-3.1-fast-generate-preview, and veo-3.1-lite-generate-preview) is deprecated and will be shut down on October 22, 2026; migrate to Gemini Omni Flash (gemini-omni-1.1-flash) or the GA models available through the Gemini Enterprise Agent Platform to avoid service disruption. - Veo 3.1 Standard video with audio price (default) - $0.40 (720p and 1080p) - $0.60 (4k) - Veo 3.1 Fast video with audio price (default) - $0.10 (720p) - $0.12 (1080p) - $0.30 (4k) - Veo 3.1 Lite video with audio price (default) - $0.05 (720p) - $0.08 (1080p)
- Update Oct 20, 2026, 6:00 AM
Google Gemini deprecations changed
Model deprecation and migration paths updated: Gemini flash-lite models now migrate to gemini-3.1-flash-lite, Imagen and Veo models redirect to gemini-nano-banana-2.1 or gemini-omni-1.1-flash, and new robotics models added with no shutdown date announced.
- gemini-2.0-flash-lite-preview migration target changed from gemini-2.5-flash-lite to gemini-3.1-flash-lite
- veo-3.0-generate-001 and veo-3.0-fast-generate-001 now redirect to gemini-omni-1.1-flash instead of veo-3.1-generate-preview
- gemini-robotics-er-2-preview and gemini-robotics-er-2-streaming-preview added with July 30, 2026 release date and no shutdown date announced
View raw diff +14 −12
- | gemini-2.0-flash-lite-preview | February 5, 2025 | December 9, 2025 | gemini-2.5-flash-lite | - | gemini-2.0-flash-lite-preview-02-05 | February 5, 2025 | December 9, 2025 | gemini-2.5-flash-lite | - | imagen-3.0-generate-002 | February 6, 2025 | November 10, 2025 | imagen-4.0-generate-001 | - | imagen-4.0-generate-preview-06-06 | June 24, 2025 | February 17, 2026 | imagen-4.0-generate-001 | - | imagen-4.0-ultra-generate-preview-06-06 | June 24, 2025 | February 17, 2026 | imagen-4.0-ultra-generate-001 | - | veo-3.0-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the Gemini Enterprise Agent Platform | - | veo-3.0-fast-generate-001 | September 9, 2025 | June 30, 2026 | veo-3.1-fast-generate-preview or the GA models on the Gemini Enterprise Agent Platform | - | veo-2.0-generate-001 | April 9, 2025 | June 30, 2026 | veo-3.1-generate-preview or the GA models on the Gemini Enterprise Agent Platform | - | veo-3.0-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-generate-preview | - | veo-3.0-fast-generate-preview | July 31, 2025 | November 12, 2025 | veo-3.1-fast-generate-preview | - | gemini-robotics-er-1.6-preview | April 14, 2026 | August 31, 2026 | gemini-robotics-er-2-preview | - | gemini-robotics-er-1.5-preview | September 25, 2025 | April 30, 2026 | gemini-robotics-er-1.6-preview | + | gemini-2.0-flash-lite-preview | February 5, 2025 | December 9, 2025 | gemini-3.1-flash-lite | + | gemini-2.0-flash-lite-preview-02-05 | February 5, 2025 | December 9, 2025 | gemini-3.1-flash-lite | + | imagen-3.0-generate-002 | February 6, 2025 | November 10, 2025 | gemini-nano-banana-2.1 | + | imagen-4.0-generate-preview-06-06 | June 24, 2025 | February 17, 2026 | gemini-nano-banana-2.1 | + | imagen-4.0-ultra-generate-preview-06-06 | June 24, 2025 | February 17, 2026 | gemini-nano-banana-2.1 | + | veo-3.0-generate-001 | September 9, 2025 | June 30, 2026 | gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform | + | veo-3.0-fast-generate-001 | September 9, 2025 | June 30, 2026 | gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform | + | veo-2.0-generate-001 | April 9, 2025 | June 30, 2026 | gemini-omni-1.1-flash or the GA models on the Gemini Enterprise Agent Platform | + | veo-3.0-generate-preview | July 31, 2025 | November 12, 2025 | gemini-omni-1.1-flash | + | veo-3.0-fast-generate-preview | July 31, 2025 | November 12, 2025 | gemini-omni-1.1-flash | + | gemini-robotics-er-2-preview | July 30, 2026 | No shutdown date announced | | + | gemini-robotics-er-2-streaming-preview | July 30, 2026 | No shutdown date announced | | + | gemini-robotics-er-1.6-preview | April 14, 2026 | August 31, 2026 | gemini-robotics-er-2-preview | + | gemini-robotics-er-1.5-preview | September 25, 2025 | April 30, 2026 | gemini-robotics-er-2-preview |
- Pricing Oct 20, 2026, 12:00 AM
Google Gemini API pricing changed
Multiple Gemini models seeing 2x price increases in late 2026/early 2027; Veo 3.1 Preview deprecated
Gemini 4 Argon pricing increases December 1, 2026: input $2→$4/1M, output $10→$20/1M tokensGemini 2.0 Flash pricing increases January 1, 2027: input $0.75→$1.50/1M, output $3.75→$7.50/1M tokensVeo 3.1 Preview models deprecated, shutting down October 22, 2026View raw diff +1 −0
+ Warning: Veo 3.1 Preview (veo-3.1-generate-preview, veo-3.1-fast-generate-preview, and veo-3.1-lite-generate-preview) is deprecated and will be shut down on October 22, 2026; migrate to Gemini Omni Flash (gemini-omni-1.1-flash) or the GA models available through the Gemini Enterprise Agent Platform to avoid service disruption. - Pricing Oct 17, 2026, 12:00 AM
Google Gemini API pricing changed
Clarified Gemini 4 Argon is unavailable on Free tier only (Google AI Pro restriction removed from note)
Gemini 4 Argon availability note updated: removed mention of Google AI Pro plan restrictionView raw diff +1 −1
- Note: Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan. + Note: Gemini 4 Argon is not available on the Free tier.
