BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Hugin//Provider deadline board//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Hugin — Google deadlines
X-WR-CALDESC:Published end dates from Google tracked by Hugin. This subscri
 ption contains only Google dates\; it does not imply any unpublished or in
 ferred term.
X-PUBLISHED-TTL:PT12H
REFRESH-INTERVAL;VALUE=DURATION:PT12H
BEGIN:VEVENT
UID:google-gemini-api-preview-audio-shutdown@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:180
DTSTART;VALUE=DATE:20261117
DTEND;VALUE=DATE:20261118
SUMMARY:⚑ Google: Five Gemini API preview models reach their listed shutd
 own date: the speech previews gemini-2.5-flash-preview-tts\, gemini-2.5-pr
 o-preview-tts and gemini-3.1-flash-tts-preview\, and the live previews gem
 ini-3.1-flash-live-preview and gemini-2.5-flash-native-audio-preview-12-20
 25
DESCRIPTION:Five Gemini API preview models reach their listed shutdown date
 : the speech previews gemini-2.5-flash-preview-tts\, gemini-2.5-pro-previe
 w-tts and gemini-3.1-flash-tts-preview\, and the live previews gemini-3.1-
 flash-live-preview and gemini-2.5-flash-native-audio-preview-12-2025\n\nMO
 VES TO: From the table's replacement column: gemini-3.8-flash-tts or gemin
 i-3.8-flash-lite-tts for all three speech previews\, and gemini-3.8-live f
 or both live previews.\n\nBEFORE THIS DATE: Search your configuration for 
 the five exact model ids and repoint them: the three TTS ids at gemini-3.8
 -flash-tts or gemini-3.8-flash-lite-tts\, the two live ids at gemini-3.8-l
 ive. All five are preview endpoints\, which Google's deprecation policy tr
 eats differently from generally available models — the replacements are 
 generally available ids\, not previews.\n\nCaveat: One date\, five ids\, a
 nd only on the Gemini API surface. The table states a listed shutdown date
  is the earliest on which a model might be retired\, so November 17 is a f
 loor\; Google says it will communicate the exact date with advance notice.
  Replacing a speech or live-audio preview is not always a find-and-replace
  — voice\, latency and streaming behaviour can differ between a preview 
 and its generally available successor\, and the table says nothing about t
 hat.\n\nAuthoritative document (Gemini API deprecations): https://ai.googl
 e.dev/gemini-api/docs/deprecations\n\nTracked by Hugin: https://hugin.stud
 io/deadlines?provider=Google\nOnly dates a provider has published about it
 s own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: Search your configuration for the five exact model ids 
 and repoint them: the three TTS ids at gemini-3.8-flash-tts or gemini-3.8-
 flash-lite-tts\, the two live ids at gemini-3.8-live. All five are preview
  endpoints\, which Google's deprecation policy treats differently from gen
 erally available models — the replacements are generally available ids\,
  not previews.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-agent-platform-gemini-3-6-flash-retirement@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:182
DTSTART;VALUE=DATE:20261119
DTEND;VALUE=DATE:20261120
SUMMARY:⚑ Google: gemini-3.6-flash retires on Google Cloud's Gemini Enter
 prise Agent Platform\, four months after its release
DESCRIPTION:gemini-3.6-flash retires on Google Cloud's Gemini Enterprise Ag
 ent Platform\, four months after its release\n\nMOVES TO: gemini-3.8-flash
 \, named in the short-term availability table's replacement column.\n\nBEF
 ORE THIS DATE: If an Agent Platform call names gemini-3.6-flash\, move it 
 to gemini-3.8-flash before November 19. This is a short-term availability 
 model: the page says such a model stays active until a replacement ships a
 nd a date is announced\, so the date is new rather than moved\, and the an
 nouncement is the warning.\n\nCaveat: Google Cloud's schedule only\; the G
 emini API's deprecations page is a separate clock. The page commits to at 
 least 45 days' notice for a short-term model and says a posted retirement 
 date can be extended but not pulled earlier\, so this is a floor. A model 
 released July 21\, 2026 and retiring November 19\, 2026 is a four-month li
 fe by this desk's count — short\, and exactly what the short-term table 
 is for.\n\nAuthoritative document (Agent Platform model versions and lifec
 ycle): https://docs.cloud.google.com/gemini-enterprise-agent-platform/mode
 ls/model-versions\n\nTracked by Hugin: https://hugin.studio/deadlines?prov
 ider=Google\nOnly dates a provider has published about its own product app
 ear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: If an Agent Platform call names gemini-3.6-flash\, move
  it to gemini-3.8-flash before November 19. This is a short-term availabil
 ity model: the page says such a model stays active until a replacement shi
 ps and a date is announced\, so the date is new rather than moved\, and th
 e announcement is the warning.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-4-argon-paid-price-doubling@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:15
DTSTART;VALUE=DATE:20261201
