16 tracked changes to Google models in the twelve months to 2026-09-24, newest first. Each one cites Google's own announcement and carries one recommended action.
What we track
Models named
17
Entries
16
Deprecation
2
New version
7
Tool change
4
Pricing
2
Weight refresh
1
Named in this log
gemini-2.5-pro, gemini-2.5-flash, gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.5-flash, Flex, Priority, Built-in Tools and Function Calling Combination, Grounding with Google Maps, gemini-3-pro-preview, gemini-3.1-pro-preview, gemini-3.1-pro-preview-customtools, gemini-3-flash-preview, total_thought_tokens, Grounding with Google Search
These are the ids and API surfaces Google named in the announcements we track. They are what the entries below are about, and they are not a claim about everything Google ships.
Google limited access to Gemini 2.5 models to projects that are actively using them. The entry points developers to Gemini 3.5 Flash-Lite or Gemini 3.8 Flash instead.
Chat assistant: A forced move changes the model behind every answer. Google's own documentation says most production apps should use a specific stable model, and hedges only that stable models usually do not change.
RAG: When the generating model is replaced, the answer is scored again for faithfulness, which Ragas defines as the share of claims in a response that can be inferred from the retrieved context. It scores grounding in that context, not factual truth.
Plan a migrationCheck whether any project still calls a Gemini 2.5 model id, and open a migration ticket for the ones that do before new projects lose access.
Google released gemini-3.8-flash as generally available. The entry states it brings improvements for long horizon software engineering.
Agent: Long horizon work is mostly tool calls. Arize Phoenix reconstructs two signals from a trace, tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path.
Generation: Generated text has no single correct answer to match against, so the tempting fix when a new model writes differently is to move the expected outputs. Galtea warns against updating ground truth to match model behaviour.
Rerun the suiteQueue gemini-3.8-flash into the next comparison run against the Flash model you use now, and record the result before moving traffic.
Google released gemini-3.7-flash. The entry states it brings substantial improvements across software engineering.
Chat assistant: Putting the new Flash model beside the one you pin is pairwise comparison of two application versions, one of the four evaluator types LangSmith documents, alongside human review, rule based code functions and LLM as judge.
Rerun the suiteAdd gemini-3.7-flash to the comparison run you already schedule for Flash tier models, and note where its answers differ from the version you pin.
Google released gemini-3.6-flash and gemini-3.5-flash-lite as generally available. The same entry deprecates the sampling parameters temperature, top_p and top_k.
Classification: Classifiers usually pin sampling parameters in the request builder, so a deprecation here is a change to caller code rather than to the model you chose. Anthropic made the same kind of change from Claude Opus 4.7 onward, where a non default temperature, top_p or top_k returns a 400 error.
Extraction: Removing sampling parameters changes the request every fixture runs through. Braintrust tracks every change to a dataset so experiments can pin to specific versions, which is what keeps the run before the edit comparable with the run after it.
Revisit the promptSearch your request builders for temperature, top_p and top_k on Gemini calls and plan their removal, then rerun the affected cases with the parameters dropped.
Google launched public preview support for the Computer Use tool in Gemini 3.5 Flash.
Agent: Future AGI describes scoring an agent at four resolutions, end to end, trajectory, step and turn, writes that a high end to end score can hide bad tool calls, and warns that strong per step scores can still miss that the agent pursued the wrong goal.
Rerun the suiteRun your agent cases with the Computer Use tool enabled on gemini-3.5-flash and keep the recorded tool calls, not only the final answers.
Google released gemini-3.5-flash as generally available. The same entry launches Managed Agents in public preview and an antigravity-preview-05-2026 general purpose managed agent.
Chat assistant: Moving a preview pin onto a generally available id is the direction Google's own documentation points, saying most production apps should use a specific stable model and hedging that stable models usually do not change.
Agent: A managed agent in public preview carries a shorter clock than a stable model. Google says Gemini preview models may be used in production but will be deprecated with at least 2 weeks' notice.
Rerun the suiteMove any preview Flash pin onto the generally available id and run the suite once to see whether the outputs shifted.
Google released the Built-in Tools and Function Calling Combination feature, which makes it possible to use Gemini's built-in tools alongside custom function calling tools in a single API call. The same changelog entry says Grounding with Google Maps is now supported for Gemini 3 models going forward.