- Update Oct 15, 2026, 12:00 AM
Google Gemini API changelog changed
Documentation links updated from generic 'Latest model' references to specific Gemini 3.8 Flash and Gemini 3.6 Flash model guides.
- Links changed from 'Latest model guide' to 'Gemini 3.8 Flash guide' and 'Gemini 3.6 Flash guide'
- URL destinations changed from /latest-model endpoints to /whats-new-gemini-3.8 and /whats-new-gemini-3.6
View raw diff +4 −3
- the Latest model guide. - To learn more, see the Latest Gemini model - Latest Gemini Model + the Gemini 3.8 Flash guide. + To learn more, see the + Gemini 3.6 Flash guide. + Gemini 3.6 Flash guide
- Pricing Oct 15, 2026, 12:00 AM
Google Gemini API pricing changed
Gemini 1.5 Flash context caching prices cut in half
Gemini 1.5 Flash · context_caching_price$0.20, prompts ≤200k; $0.40, prompts >200k→$0.10, prompts ≤200k; $0.20, prompts >200kView raw diff +4 −0
+ $0.015 + $9.00, prompts > 200k tokens + $0.10, prompts <= 200k tokens + $0.20, prompts > 200k tokens
- Update Oct 14, 2026, 12:00 AM
Google Gemini API changelog changed
Gemini 4 Argon (gemini-4-argon) released as generally available on October 13, 2026, alongside updated documentation links for deprecated Flash models.
- Gemini 4 Argon (gemini-4-argon) released for complex coding, agentic, math, and science tasks
- gemini-3.7-flash deprecated and routed to gemini-3.8-flash
- gemini-3.5-flash deprecated and routed to gemini-3.6-flash
View raw diff +9 −2
- Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. - Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide. + October 13, 2026 + Gemini 4 Argon (gemini-4-argon) generally available (GA): Released + Gemini 4 Argon (gemini-4-argon), + our most capable model built for complex coding, agentic, math, and science + tasks. + For API changes, pricing, and migration guidance, see + What's new in Gemini 4 Argon. + Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. + Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide.
- Pricing Oct 13, 2026, 6:00 PM
Google Gemini API pricing changed
Gemini 4 models added with tiered pricing; all models scheduled for 2x price increase on December 1, 2026
Gemini 4 Argon introduced with prices $2-4/1M input, $10-20/1M output (scheduled increase Dec 1, 2026)Gemini 4 Mega prices: $1-2/1M input, $5-10/1M output (scheduled increase Dec 1, 2026)Gemini 4 Flash prices: $1-2/1M input, $5-10/1M output (scheduled increase Dec 1, 2026)Gemini 4 Flash Extended prices: $3.60-7.20/1M input, $18-36/1M output (scheduled increase Dec 1, 2026)View raw diff +26 −0
+ Our flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long-decode generation up to 1M tokens. + Note: Gemini 4 Argon is not available on the Free tier or on the Google AI Pro plan. + $2.00 through November 30, 2026. + $4.00 starting December 1, 2026. + $10.00 through November 30, 2026. + $20.00 starting December 1, 2026. + $0.10 through November 30, 2026. + $0.20 starting December 1, 2026. + $1.00 through November 30, 2026. + $2.00 starting December 1, 2026. + $5.00 through November 30, 2026. + $10.00 starting December 1, 2026. + $0.05 through November 30, 2026. + $0.10 starting December 1, 2026. + $1.00 through November 30, 2026. + $2.00 starting December 1, 2026. + $5.00 through November 30, 2026. + $10.00 starting December 1, 2026. + $0.05 through November 30, 2026. + $0.10 starting December 1, 2026. + $3.60 through November 30, 2026. + $7.20 starting December 1, 2026. + $18.00 through November 30, 2026. + $36.00 starting December 1, 2026. + $0.18 through November 30, 2026. + $0.36 starting December 1, 2026.
- Update Oct 13, 2026, 12:00 AM
Google Gemini API changelog changed
Deprecated Gemini models gemini-3.7-flash and gemini-3.5-flash are no longer available to select in Google AI Studio, with automatic API routing to their replacements.
- gemini-3.7-flash no longer available to select in Google AI Studio, auto-routed to gemini-3.8-flash
- gemini-3.5-flash no longer available to select in Google AI Studio, auto-routed to gemini-3.6-flash
View raw diff +2 −2
- Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. All requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. - Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. All requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide. + Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. + Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide.
- Update Oct 13, 2026, 12:00 AM
Google Gemini deprecations changed
Updated deprecation status descriptions for gemini-3.7-flash and gemini-3.5-flash to clarify they are not available in Google AI Studio but continue routing requests automatically without shutdown dates.
- gemini-3.7-flash shutdown date changed from 'No shutdown date announced' to 'N/A'
- gemini-3.5-flash shutdown date changed from 'No shutdown date announced' to 'N/A'
- Both models now noted as 'not available to select in Google AI Studio' with clarification that endpoints are not shutting down
View raw diff +2 −2
- | gemini-3.7-flash | August 13, 2026 | No shutdown date announced | gemini-3.8-flash (requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash) | - | gemini-3.5-flash | May 19, 2026 | No shutdown date announced | gemini-3.6-flash (requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash) | + | gemini-3.7-flash | August 13, 2026 | N/A | gemini-3.8-flash (not available to select in Google AI Studio; the endpoint is not shutting down and automatically routes API requests to gemini-3.8-flash) | + | gemini-3.5-flash | May 19, 2026 | N/A | gemini-3.6-flash (not available to select in Google AI Studio; the endpoint is not shutting down and automatically routes API requests to gemini-3.6-flash) |
- Update Oct 10, 2026, 6:00 AM
Google Gemini API changelog changed
Gemini 3.7 Flash and 3.5 Flash models are deprecated with automatic routing to newer versions (3.8 Flash and 3.6 Flash respectively).