DTEND;VALUE=DATE:20261202
SUMMARY:⚑ Google: Every per-token Gemini API price on gemini-4-argon doub
 les: Standard input from $2.00 to $4.00 and output from $10.00 to $20.00 p
 er million tokens\, with Batch\, Flex\, Priority\, the invite-only Contrib
 utor tier and context caching stepping the same way
DESCRIPTION:Every per-token Gemini API price on gemini-4-argon doubles: Sta
 ndard input from $2.00 to $4.00 and output from $10.00 to $20.00 per milli
 on tokens\, with Batch\, Flex\, Priority\, the invite-only Contributor tie
 r and context caching stepping the same way\n\nBEFORE THIS DATE: If you ru
 n Google's flagship reasoning model\, budget December at twice your Novemb
 er spend on it — a month before the Gemini 3 Flash family's own doubling
  on January 1\, 2027. A spend cap or prepaid balance set in dollars is rea
 ched twice as fast by unchanged traffic\, so check both before December 1.
 \n\nCaveat: Listed prices on Google's pricing page\, which reads '$2.00 th
 rough November 30\, 2026.' then '$4.00 starting December 1\, 2026.' for Ar
 gon's Standard input\; not a customer notice and not a bill. Every per-tok
 en rate on the model steps to exactly twice its current figure\; the groun
 ding charges carry no dated second figure. Argon has no free tier to be un
 affected. The step is a month earlier than the Flash family's January 1\, 
 2027 step recorded in google-gemini-flash-paid-price-doubling\, and Google
 's changelog names no Argon figure — the same pattern the September 28 r
 ecord found on the Flash models. Gemini Developer API only: Google Cloud's
  Agent Platform prices were not read\, and this desk holds no invoice.\n\n
 Authoritative document (Gemini API pricing): https://ai.google.dev/gemini-
 api/docs/pricing\n\nTracked by Hugin: https://hugin.studio/deadlines?provi
 der=Google\nOnly dates a provider has published about its own product appe
 ar here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,price-change
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: If you run Google's flagship reasoning model\, budget D
 ecember at twice your November spend on it — a month before the Gemini 3
  Flash family's own doubling on January 1\, 2027. A spend cap or prepaid b
 alance set in dollars is reached twice as fast by unchanged traffic\, so c
 heck both before December 1.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-flash-paid-price-doubling@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:549
DTSTART;VALUE=DATE:20270101
DTEND;VALUE=DATE:20270102
SUMMARY:⚑ Google: Paid Gemini API prices double for Gemini 3.6 Flash\, 3.
 7 Flash and 3.8 Flash: standard input from $0.75 to $1.50 and output from 
 $3.75 to $7.50 per million tokens\, with the 3.8 Flash TTS and 3.8 Flash-L
 ite TTS speech models doubling the same day
DESCRIPTION:Paid Gemini API prices double for Gemini 3.6 Flash\, 3.7 Flash 
 and 3.8 Flash: standard input from $0.75 to $1.50 and output from $3.75 to
  $7.50 per million tokens\, with the 3.8 Flash TTS and 3.8 Flash-Lite TTS 
 speech models doubling the same day\n\nBEFORE THIS DATE: Budget January at
  twice your current spend on these models. A spend cap or prepaid balance 
 set in dollars will be reached twice as fast by the same traffic\, so chec
 k both before the date.\n\nCaveat: Listed prices on Google's pricing page\
 , which reads '$0.75 through December 31\, 2026.' then '$1.50 starting Jan
 uary 1\, 2027.' for all three models' standard input\; not a customer noti
 ce and not a bill. Batch\, Flex\, Priority and context caching step the sa
 me way\, the free tier stays 'Free of charge'\, and Gemini 3.5 Flash has n
 o step. Google's changelog calls the 3.7 Flash rate introductory without n
 aming a figure and mentions no step for the others. Gemini API only: price
 s on Google Cloud's Agent Platform were not read.\n\nAuthoritative documen
 t (Gemini API pricing): https://ai.google.dev/gemini-api/docs/pricing\n\nT
 racked by Hugin: https://hugin.studio/deadlines?provider=Google\nOnly date
 s a provider has published about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,price-change
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: Budget January at twice your current spend on these mod
 els. A spend cap or prepaid balance set in dollars will be reached twice a
 s fast by the same traffic\, so check both before the date.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-agent-platform-gemini-3-7-flash-retirement@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:618
DTSTART;VALUE=DATE:20270128
DTEND;VALUE=DATE:20270129
SUMMARY:⚑ Google: gemini-3.7-flash retires on Google Cloud's Gemini Enter
 prise Agent Platform
DESCRIPTION:gemini-3.7-flash retires on Google Cloud's Gemini Enterprise Ag
 ent Platform\n\nMOVES TO: gemini-3.8-flash\, named in the short-term avail
 ability table's replacement column — the same successor the table names 
 for gemini-3.6-flash.\n\nBEFORE THIS DATE: If an Agent Platform call names
  gemini-3.7-flash\, move it to gemini-3.8-flash before January 28\, 2027. 