Agent: Mixing built in tools with custom functions changes which tool is chosen and in what order. Arize Phoenix describes reading tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path.
Rerun the suiteIf you combine a built in tool with your own functions in one call, record the tool calls for a set of cases before and after, so a changed selection order is visible.
RAG: A retrieval feature pinned to a preview id can lose that id on short notice. Google says Gemini preview models may be used in production but will be deprecated with at least 2 weeks' notice.
Classification: A classifier that runs unattended is the last place a shutdown gets noticed. Google's documentation says most production apps should use a specific stable model, and hedges that stable models usually do not change.
Plan a migrationReplace any gemini-3-pro-preview pin with a current Gemini 3 id and rerun the affected suites, since the preview id no longer serves.
Google released gemini-3.1-pro-preview and launched a gemini-3.1-pro-preview-customtools variant.
Agent: A custom tools variant changes how the agent reaches its answer, not only what it answers. Future AGI describes scoring an agent at four resolutions, end to end, trajectory, step and turn, and writes that a high end to end score can hide bad tool calls, while strong per step scores can still miss that the agent pursued the wrong goal.
Rerun the suiteRun the Pro tier comparison against gemini-3.1-pro-preview, and keep the custom tools variant in a separate run so tool behaviour differences stay visible.
Google launched support for the Computer Use tool in gemini-3-pro-preview and gemini-3-flash-preview.
Agent: Arize Phoenix describes reconstructing tool_path, the ordered tool calls with their arguments, and tool_io, what each tool was called with and what it returned, and warns that a correct looking answer can come from a broken path.
Rerun the suiteBoth ids are preview models, so keep the rerun cycle short for anything built on this tool, and record which preview id each run used.
Google changed the latest aliases to point to Gemini 3 models.
Chat assistant: Google says a latest alias points at the most recent release of a model variation and is hot swapped with every new release of that variation, so an assistant served through the alias changes with no action on your side.
RAG: An answer path that reads retrieved documents is easier to reason about when the model id is explicit. Google's documentation says most production apps should use a specific stable model, and hedges that stable models usually do not change.
Generation: Future AGI writes that OpenAI, Anthropic, Google and most frontier providers update model weights without a major version bump. That is one vendor's characterisation of the market, and Google's documented alias behaviour is the provider's own side of it.
Re-pin the versionReplace any latest alias in your configuration with an explicit model id, and rerun the suites that were served through the alias to see what moved.
Google renamed the total_reasoning_tokens field to total_thought_tokens, saying the new name better aligns with the concept of thoughts in thinking models. The change affects v1beta.
Rerun the suiteUpdate anything that reads total_reasoning_tokens from a v1beta response, including cost dashboards and eval harness logging, then run a batch and check the field is populated.
Google launched gemini-3-flash-preview. The entry describes frontier class performance and upgraded reasoning capabilities.
Summarisation: A summariser pinned to a preview id runs on a shorter clock. Google says Gemini preview models may be used in production but will be deprecated with at least 2 weeks' notice.
Rerun the suiteAdd gemini-3-flash-preview to your Flash tier comparison run, and keep the preview id out of production pins until a stable id ships.
Google launched gemini-3-pro-preview. The entry describes state of the art reasoning and multimodal capabilities.
Chat assistant: A first baseline on a preview id is a baseline with a short life. Google says Gemini preview models may be used in production but will be deprecated with at least 2 weeks' notice.
Rerun the suiteSet up a first baseline run against gemini-3-pro-preview so later Gemini 3 versions have something to be compared with.
Change-log entries restate provider announcements with sources and dates. Impact notes cite public practitioner reports. The site publishes no measurements of its own on any model.
Questions about Google changes
Where do the Google entries come from?
From Google's own pages. Every entry links to the changelog, release note, deprecation table or pricing page that carries the announcement. Nothing here is sourced from coverage or from reports by users.
Does DriftCaught test Google models?
No. This site publishes no measurement of any model. We restate what the provider announced and cite published practitioner guides for what that kind of change typically touches.
What should I do when Google announces something?
Check whether the model id you run is named. If it is, rerun your suite against your dataset and read the result against the thresholds you agreed. Each entry carries one recommended action: rerun, re-pin, re-prompt or migrate.
Is every Google announcement here?
No. The log covers changes to the model families we track for customers, inside a twelve-month window, where the announcement is reachable on Google's own domain. Send us a link to anything missing and we will add it.