- gemini-3.7-flash deprecated, requests routed to gemini-3.8-flash
- gemini-3.5-flash deprecated, requests routed to gemini-3.6-flash
- developers should update model strings to gemini-3.8-flash or gemini-3.6-flash
View raw diff +2 −0
+ Gemini 3.7 Flash deprecation: gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. All requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash. Update your model string to gemini-3.8-flash and review the Gemini 3.8 Flash guide. + Gemini 3.5 Flash deprecation: gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. All requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash ) and review the Gemini 3.6 Flash guide.
- Update Oct 10, 2026, 6:00 AM
Google Gemini deprecations changed
Requests to gemini-3.7-flash and gemini-3.5-flash are now automatically routed to newer model versions (gemini-3.8-flash and gemini-3.6-flash respectively).
- gemini-3.7-flash requests automatically route to gemini-3.8-flash
- gemini-3.5-flash requests automatically route to gemini-3.6-flash
View raw diff +2 −2
- | gemini-3.7-flash | August 13, 2026 | No shutdown date announced | | - | gemini-3.5-flash | May 19, 2026 | No shutdown date announced | | + | gemini-3.7-flash | August 13, 2026 | No shutdown date announced | gemini-3.8-flash (requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash) | + | gemini-3.5-flash | May 19, 2026 | No shutdown date announced | gemini-3.6-flash (requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash) |
- Pricing Oct 10, 2026, 12:00 AM
Google Gemini API pricing changed
Gemini API pricing increases effective January 1, 2027 across multiple models, with output prices doubling for audio/text models.
Multiple models: price increase scheduled for January 1, 2027 across Flash, Pro, Pro Audio, and Audio modelsView raw diff +0 −6
- $9.00 - $0.15 - $0.075 - $0.08 - $16.20 - $0.27
- Pricing Oct 9, 2026, 6:00 PM
Google Gemini API pricing changed
Search request free tier now spans all Gemini 3 and newer models instead of just 3.x versions
Search requests scope expanded from 'Gemini 3.x models' to 'all Gemini 3 and newer models'View raw diff +66 −81
- 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 requests per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests. - 5,000 prompts per month (free, shared across Gemini 3), then $14 / 1,000 search queries - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests for text and image-based grounding. - 5,000 free search requests per month (shared across all Gemini 3.x models), then $14 per 1,000 requests for text and image-based grounding. - $0.125 (input caching) through December 31, 2026. - $0.25 (input caching) starting January 1, 2027. - $0.0625 (input caching) through December 31, 2026. - $0.125 (input caching) starting January 1, 2027. - $0.025 (input caching) through December 31, 2026. - $0.05 (input caching) starting January 1, 2027. - $0.225 (input caching) through December 31, 2026. - $0.45 (input caching) starting January 1, 2027. - $0.125 (input caching) through December 31, 2026.
- Update Oct 9, 2026, 12:00 PM
Google Gemini API changelog changed
Deep Research Agent deep-research-pro-preview-12-2025 is deprecated and will shut down on October 23, 2026; users must migrate to deep-research-preview-04-2026 or deep-research-max-preview-04-2026.
- deep-research-pro-preview-12-2025 agent deprecation with shutdown on October 23, 2026
- migrate agent parameter to deep-research-preview-04-2026 or deep-research-max-preview-04-2026
- update interactions.create requests with new agent parameter
View raw diff +10 −0
+ October 8, 2026 + Deep Research Agent deep-research-pro-preview-12-2025 deprecation: + The deep-research-pro-preview-12-2025 agent is deprecated and will be + shut down on **October 23, + 2026**. + Migrate your requests to one of the newer [Deep + Research](https://ai.google.dev/gemini-api/docs/deep-research) agent versions: + To migrate, update the agent parameter in your interactions.create + requests from deep-research-pro-preview-12-2025 to + deep-research-preview-04-2026 (or deep-research-max-preview-04-2026).
- Update Oct 9, 2026, 12:00 PM
Google Gemini deprecations changed
Added three new deep-research model versions with April 2026 and December 2025 release dates and sunset information.
- deep-research-preview-04-2026 released April 21, 2026 with no shutdown date announced
- deep-research-max-preview-04-2026 released April 21, 2026 with no shutdown date announced
- deep-research-pro-preview-12-2025 released December 11, 2025 with October 23, 2026 shutdown date
View raw diff +3 −0
+ | deep-research-preview-04-2026 | April 21, 2026 | No shutdown date announced | | + | deep-research-max-preview-04-2026 | April 21, 2026 | No shutdown date announced | | + | deep-research-pro-preview-12-2025 | December 11, 2025 | October 23, 2026 | deep-research-preview-04-2026 |
- Update Oct 7, 2026, 6:00 AM
Google Gemini API changelog changed
Gemini API deprecation notice changed from having a specific shutdown date (October 29, 2026) to stating no shutdown date has been announced.