 Both of the flash models this table retires point at the same successor\, 
 so a caller on either can make the move once.\n\nCaveat: Google Cloud's sc
 hedule only. The page commits to at least 45 days' notice for a short-term
  availability model and says a posted date can be extended but not pulled 
 earlier. gemini-3.8-flash itself appears in the same table with no retirem
 ent date announced\, which under the table's own rule means it keeps answe
 ring until Google posts one.\n\nAuthoritative document (Agent Platform mod
 el versions and lifecycle): https://docs.cloud.google.com/gemini-enterpris
 e-agent-platform/models/model-versions\n\nTracked by Hugin: https://hugin.
 studio/deadlines?provider=Google\nOnly dates a provider has published abou
 t its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: If an Agent Platform call names gemini-3.7-flash\, move
  it to gemini-3.8-flash before January 28\, 2027. Both of the flash models
  this table retires point at the same successor\, so a caller on either ca
 n make the move once.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-2-5-flash-image-shutdown@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:328
DTSTART;VALUE=DATE:20270315
DTEND;VALUE=DATE:20270316
SUMMARY:⚑ Google: gemini-2.5-flash-image reaches its earliest listed shut
 down date in the Gemini API
DESCRIPTION:gemini-2.5-flash-image reaches its earliest listed shutdown dat
 e in the Gemini API\n\nMOVES TO: gemini-3.1-flash-lite-image\, named in th
 e deprecations table's replacement column as of 2026-10-07 — the same re
 placement Google Cloud's Agent Platform names for this id. Until a date be
 tween 2026-09-27 and 2026-10-07 the table named gemini-3.1-flash-image-pre
 view instead\, a preview listed with its own June 25\, 2026 shutdown.\n\nB
 EFORE THIS DATE: Repoint calls that name gemini-2.5-flash-image at gemini-
 3.1-flash-lite-image before March 15\, 2027. Google lists that as the earl
 iest possible shutdown\, so the model may keep answering past it — plan 
 for the date\, do not wait for a failure. Google Cloud's Agent Platform no
 w gives the same id the same date\, so a caller on either surface has one 
 deadline rather than two.\n\nCaveat: Google's table states listed shutdown
  dates are 'the earliest possible dates on which a model might be retired'
  — a floor\, not a schedule — and that it will give advance notice of 
 the exact date. The move from October 2\, 2026 to March 15\, 2027 is this 
 desk's reading of two dated fetches of the same page\, on September 27 and
  October 7\; Google published no release note this desk found announcing i
 t. On September 14 the page sent an unauthenticated plain client to a sign
 -in flow and was read through a rendering fetcher\; on September 27 and Oc
 tober 7 it answered curl.\n\nAuthoritative document (Gemini API deprecatio
 ns): https://ai.google.dev/gemini-api/docs/deprecations\n\nTracked by Hugi
 n: https://hugin.studio/deadlines?provider=Google\nOnly dates a provider h
 as published about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: Repoint calls that name gemini-2.5-flash-image at gemin
 i-3.1-flash-lite-image before March 15\, 2027. Google lists that as the ea
 rliest possible shutdown\, so the model may keep answering past it — pla
 n for the date\, do not wait for a failure. Google Cloud's Agent Platform 
 now gives the same id the same date\, so a caller on either surface has on
 e deadline rather than two.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-2-5-flash-image-agent-platform-retirement@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:328
