Reported News
Gemini 2.5 Pro and 2.5 Flash deprecated: API calls auto-route to newer models from December 1, 2026
Google's Gemini API changelog for November 2, 2026 says gemini-2.5-pro and gemini-2.5-flash are deprecated and gone from Google AI Studio. Effective December 1, 2026, requests to them automatically route to gemini-3.8-flash and gemini-3.5-flash-lite respectively, billed at those models' rates.
- Changes reported
- 5
- listed below, each from a source we read
- We tested
- Not tested yet
- reported from sources; we did not run it ourselves
- Gaps we flag
- 4
- things we could not verify
- Sources
- 2
- 2 primary, linked below
What changed
| # | What the source says | Status |
|---|---|---|
| 01 | gemini-2.5-pro and gemini-2.5-flash are now deprecated and can no longer be selected in Google AI Studio, per the November 2, 2026 entry in the Gemini API changelog. | Reported |
| 02 | From December 1, 2026, API requests to gemini-2.5-pro automatically route to gemini-3.8-flash and are billed at Gemini 3.8 Flash rates; requests to gemini-2.5-flash route to gemini-3.5-flash-lite at its rates. | Reported |
| 03 | Google lists breaking changes on the new targets: function calling and thought_signature validation, thinking_level replacing thinking_budget, and removed sampling parameters and prefilled model turns. | Reported |
| 04 | The deprecations page says API access to the 2.5 models is limited to users who have actively used them in the past, and lists December 1, 2026 as the shutdown date for both. | Reported |
| 05 | gemini-2.5-flash-lite is not deprecated and stays available through the API with no shutdown date announced. | Reported |
reported by the sourcemeasured or run by usnot verified
Primary source: Google: Gemini API changelog (November 2, 2026). We are the fast, independent index; the vendor’s own page is the source of record for this release.
Who it matters for
Anyone with gemini-2.5-pro or gemini-2.5-flash hard-coded in an app, agent or pipeline: change the model string and test against the migration guide before December 1, 2026, because the silent re-route changes both behaviour and billing and the listed breaking changes can fail requests that send thinking_budget or sampling parameters.
Teams already on Gemini 3.x models, or using gemini-2.5-flash-lite, can ignore it for now.
In the source’s words
“is deprecated and is no longer available to select in Google AI Studio.”
“Access through the API is limited to existing users who have actively used it in the past.”
“is not deprecated and remains available through the API until further notice.”
What we have not verified
- We did not run requests against the deprecated models or the routing targets.
- We did not compare per-token prices; Google says routed calls are billed at the new models' rates, so costs may go up or down depending on usage.
- The changelog entry is dated November 2, 2026 without a time, so the source publish time is set to midnight UTC on that date.
- Whether Vertex AI follows the same schedule is not covered by these Gemini API pages.
This brief is Reported: written from the sources below, not from running the release ourselves.
Sources
- Google: Gemini API changelog (November 2, 2026)primary source · fetched 2026-11-03
- Google: Gemini API deprecationsprimary source · fetched 2026-11-03
Related
Spotted an error? See our corrections policy or email the address on the contact page. Markdown version for agents: /news/gemini-2-5-pro-flash-deprecated-auto-route-december-1.md
Want these briefs in your Google Top Stories? Add Agentic Weekly as a preferred source on Google.
Newsletter
The Weekly Verdict. Free, every Monday.
A free email every Monday: the week's few big AI releases, then 5 short use cases for the new models, each with a prompt you can paste.
Free. Double opt-in. One click to unsubscribe.