- shutdown date changed from October 29, 2026 to no shutdown date announced
- deprecation link to shutdown timeline removed
View raw diff +1 −2
- deprecated and will be shut down on - October 29, 2026. Migrate to + deprecated (no shutdown date announced). Migrate to
- Update Oct 7, 2026, 6:00 AM
Google Gemini deprecations changed
The shutdown date for gemini-3.1-flash-image model changed from October 29, 2026 to no announced shutdown date.
- gemini-3.1-flash-image shutdown date changed from October 29, 2026 to No shutdown date announced
View raw diff +1 −1
- | gemini-3.1-flash-image | May 28, 2026 | October 29, 2026 | gemini-nano-banana-2.1 | + | gemini-3.1-flash-image | May 28, 2026 | No shutdown date announced | gemini-nano-banana-2.1 |
- Pricing Oct 7, 2026, 6:00 AM
Google Gemini API pricing changed
Gemini 3.0 Flash and Flash-8B image generation prices increased up to 49% for 4K output
Gemini 3.0 Flash (image output) · output_token_price$0.0756 per 4K image→$0.113 per 4K imageGemini 3.0 Flash-8B (image output) · output_token_price$0.0378 per 4K image→$0.0567 per 4K imageView raw diff +4 −4
- and $0.0756 per 4K image*. - and $0.0378 per 4K image*. - Output images at 4K (4096x4096px) consume 2520 tokens and are equivalent to - $0.0756 per image. + and $0.113 per 4K image*. + and $0.0567 per 4K image*. + Output images at 4K (4096x4096px) consume 3780 tokens and are equivalent to + $0.113 per image.
- Update Oct 7, 2026, 12:00 AM
Google Gemini API changelog changed
Gemini Nano Banana 2.1 model released as GA and gemini-3.1-flash-image deprecated with October 29, 2026 shutdown date.
- Gemini Nano Banana 2.1 (gemini-nano-banana-2.1) released as high-efficiency image generation model
- gemini-3.1-flash-image model deprecated and will shut down October 29, 2026
- Supports wide and panoramic aspect ratios (1:4, 4:1, 1:8, 8:1) at 1K, 2K, and 4K resolutions
View raw diff +16 −0
+ October 6, 2026 + Gemini Nano Banana 2.1 generally available (GA): Released + Gemini Nano Banana 2.1 + (gemini-nano-banana-2.1), the latest high-efficiency image generation and + conversational editing model. An update to Nano Banana 2 + (gemini-3.1-flash-image ), + it maintains Flash-level speed and cost efficiency while delivering + significant improvements in visual quality, prompt adherence, multi-turn + character consistency, text rendering, and wide and panoramic aspect ratio + generation (1:4, 4:1, 1:8, 8:1) across 1K, 2K, and 4K + resolutions. + See the Image generation guide to get + Deprecation announcement: The gemini-3.1-flash-image model is + deprecated and will be shut down on + October 29, 2026. Migrate to + gemini-nano-banana-2.1.
- Update Oct 7, 2026, 12:00 AM
Google Gemini deprecations changed
Multiple preview models now have shutdown dates set to November 17, 2026, and new Nano Banana models section added with updated migration paths for image and TTS models.
- gemini-3.1-flash-tts-preview, gemini-3.1-flash-live-preview, and gemini-2.5-flash-native-audio-preview-12-2025 shutdown date changed to November 17, 2026
- New gemini-nano-banana-2.1 model added with release October 6, 2026
- Image models now migrate to gemini-nano-banana-2.1 instead of previous migration targets
View raw diff +17 −13
- | gemini-3.1-flash-image | May 28, 2026 | No shutdown date announced | | - | gemini-3.1-flash-tts-preview | February 26, 2026 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | - | gemini-3.1-flash-image-preview | February 26, 2026 | June 25, 2026 | gemini-3.1-flash-image | - | gemini-2.5-flash-image | October 2, 2025 | October 2, 2026 | gemini-3.1-flash-image-preview | - | gemini-2.5-flash-image-preview | May 7, 2025 | January 15, 2026 | gemini-2.5-flash-image | - | gemini-2.0-flash-preview-image-generation | May 7, 2025 | November 14, 2025 | gemini-2.5-flash-image | - | gemini-3.1-flash-live-preview | March 11, 2026 | No shutdown date announced | gemini-3.8-live | - | gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | No shutdown date announced | gemini-3.8-live | - | gemini-2.5-flash-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | - | gemini-2.5-pro-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | - | imagen-4.0-generate-001 | June 24, 2025 | August 17, 2026 | gemini-3.1-flash-image | - | imagen-4.0-ultra-generate-001 | June 24, 2025 | August 17, 2026 | gemini-3.1-flash-image | - | imagen-4.0-fast-generate-001 | June 24, 2025 | August 17, 2026 | gemini-3.1-flash-image | + | gemini-3.1-flash-tts-preview | February 26, 2026 | November 17, 2026 | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | + | gemini-3.1-flash-live-preview | March 11, 2026 | November 17, 2026 | gemini-3.8-live | + | gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | November 17, 2026 | gemini-3.8-live | + | gemini-2.5-flash-preview-tts | May 20, 2025 | November 17, 2026 | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | + | gemini-2.5-pro-preview-tts | May 20, 2025 | November 17, 2026 | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | + Nano Banana models + | gemini-nano-banana-2.1 | October 6, 2026 | No shutdown date announced | | + | gemini-3.1-flash-lite-image | June 30, 2026 | No shutdown date announced | | + | gemini-3.1-flash-image | May 28, 2026 | October 29, 2026 | gemini-nano-banana-2.1 | + | gemini-2.5-flash-image | October 2, 2025 | March 15, 2027 | gemini-3.1-flash-lite-image | + | gemini-3.1-flash-image-preview | February 26, 2026 | June 25, 2026 | gemini-nano-banana-2.1 | + | gemini-2.5-flash-image-preview | May 7, 2025 | January 15, 2026 | gemini-nano-banana-2.1 | + | gemini-2.0-flash-preview-image-generation | May 7, 2025 | November 14, 2025 | gemini-nano-banana-2.1 | + | imagen-4.0-generate-001 | June 24, 2025 | August 17, 2026 | gemini-nano-banana-2.1 | + | imagen-4.0-ultra-generate-001 | June 24, 2025 | August 17, 2026 | gemini-nano-banana-2.1 | + | imagen-4.0-fast-generate-001 | June 24, 2025 | August 17, 2026 | gemini-nano-banana-2.1 | + | gemini-omni-flash-preview | June 30, 2026 | October 22, 2026 | gemini-omni-1.1-flash |
- Pricing Oct 6, 2026, 6:00 PM
Google Gemini API pricing changed
Added image generation capabilities to Gemini 1.5 Pro and Flash with separate image output pricing
Gemini 1.5 Pro with images added: $1.50 input, $7.50 text output / $30.00 image output per 1M tokensGemini 1.5 Flash with images added: $0.75 input, $3.75 text output / $15.00 image output per 1M tokensView raw diff +16 −0
+ $1.50 (text/image/video) + $7.50 (text and thinking) + Equivalent to $0.0336 per 1K image*, + $0.0504 per 2K image*, + and $0.0756 per 4K image*. + $0.75 (text, image, video) + $3.75 (text and thinking) + Equivalent to $0.0168 per 1K image*, + $0.0252 per 2K image*, + and $0.0378 per 4K image*. + Image output is priced at $30 per 1,000,000 tokens (Standard) and + $15 per 1,000,000 tokens (Batch). Output images at 1K (1024x1024px) consume 1120 + tokens and are equivalent to $0.0336 per image. Output images at 2K + (2048x2048px) consume 1680 tokens and are equivalent to $0.0504 per image. + Output images at 4K (4096x4096px) consume 2520 tokens and are equivalent to + $0.0756 per image.
- Update Oct 2, 2026, 12:00 AM
Google Gemini API changelog changed
Updated documentation URL for Gemini 3.1 Flash Image Preview and Gemini 2.5 Flash Native Audio model reference.
- Gemini 3.1 Flash Image Preview URL changed from gemini-3.1-flash-image-preview to gemini-3.1-flash-image
- Gemini 2.5 Flash Native Audio URL changed to gemini-2.5-flash-native-audio-preview-12-2025
View raw diff +3 −2
- Launched Nano Banana 2, Gemini 3.1 Flash Image Preview, a high-efficiency - 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 Nano Banana 2, [Gemini 3.1 Flash Image + Preview](https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-image), a high-efficiency + 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.
- Update Oct 1, 2026, 6:00 AM
Google Gemini deprecations changed
Added new model variant gemini-2.5-computer-use-preview-10-2025 with October 7, 2025 release date and July 28, 2026 sunset date.
- Model: gemini-2.5-computer-use-preview-10-2025
- Release date: October 7, 2025
- Sunset date: July 28, 2026
View raw diff +1 −0
+ | gemini-2.5-computer-use-preview-10-2025 | October 7, 2025 | July 28, 2026 | gemini-3.8-flash | - Pricing Oct 1, 2026, 6:00 AM
Google Gemini API pricing changed
Gemini 2.5 Computer Use pricing reference updated from Gemini 3.5 Flash to Gemini 3.8 Flash
model_pricing_referenceGemini 2.5 Computer Use legacy pricing reference updated to Gemini 3.8 Flash pricingView raw diff +1 −2
- $2.50, prompts > 200k token - Charged as regular tokens per model pricing (e.g., standard Gemini 3.5 Flash pricing). See the Gemini 2.5 Computer Use Preview pricing table for legacy model rates. + Charged as regular tokens per model pricing (e.g., standard Gemini 3.8 Flash pricing).
- Update Sep 30, 2026, 6:00 AM
Google Gemini deprecations changed
Three veo-3.1 preview models now have announced shutdown dates of October 22, 2026 and specified migration path to gemini-omni-1.1-flash.
- veo-3.1-lite-generate-preview shutdown date changed from 'No shutdown date announced' to October 22, 2026
- veo-3.1-generate-preview shutdown date changed from 'No shutdown date announced' to October 22, 2026
- veo-3.1-fast-generate-preview shutdown date changed from 'No shutdown date announced' to October 22, 2026
View raw diff +3 −5
- | veo-3.1-lite-generate-preview | March 31, 2026 | No shutdown date announced | | - | veo-3.1-generate-preview | October 15, 2025 | No shutdown date announced | | - | veo-3.1-fast-generate-preview | October 15, 2025 | No shutdown date announced | | - | Deprecated models |||| - | gemini-omni-flash-preview | June 30, 2026 | September 30, 2026 | gemini-omni-1.1-flash | + | veo-3.1-lite-generate-preview | March 31, 2026 | October 22, 2026 | gemini-omni-1.1-flash | + | veo-3.1-generate-preview | October 15, 2025 | October 22, 2026 | gemini-omni-1.1-flash | + | veo-3.1-fast-generate-preview | October 15, 2025 | October 22, 2026 | gemini-omni-1.1-flash |
- Update Sep 25, 2026, 6:00 AM
Google Gemini deprecations changed
Deprecated gemini-3.1-flash-tts-preview model removed from table; migration path updated to gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts for preview TTS models.