DTSTART;VALUE=DATE:20270315
DTEND;VALUE=DATE:20270316
SUMMARY:⚑ Google: gemini-2.5-flash-image retires on Google Cloud's Gemini
  Enterprise Agent Platform\, after an extension from October 2\, 2026
DESCRIPTION:gemini-2.5-flash-image retires on Google Cloud's Gemini Enterpr
 ise Agent Platform\, after an extension from October 2\, 2026\n\nMOVES TO:
  gemini-3.1-flash-lite-image\, named in the September 14 release note and 
 the model-versions table — a different replacement from the one the Gemi
 ni API names for the same id.\n\nBEFORE THIS DATE: On Google Cloud\, plan 
 the move to gemini-3.1-flash-lite-image before March 15\, 2027. On the Gem
 ini API the same model id has an October 2\, 2026 earliest shutdown instea
 d — check which surface you call.\n\nCaveat: Extended once already\, on 
 September 14\, from October 2\, 2026. Google says Cloud retirement dates m
 ay be extended but will not be moved earlier than listed.\n\nAuthoritative
  document (Agent Platform model versions and lifecycle): https://docs.clou
 d.google.com/gemini-enterprise-agent-platform/models/model-versions\nAnnou
 nced in: https://docs.cloud.google.com/gemini-enterprise-agent-platform/re
 lease-notes\n\nTracked by Hugin: https://hugin.studio/deadlines?provider=G
 oogle\nOnly dates a provider has published about its own product appear he
 re.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:TENTATIVE
BEGIN:VALARM
ACTION:DISPLAY
DESCRIPTION:Google: On Google Cloud\, plan the move to gemini-3.1-flash-lit
 e-image before March 15\, 2027. On the Gemini API the same model id has an
  October 2\, 2026 earliest shutdown instead — check which surface you ca
 ll.
TRIGGER:-P7D
END:VALARM
END:VEVENT
BEGIN:VEVENT
UID:google-veo-3-1-preview-shutdown@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:334
DTSTART;VALUE=DATE:20261022
DTEND;VALUE=DATE:20261023
SUMMARY:⚑ Google: Three Veo 3.1 preview video models — veo-3.1-generate
 -preview\, veo-3.1-fast-generate-preview and veo-3.1-lite-generate-preview
  — reach their earliest listed shutdown date in the Gemini API
DESCRIPTION:Three Veo 3.1 preview video models — veo-3.1-generate-preview
 \, veo-3.1-fast-generate-preview and veo-3.1-lite-generate-preview — rea
 ch their earliest listed shutdown date in the Gemini API\n\nMOVES TO: gemi
 ni-omni-1.1-flash\, named in the deprecations table's replacement column f
 or all three — Google's Gemini Omni Flash video model\, not a newer Veo.
 \n\nBEFORE THIS DATE: If you generate video through the Gemini API with a 
 veo-3.1 preview model id\, test gemini-omni-1.1-flash before October 22: i
 t is a different model\, not a rename\, so check output and parameters\, n
 ot just the id. Google lists the date as the earliest possible shutdown\; 
 plan for it rather than waiting for a failure.\n\nCaveat: Google's lifecyc
 le table says listed shutdown dates 'indicate the earliest possible dates 
 on which a model might be retired'. October 21 update: the pricing page se
 parately states that all three Veo 3.1 previews 'will be shut down on Octo
 ber 22\, 2026' and names Gemini Omni Flash or GA models through the Gemini
  Enterprise Agent Platform as migration options. Read both current pages\;
  no endpoint was called and neither supplies a shutdown hour. Historical r
 eading: the date appeared in the revision stamped 'Last updated 2026-10-01
  UTC'\; the Internet Archive's September 26 copy said 'No shutdown date an
