Model retirements / Gemini 2.5 Flash and Gemini 2.5 Pro

Google deprecation · 11 days left

Gemini 2.5 Flash and Gemini 2.5 Pro retire from the Google API on 1 December 2026.

Google shuts down gemini-2.5-flash and gemini-2.5-pro from 1 December 2026. It names gemini-3.5-flash-lite and gemini-3.8-flash as the replacements. Source: Google: Gemini API deprecations, checked 9 Nov 2026.

Retirement date
1 December 2026
Days left
11
Official replacements
Gemini 3.5 Flash-Lite and Gemini 3.8 Flash

Paste your prompt. See how the replacement answers it.

We run it on Gemini 2.5 Flash, Gemini 3.5 Flash Lite, DeepSeek V4.1 Flash 1017 and Claude Haiku 5.5: the model you're on, its official replacement and up to two cheaper current models. Same test cases for each, every answer checked, with cost and speed side by side.

$10 of free test credit · No credit card needed · We keep a pasted prompt for 24 hours (privacy)

A real example · Experiment 01

What you give us, and what you get back.

A test we ran and published, with Gemini 3.8 Flash among the models. Yours has the same columns, with the model you're on now beside its replacement.

  1. 1You paste a prompt

    You are the friendly assistant for a small hotel. Answer the guest's message helpfully using the hotel info.

    An assistant answering guests from the hotel's own information, without inventing policy or promising outcomes.

  2. 2We test it

    • 18 test cases the prompt had not seen, each run twice
    • 7 models answer every case
    • 7 checks mark each answer right or wrong

    We also rewrote the prompt once. The figures are for the rewritten prompt.

  3. 3You get quality, cost and speed for each model

    ModelAnswers that passCost per 1,000Time per answer
    Best qualityGPT-6.1 Sol low thinking94% 34 of 36$1.403.8 s
    Best valueDeepSeek V4.1 Flash medium thinking81% 29 of 36$0.255.0 s
    Fast and solidGemini 3.8 Flash low thinking81% 29 of 36$0.882.9 s

    Best value: DeepSeek V4.1 Flash. 81% of answers passed at $0.25 per 1,000, against 94% at $1.40 for GPT-6.1 Sol. Their likely ranges overlap, so this test alone does not show a clear lead.

Tested 4 November 2026. Cost is per 1,000 answers; time is the typical time for one answer. See every answer and the method →

What's retiring, and what replaces it

RetiringOfficial replacementOur data
gemini-2.5-flash
Gemini 2.5 Flash
gemini-3.5-flash-lite
Gemini 3.5 Flash-Lite
Gemini 2.5 Flash · Gemini 3.5 Flash-Lite · the two compared
gemini-2.5-pro
Gemini 2.5 Pro
gemini-3.8-flash
Gemini 3.8 Flash
Gemini 2.5 Pro · Gemini 3.8 Flash · the two compared

Google gives this as the earliest possible shutdown date and says it will confirm the exact date with advance notice.

Gemini 2.5 Flash-Lite is not on the list: Google says it stays available until further notice.

Dates and replacements are Google's, from https://aistudio.google.com/docs/deprecations. Plan to have moved before the date; check the source for any change.

Why a swap can quietly change your outputs

A replacement may score higher on benchmarks, but that doesn't mean it does your task the same way. Usually nothing errors. The answers change, and your users may notice before you do.

Format
The new model may wrap JSON in a code fence, add Markdown, change headings or drop a field your code reads.
Tone
Warmer, blunter, more formal or more chatty. It reads as a different writer.
Refusals
It may refuse or hedge on inputs the old model handled, or answer ones it used to decline.
Length
Answers often get longer or shorter. That can break a limit on screen, in an SMS or in a feed.
Instructions
Edge-case rules in your prompt (never mention X, always end with Y) are where models differ most.
Cost and speed
Price per token, tokens per answer and thinking time all change, so the cost of each answer can move even at a similar list price.

Re-test before you switch

  1. Find every place your code, config and environment variables name the old model ID.
  2. Collect 10 to 20 real inputs, including the awkward ones that went wrong before.
  3. Write down what a good answer does: its format, length, what it must say and must not.
  4. Run the old and the new model on the same prompt and the same inputs, side by side.
  5. Read the answers that changed, not just the pass rate.
  6. Compare cost and time per answer, then adjust the prompt if you need to and test again.
  7. Switch before the date, and keep the cases as a regression test for the next change.

We can run both sides of these swaps for you: Gemini 2.5 Flash against Gemini 3.5 Flash-Lite; Gemini 2.5 Pro against Gemini 3.8 Flash.

All model retirements and tool shutdowns