- gemini-3.1-flash-tts-preview row deleted
- gemini-2.5-flash-preview-tts migration target changed from gemini-3.1-flash-tts-preview to gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts
- gemini-2.5-pro-preview-tts migration target changed from gemini-3.1-flash-tts-preview to gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts
View raw diff +2 −3
- | gemini-3.1-flash-tts-preview | April 13, 2026 | No shutdown date announced | | - | gemini-2.5-flash-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.1-flash-tts-preview | - | gemini-2.5-pro-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.1-flash-tts-preview | + | gemini-2.5-flash-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts | + | gemini-2.5-pro-preview-tts | May 20, 2025 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts |
- Pricing Sep 24, 2026, 6:00 PM
Google Gemini API pricing changed
Audio output pricing specified with per-10-second equivalents and January 2027 rate increases across Gemini 2.0 audio models
Audio pricing tiers added with per-10-second equivalents for multiple Gemini 2.0 audio models, with increases scheduled for January 1, 2027View raw diff +16 −0
+ Equivalent to $0.00225 per 10s audio* through December 31, 2026. + Equivalent to $0.0045 per 10s audio* starting January 1, 2027. + Equivalent to $0.001125 per 10s audio* through December 31, 2026. + Equivalent to $0.00225 per 10s audio* starting January 1, 2027. + Equivalent to $0.001125 per 10s audio* through December 31, 2026. + Equivalent to $0.00225 per 10s audio* starting January 1, 2027. + Equivalent to $0.00405 per 10s audio* through December 31, 2026. + Equivalent to $0.0081 per 10s audio* starting January 1, 2027. + Equivalent to $0.0015 per 10s audio* through December 31, 2026. + Equivalent to $0.003 per 10s audio* starting January 1, 2027. + Equivalent to $0.00075 per 10s audio* through December 31, 2026. + Equivalent to $0.0015 per 10s audio* starting January 1, 2027. + Equivalent to $0.00075 per 10s audio* through December 31, 2026. + Equivalent to $0.0015 per 10s audio* starting January 1, 2027. + Equivalent to $0.0027 per 10s audio* through December 31, 2026. + Equivalent to $0.0054 per 10s audio* starting January 1, 2027.
- Update Sep 23, 2026, 6:00 PM
Google Gemini API changelog changed
Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS models released as generally available with new Voices endpoint and voice design features.
- Gemini 3.8 Flash TTS (gemini-3.8-flash-tts) flagship model for studio-grade voice fidelity
- Gemini 3.8 Flash-Lite TTS (gemini-3.8-flash-lite-tts) replaces gemini-3.1-flash-tts-preview for production use
- Gemini API Voices endpoint (/v1beta/voices) released with 150+ prebuilt and custom voices
View raw diff +13 −0
+ September 22, 2026 + **Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS generally available + (GA)**: Released our next-generation text-to-speech (TTS) audio models and + the Gemini API Voices endpoint (/v1beta/voices): + **Gemini 3.8 Flash TTS + (gemini-3.8-flash-tts)**: Flagship creative TTS model engineered for studio-grade voice fidelity, nuanced acting, regional dialects, and long-form multi-turn stability. + **Gemini 3.8 Flash-Lite TTS + (gemini-3.8-flash-lite-tts)**: Fast, cost-efficient TTS model built to replace gemini-3.1-flash-tts-preview for high-throughput production and real-time voice agent cascades. + **Voice design, + Voice replication, and the + Extended Voice Library **: Create persistent custom vocal personas from text prompts, replicate voices with consent verification, and query 150+ prebuilt and custom voices. + See the Text-to-speech guide to get + started.
- Update Sep 23, 2026, 6:00 PM
Google Gemini deprecations changed
Three new text-to-speech models added to the Gemini API: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts with September 22, 2026 availability, and gemini-3.1-flash-tts-preview with February 26, 2026 availability.
- gemini-3.8-flash-tts available September 22, 2026
- gemini-3.8-flash-lite-tts available September 22, 2026
- gemini-3.1-flash-tts-preview available February 26, 2026 with migration path to gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts
View raw diff +3 −0
+ | gemini-3.8-flash-tts | September 22, 2026 | No shutdown date announced | | + | gemini-3.8-flash-lite-tts | September 22, 2026 | No shutdown date announced | | + | gemini-3.1-flash-tts-preview | February 26, 2026 | No shutdown date announced | gemini-3.8-flash-tts or gemini-3.8-flash-lite-tts |
- Pricing Sep 23, 2026, 6:00 PM
Google Gemini API pricing changed
Gemini 3.1 audio models added with audio-specific pricing through 2027
Audio model pricing introduced for Gemini 3.1 series (Nano, Flash, Pro) with dual text and audio pricing tiersView raw diff +48 −0
+ $0.50 (text) through December 31, 2026. + $1.00 (text) starting January 1, 2027. + $9.00 (audio) through December 31, 2026. + $18.00 (audio) starting January 1, 2027. + $0.125 (input caching) through December 31, 2026. + $0.25 (input caching) starting January 1, 2027. + $0.25 (text) through December 31, 2026. + $0.50 (text) starting January 1, 2027. + $4.50 (audio) through December 31, 2026. + $9.00 (audio) starting January 1, 2027. + $0.0625 (input caching) through December 31, 2026. + $0.125 (input caching) starting January 1, 2027. + $0.25 (text) through December 31, 2026. + $0.50 (text) starting January 1, 2027. + $4.50 (audio) through December 31, 2026. + $9.00 (audio) starting January 1, 2027. + $0.025 (input caching) through December 31, 2026. + $0.05 (input caching) starting January 1, 2027. + $0.90 (text) through December 31, 2026. + $1.80 (text) starting January 1, 2027. + $16.20 (audio) through December 31, 2026. + $32.40 (audio) starting January 1, 2027. + $0.225 (input caching) through December 31, 2026. + $0.45 (input caching) starting January 1, 2027. + $0.50 (text) through December 31, 2026. + $1.00 (text) starting January 1, 2027. + $6.00 (audio) through December 31, 2026. + $12.00 (audio) starting January 1, 2027. + $0.125 (input caching) through December 31, 2026. + $0.25 (input caching) starting January 1, 2027. + $0.25 (text) through December 31, 2026. + $0.50 (text) starting January 1, 2027. + $3.00 (audio) through December 31, 2026. + $6.00 (audio) starting January 1, 2027. + $0.0625 (input caching) through December 31, 2026. + $0.125 (input caching) starting January 1, 2027. + $0.25 (text) through December 31, 2026. + $0.50 (text) starting January 1, 2027. + $3.00 (audio) through December 31, 2026. + $6.00 (audio) starting January 1, 2027. + $0.025 (input caching) through December 31, 2026. + $0.05 (input caching) starting January 1, 2027. + $0.90 (text) through December 31, 2026. + $1.80 (text) starting January 1, 2027. + $10.80 (audio) through December 31, 2026. + $21.60 (audio) starting January 1, 2027. + $0.225 (input caching) through December 31, 2026. + $0.45 (input caching) starting January 1, 2027.
- Update Sep 22, 2026, 6:00 PM
Google Gemini API changelog changed
Gemini 2.5 model access is now restricted to users with prior active usage; new projects should use 3.5 Flash-Lite or 3.8 Flash models instead.
- 2.5 models limited to users who have actively used them in the past
- New projects should use 3.5 Flash-Lite or 3.8 Flash models
- 2.5 models will continue to be served through the API until further notice
View raw diff +2 −0
+ September 18, 2026 + Gemini 2.5 models access update: To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications.
- Update Sep 22, 2026, 6:00 PM
Google Gemini deprecations changed
Access to Gemini 2.5 models is now limited to users with past usage; new projects should use 3.5 Flash-Lite or 3.8 Flash models.
- 2.5 models access limited to users who have actively used them in the past
- recommended models for new projects are 3.5 Flash-Lite or 3.8 Flash
- 2.5 models remain available through the API and are not deprecated
View raw diff +2 −0
+ Note: To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications. + Note: To ensure reliable performance for everyone, we are limiting access to the 2.5 models to users who have actively used them in the past. These models are not deprecated and will continue to be served until further notice through the API. For any new projects, use our latest models: 3.5 Flash-Lite or 3.8 Flash. This helps us maintain sufficient capacity for both ongoing legacy workflows and new applications.
- Update Sep 18, 2026, 12:00 AM
Google Gemini API changelog changed
Antigravity Agent 09-2026 released with redesigned built-in tool parameters (PascalCase instead of snake_case) and new file editing approach using line-range replacements instead of full rewrites.
- antigravity-preview-09-2026 replaces antigravity-preview-05-2026
- File editing changed from write_file(path, content) full rewrite to replace_file_content(TargetFile, StartLine, EndLine, TargetContent, ReplacementContent)
- New tools added: find_by_name() and grep_search() for file and code search
View raw diff +22 −0
+ September 17, 2026 + Antigravity Agent 09-2026: Released antigravity-preview-09-2026, + which replaces and deprecates antigravity-preview-05-2026. + If you run on a remote sandbox (environment: "remote") and read only + output_text or model_output steps, update the agent string and nothing + else changes. + If you run tools locally (local_environment) or parse function_call + steps, the built-in tools changed. Parameters use PascalCase instead of + snake_case, and file edits use line-range replacements instead of full + rewrites. + | Capability | 05-2026 | 09-2026 | + |---|---|---| + | File creation | write_file(path, content) | write_to_file(TargetFile, CodeContent, Overwrite, Description) | + | File editing | write_file(path, content), full rewrite | replace_file_content(TargetFile, StartLine, EndLine, TargetContent, ReplacementContent) | + | File reading | read_file(path, offset, limit), byte offsets | view_file(AbsolutePath, StartLine, EndLine, ContentOffset) | + | Directory listing | list_files(path) | list_dir(DirectoryPath) | + | File and code search | None, agents used shell commands | find_by_name(SearchDirectory, Pattern, MaxDepth) and grep_search(SearchPath, Query, IsRegex) | + | Shell execution | code_execution(command, timeout_seconds) | Unchanged | + | Web search | google_search(queries) | Unchanged | + See the Antigravity Agent guide. + antigravity-preview-05-2026 shuts down on October 5, 2026, tracked on the + deprecations page.
- Update Sep 18, 2026, 12:00 AM
Google Gemini deprecations changed
Gemini API documentation now covers managed agents with deprecation/shutdown policy, introducing two preview agents with specific release and shutdown dates.
- antigravity-preview-09-2026 released September 17, 2026 with no shutdown date announced
- antigravity-preview-05-2026 released May 19, 2026 with shutdown date October 5, 2026
- managed agents section added to API model deprecation documentation
View raw diff +9 −4
- models in the Gemini API. A "deprecation " is the announcement that we - no longer provide support for a model, and that it will be "shut down " in - the near future. Once a model is "shutdown", it is completely - turned off, and the endpoint is no longer available. + models and for managed agents in the Gemini API. A "deprecation " is the + announcement that we no longer provide support for a model, and that it will be + "shut down " in the near future. Once a model is "shutdown", it is + completely turned off, and the endpoint is no longer available. + Managed agents + | Agent | Release date | Shutdown date | Recommended replacement | + | Preview agents |||| + | antigravity-preview-09-2026 | September 17, 2026 | No shutdown date announced | | + | antigravity-preview-05-2026 | May 19, 2026 | October 5, 2026 | antigravity-preview-09-2026 |
- Update Sep 16, 2026, 12:00 AM
Google Gemini API changelog changed
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking models released as generally available for real-time voice applications via the Live API.
- Gemini 3.8 Live (gemini-3.8-live) for low-latency voice agent experiences with interleaved reasoning
- Gemini 3.8 Live Extended Thinking (gemini-3.8-live-extended-thinking) for high-reasoning audio interactions
- Release date September 15, 2026
View raw diff +9 −0
+ September 15, 2026 + **Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking generally available + (GA)**: Released two new audio-to-audio models for real-time voice + applications using the Live API: + Gemini 3.8 Live (gemini-3.8-live ): The default option for most low-latency voice agent experiences and real-time dialogue without reasoning delays. Features interleaved reasoning, default asynchronous function calling, and full session client content updates. + Gemini 3.8 Live Extended Thinking (gemini-3.8-live-extended-thinking ): High-reasoning audio-to-audio model supporting background reasoning during live audio interactions, recommended when higher background reasoning is required. + To get started, see the Live API guide, the + Capabilities guide, and the + Thinking guide.
- Update Sep 16, 2026, 12:00 AM
Google Gemini deprecations changed
Model deprecation paths updated: older Gemini models now route to gemini-3.8-live instead of gemini-3.1-flash-live-preview, and two new gemini-3.8-live variants introduced with September 15, 2026 availability date.
- gemini-2.0-flash-live-001 deprecation target changed from gemini-3.1-flash-live-preview to gemini-3.8-live
- New models gemini-3.8-live and gemini-3.8-live-extended-thinking added with September 15, 2026 launch date
- gemini-3.1-flash-live-preview deprecation target changed to gemini-3.8-live
View raw diff +8 −4
- | gemini-2.0-flash-live-001 | April 9, 2025 | December 9, 2025 | gemini-3.1-flash-live-preview | - | gemini-3.1-flash-live-preview | March 11, 2026 | No shutdown date announced | | - | gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | No shutdown date announced | gemini-3.1-flash-live-preview | - | gemini-live-2.5-flash-preview | June 17, 2025 | December 9, 2025 | gemini-3.1-flash-live-preview | + | gemini-3.8-live | September 15, 2026 | No shutdown date announced | | + | gemini-3.8-live-extended-thinking | September 15, 2026 | No shutdown date announced | | + | gemini-3.8-live | September 15, 2026 | No shutdown date announced | | + | gemini-3.8-live-extended-thinking | September 15, 2026 | No shutdown date announced | | + | gemini-2.0-flash-live-001 | April 9, 2025 | December 9, 2025 | gemini-3.8-live | + | gemini-3.1-flash-live-preview | March 11, 2026 | No shutdown date announced | gemini-3.8-live | + | gemini-2.5-flash-native-audio-preview-12-2025 | December 12, 2025 | No shutdown date announced | gemini-3.8-live | + | gemini-live-2.5-flash-preview | June 17, 2025 | December 9, 2025 | gemini-3.8-live |
- Update Sep 15, 2026, 6:00 PM
Google Gemini API changelog changed
Lyria 3.5 music generation model status changed from public preview to generally available (GA).
- Lyria 3.5 changed from public preview to generally available (GA)
View raw diff +2 −2
- Lyria 3.5 in public preview: Released the next generation of Google's music - generation model: + Lyria 3.5 generally available (GA): Released the next generation of + Google's music generation model:
- Pricing Sep 11, 2026, 6:00 PM
Google Gemini API pricing changed
Removed specific pricing rates ($1.00, $2.00, $5.00) for Gemini Enterprise, simplifying enterprise tier description.
- Removed: $1.00 (text / image / video)
- Removed: $2.00 (audio)
- Removed: $5.00
View raw diff +1 −4
- For large-scale deployments with custom needs for security, support, and compliance, powered by Gemini Enterprise Agent Platform. - $1.00 (text / image / video) - $2.00 (audio) - $5.00 + For enterprise deployments, powered by Gemini Enterprise Agent Platform.
- Pricing Sep 8, 2026, 6:00 PM
Google Gemini API pricing changed
Major price increases for Gemini 2.0 Flash and 3.5 Pro/Sonnet effective January 1, 2027
Gemini 2.0 Flash family · price$1.00 input / $5.00 output per 1M tokens→$2.00 input / $10.00 output per 1M tokens effective January 1, 2027Gemini 3.5 Pro · price$1.50 input / $6.00 output per 1M tokens→$3.00 input / $12.00 output per 1M tokens effective January 1, 2027Gemini 3.5 Sonnet · price$0.75 input / $3.00 output per 1M tokens→$1.50 input / $6.00 output per 1M tokens effective January 1, 2027View raw diff +16 −5
- $2.00 (text / image / video / audio) - $10.00 - $1.00 (text / image / video / audio) - $2.00 (text / image / video / audio) - $10.00 + $1.00 (text / image / video / audio) through December 31, 2026. + $2.00 (text / image / video / audio) starting January 1, 2027. + $5.00 through December 31, 2026. + $10.00 starting January 1, 2027. + $0.10 through December 31, 2026. + $0.20 starting January 1, 2027. + $0.50 (text / image / video / audio) through December 31, 2026. + $1.00 (text / image / video / audio) starting January 1, 2027. + $2.50 through December 31, 2026. + $5.00 starting January 1, 2027. + $0.05 through December 31, 2026. + $0.10 starting January 1, 2027. + $1.00 (text / image / video / audio) through December 31, 2026. + $2.00 (text / image / video / audio) starting January 1, 2027. + $5.00 through December 31, 2026. + $10.00 starting January 1, 2027.