 nounced'\, and no changelog entry for them was found September 30. Gemini 
 API only\; this is not a new reading of Veo availability on Google Cloud's
  Agent Platform.\n\nAuthoritative document (Gemini API deprecations): http
 s://ai.google.dev/gemini-api/docs/deprecations\n\nTracked by Hugin: https:
 //hugin.studio/deadlines?provider=Google\nOnly dates a provider has publis
 hed about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-omni-flash-preview-shutdown@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:334
DTSTART;VALUE=DATE:20261022
DTEND;VALUE=DATE:20261023
SUMMARY:⚑ Google: Gemini Omni Flash Preview reaches its listed Gemini API
  shutdown date
DESCRIPTION:Gemini Omni Flash Preview reaches its listed Gemini API shutdow
 n date\n\nMOVES TO: gemini-omni-1.1-flash\, named in the lifecycle table\n
 \nBEFORE THIS DATE: Review uses of gemini-omni-flash-preview and test the 
 named replacement. The table lists October 22 without a shutdown hour.\n\n
 Caveat: Read October 22\, 2026: the lifecycle table prints gemini-omni-fla
 sh-preview June 30\, 2026 October 22\, 2026 gemini-omni-1.1-flash\, under 
 its earliest-possible-date caveat. The pricing page no longer carries this
  preview ID or yesterday's explicit October 22 warning. Removal from a pri
 ce page does not prove endpoint shutdown. No endpoint was called\, no exec
 ution outcome is filed\, and the earlier September 30 deprecation remains 
 a distinct historical event.\n\nAuthoritative document (Gemini API depreca
 tions): https://ai.google.dev/gemini-api/docs/deprecations\n\nTracked by H
 ugin: https://hugin.studio/deadlines?provider=Google\nOnly dates a provide
 r has published about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
BEGIN:VEVENT
UID:google-agent-platform-open-model-maas-retirement@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:333
DTSTART;VALUE=DATE:20261021
DTEND;VALUE=DATE:20261022
SUMMARY:⚑ Google: Sixteen open-model MaaS endpoints retire from Google Cl
 oud's Gemini Enterprise Agent Platform\, among them deepseek-ocr-maas\, gl
 m-5-maas\, gpt-oss-20b-maas\, kimi-k2-thinking-maas\, llama-3.3-70b-instru
 ct-maas and the qwen3 and multilingual-e5 endpoints
DESCRIPTION:Sixteen open-model MaaS endpoints retire from Google Cloud's Ge
 mini Enterprise Agent Platform\, among them deepseek-ocr-maas\, glm-5-maas
 \, gpt-oss-20b-maas\, kimi-k2-thinking-maas\, llama-3.3-70b-instruct-maas 
 and the qwen3 and multilingual-e5 endpoints\n\nMOVES TO: Per endpoint\, an
 d different for each\, the deprecations page's 'Self-deploy alternative': 
 the same model family deployed from Model Garden into your own project —
  DeepSeek-OCR\, DeepSeek-R1\, DeepSeek-V3.2\, DeepSeek-V3.1\, GLM 5\, GLM 
 4.7\, GPT OSS\, Kimi K2\, Llama 3.3\, MiniMax M2\, E5 Text Embedding (both
  multilingual-e5 endpoints)\, Qwen3\, Qwen3 Coder and Qwen3 Next (both qwe
 n3-next endpoints). Not a serverless endpoint\; Google names no managed re
 placement\, only 'alternative managed endpoints'.\n\nBEFORE THIS DATE: If 
 you call one of the sixteen *-maas model ids on Agent Platform\, decide be
 fore October 21 whether to self-deploy the listed alternative in your own 
 project or move to another managed model\, then change the model id in you
 r calls: Google says requests to a retired model id will fail.\n\nCaveat: 
 Google's Cloud schedule for its managed endpoints only\; the open models s
 tay available to self-deploy\, which Google's overview describes as runnin
 g in your own Google Cloud project\, unlike the serverless MaaS endpoints.
