« ### Task:
Respond to the user query using the provided context, incorporating inline citations in the format [id] only when the tag includes an explicit id attribute (e.g., ). ### Guidelines:
— If you don’t know the answer, clearly state that.
— If uncertain, ask the user for clarification.
— Respond in the same language as the user’s query.
— If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
— If the answer isn’t present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
— Only include inline citations using [id] (e.g., [1], [2]) when the tag includes an id attribute. — Do not cite if the tag does not contain an id attribute.
— Do not use XML tags in your response.
— Ensure citations are concise and directly related to the information provided. ### Example of Citation:
If the user asks about a specific topic and the information is found in a source with a provided id attribute, the response should include the citation like in the following example: «According to the study, the proposed method increases efficiency by 20% [1].» ### Output:
Provide a clear and direct response to the user’s query, including inline citations in the format [id] only when the tag with id attribute is present in the context.
This update only applies to Vertex AI; if you have projects that use Gemini on AI
Studio, other retirement dates may apply and can be found in the Gemini
deprecations documentation.
We understand this change may require some planning and have provided
additional information below to help you with the transition.
What you need to know
Key changes:
Gemini 2.5 Pro, Gemini 2.5 Flash, and 2.5 Flash Lite on Vertex AI will be
discontinued no earlier than October 16, 2026.
We will provide at least 6 months notice once a discontinuation date is
confirmed.
Potential impact:
10.04.2026, 15:21 почта builded — [Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or Flash Lite before Oct 16, 2026
https://mail.google.com/mail/u/0/?ik=cf99d96bf8&view=pt&search=all&permthid=thread-f:1861997767729919083&simpl=msg-f:18619977677299… 1/3
migration guide.
Thanks for choosing Vertex AI.
10.04.2026, 15:21 почта builded — [Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or Flash Lite before Oct 16, 2026
https://mail.google.com/mail/u/0/?ik=cf99d96bf8&view=pt&search=all&permthid=thread-f:1861997767729919083&simpl=msg-f:18619977677299… 2/3
DOCUMENTATION
SUPPORT
– The Google Cloud Team
© 2026 Google LLC 1600 Amphitheatre Parkway, Mountain View, CA 94043
You’ve received this mandatory service announcement to update you about important changes to
Google Cloud or your account. 10.04.2026, 15:21 почта builded — [Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or Flash Lite before Oct 16, 2026
https://mail.google.com/mail/u/0/?ik=cf99d96bf8&view=pt&search=all&permthid=thread-f:1861997767729919083&simpl=msg-f:18619977677299… 3/3
так нужно проверить а доступны ли они мне? » ### Task:
Respond to the user query using the provided context, incorporating inline citations in the format [id] only when the tag includes an explicit id attribute (e.g., ). ### Guidelines:
— If you don’t know the answer, clearly state that.
— If uncertain, ask the user for clarification.
— Respond in the same language as the user’s query.
— If the context is unreadable or of poor quality, inform the user and provide the best possible answer.
— If the answer isn’t present in the context but you possess the knowledge, explain this to the user and provide the answer using your own understanding.
— Only include inline citations using [id] (e.g., [1], [2]) when the tag includes an id attribute. — Do not cite if the tag does not contain an id attribute.
— Do not use XML tags in your response.
— Ensure citations are concise and directly related to the information provided. ### Example of Citation:
If the user asks about a specific topic and the information is found in a source with a provided id attribute, the response should include the citation like in the following example: «According to the study, the proposed method increases efficiency by 20% [1].» ### Output:
Provide a clear and direct response to the user’s query, including inline citations in the format [id] only when the tag with id attribute is present in the context.
This update only applies to Vertex AI; if you have projects that use Gemini on AI
Studio, other retirement dates may apply and can be found in the Gemini
deprecations documentation.
We understand this change may require some planning and have provided
additional information below to help you with the transition.
What you need to know
Key changes:
Gemini 2.5 Pro, Gemini 2.5 Flash, and 2.5 Flash Lite on Vertex AI will be
discontinued no earlier than October 16, 2026.
We will provide at least 6 months notice once a discontinuation date is
confirmed.
Potential impact:
10.04.2026, 15:21 почта builded — [Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or Flash Lite before Oct 16, 2026
https://mail.google.com/mail/u/0/?ik=cf99d96bf8&view=pt&search=all&permthid=thread-f:1861997767729919083&simpl=msg-f:18619977677299… 1/3
migration guide.
Thanks for choosing Vertex AI.
10.04.2026, 15:21 почта builded — [Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or Flash Lite before Oct 16, 2026
https://mail.google.com/mail/u/0/?ik=cf99d96bf8&view=pt&search=all&permthid=thread-f:1861997767729919083&simpl=msg-f:18619977677299… 2/3
MY CONSOLE
Medvedovskyi, Gennadii
[Action Advised] Migrate Vertex Gemini API workflows to Gemini 3 Pro, Flash or
Flash Lite before Oct 16, 2026
1 письмо
Google Cloud 9 апреля 2026г. в 14:57
Ответить: Google Cloud
Кому: admin@builded.info Hello Gennadii,
You’re receiving this communication because you have projects currently using
Gemini 2.5 models.
As we continue to advance our Gemini model capabilities, we will be discontinuing
certain Generative AI models on Vertex AI.
While online documentation previously communicated a June 2026 retirement date
for Gemini 2.5 Pro, Flash and Flash Lite, we have extended the timeline to no
earlier than October 16, 2026, to better support your transition. A confirmed
discontinuation date will be set once Gemini 3 is Generally Available (GA).
This update only applies to Vertex AI; if you have projects that use Gemini on AI
так я им сейчас не должен?