  Unlike the model-versions page\, the open-model deprecations page states 
 no rule on whether its dates can move. The alternative column names a mode
 l family\, not always the exact variant: 'GPT OSS' for gpt-oss-20b-maas\, 
 'Kimi K2' for kimi-k2-thinking-maas. Since the July 21 deprecation\, Googl
 e says new use of these endpoints 'may be restricted.'\n\nAuthoritative do
 cument (Agent Platform open model deprecations): https://docs.cloud.google
 .com/gemini-enterprise-agent-platform/models/deprecations/open-models\nAnn
 ounced in: https://docs.cloud.google.com/gemini-enterprise-agent-platform/
 release-notes\n\nTracked by Hugin: https://hugin.studio/deadlines?provider
 =Google\nOnly dates a provider has published about its own product appear 
 here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-2-5-agent-platform-retirement@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:332
DTSTART;VALUE=DATE:20261020
DTEND;VALUE=DATE:20261021
SUMMARY:⚑ Google: gemini-2.5-pro\, gemini-2.5-flash and gemini-2.5-flash-
 lite retire on Google Cloud's Gemini Enterprise Agent Platform (formerly V
 ertex AI)
DESCRIPTION:gemini-2.5-pro\, gemini-2.5-flash and gemini-2.5-flash-lite ret
 ire on Google Cloud's Gemini Enterprise Agent Platform (formerly Vertex AI
 )\n\nMOVES TO: Per model\, from the page's replacement column: gemini-3.5-
 flash for gemini-2.5-pro\; gemini-3.5-flash-lite or gemini-3.1-flash-lite 
 for gemini-2.5-flash\; gemini-3.1-flash-lite or Gemma 4 for gemini-2.5-fla
 sh-lite.\n\nBEFORE THIS DATE: On Google Cloud\, move calls off the three 2
 .5 models before October 20. Gemini API (AI Studio key) callers are on a d
 ifferent clock: no shutdown date there\, but since September 18 Google ser
 ves the 2.5 models only to users who have used them before.\n\nCaveat: Goo
 gle's Cloud schedule only. The page says 'While retirement timelines may b
 e extended\, they won't be moved to an earlier date than what is listed'\,
  so October 20 is the earliest these can go. The Gemini API deprecations p
 age lists the same three ids with 'No shutdown date announced'.\n\nAuthori
 tative document (Agent Platform model versions and lifecycle): https://doc
 s.cloud.google.com/gemini-enterprise-agent-platform/models/model-versions\
 n\nTracked by Hugin: https://hugin.studio/deadlines?provider=Google\nOnly 
 dates a provider has published about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
BEGIN:VEVENT
UID:google-antigravity-preview-05-2026-shutdown@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:275
DTSTART;VALUE=DATE:20261005
DTEND;VALUE=DATE:20261006
SUMMARY:⚑ Google: The managed agent antigravity-preview-05-2026 reaches i
 ts listed shutdown date in the Gemini API
DESCRIPTION:The managed agent antigravity-preview-05-2026 reaches its liste
 d shutdown date in the Gemini API\n\nMOVES TO: antigravity-preview-09-2026
  — the model page says 'Migrate to antigravity-preview-09-2026'\, and th
 e deprecations table names it as the recommended replacement.\n\nBEFORE TH
 IS DATE: If you call antigravity-preview-05-2026\, move to antigravity-pre
 view-09-2026 and retest before October 5. It is not a rename: Google's Sep
 tember 17 changelog says the built-in tools changed\, with PascalCase para
 meters and line-range file edits for anyone running tools locally.\n\nCave
 at: Google's table says listed shutdown dates 'indicate the earliest possi
 ble dates on which a model might be retired'\, so October 5 is a floor\, n
 ot a promise of the hour. The changelog\, the deprecations table and the a
 gent's own model page all carried the same date and replacement on Septemb
 er 28.\n\nAuthoritative document (Gemini API deprecations): https://ai.goo
 gle.dev/gemini-api/docs/deprecations\nAnnounced in: https://ai.google.dev/
 gemini-api/docs/changelog\n\nTracked by Hugin: https://hugin.studio/deadli
 nes?provider=Google\nOnly dates a provider has published about its own pro
 duct appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
BEGIN:VEVENT
UID:google-gemini-omni-flash-preview-deprecation@hugin.studio
DTSTAMP:20261106T182513Z
SEQUENCE:3179
DTSTART;VALUE=DATE:20260930
DTEND;VALUE=DATE:20261001
SUMMARY:⚑ Google: The gemini-omni-flash-preview endpoint is deprecated in
  the Gemini API
DESCRIPTION:The gemini-omni-flash-preview endpoint is deprecated in the Gem
 ini API\n\nMOVES TO: gemini-omni-1.1-flash\, released August 27\, 2026 as 
 the GA version of the same model.\n\nBEFORE THIS DATE: Search your configu
 ration for the exact string gemini-omni-flash-preview and repoint it at ge
 mini-omni-1.1-flash.\n\nCaveat: Google's sentence says the endpoint 'will 
 be deprecated'\, not removed\, and names the GA model in the neighbouring 
 entry rather than as a stated replacement. The changelog redirects an unau
 thenticated plain client to a sign-in page\, so this desk reads it through
  a rendering fetcher.\n\nAuthoritative document (Gemini API changelog): ht
 tps://ai.google.dev/gemini-api/docs/changelog\n\nTracked by Hugin: https:/
 /hugin.studio/deadlines?provider=Google\nOnly dates a provider has publish
 ed about its own product appear here.
URL:https://hugin.studio/deadlines?provider=Google
CATEGORIES:Google\,retirement
TRANSP:TRANSPARENT
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR