Skip to content
DriftCaught
GoogleTool change

total_thought_tokens

Tool change, announced 19 December 2025. Rerun the suite: Update 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.

What Google says changed

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.

Google: Gemini API changelog

announced 2025-12-19 . verified 2026-09-22

This section restates the provider. It adds no judgement the provider did not make, and it contains no measurement of ours.

Entry

Provider
Google
Models
total_thought_tokens
Change type
Tool change
Announced
2025-12-19
Verified
2026-09-22

What this kind of change typically touches

No impact note on this entry. A note is published only where a cited practitioner source supports it, and for this change we have none. The entry stands on the provider's announcement alone.

What to do this week

Rerun the suite

Update 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.

If you are on a plan

A tracked provider update triggers a rerun of your suite within 2 business days of the announcement, and you get a written verdict. That is one of the six guarantees on every plan.

See plansRead EV-RERUN

Other Google changes

GoogleDeprecation

gemini-2.5-pro, gemini-2.5-flash

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.

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.

Source: Google, Gemini API changelog . verified 2026-09-22

GoogleNew version

gemini-3.8-flash

Google released gemini-3.8-flash as generally available. The entry states it brings improvements for long horizon software engineering.

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.

Source: Google, Gemini API changelog . verified 2026-09-22

GoogleNew version

gemini-3.7-flash

Google released gemini-3.7-flash. The entry states it brings substantial improvements across software engineering.

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.

Source: Google, Gemini API changelog . verified 2026-09-22

Questions

How do I know this is accurate?
The entry links to Google's own page, and the date we read it is on this page. If the provider's page and this page disagree, the provider's page is right and we want to hear about it.
Does this mean my feature broke?
No. It means a thing your feature depends on changed. Whether anything about your output changed is a question only a rerun against your own dataset can answer, and that is what the recommended action is for.
Why is there no score or benchmark here?
Because we publish none. This site restates provider announcements and cites published practitioner guides. Any measurement we make belongs to the customer whose dataset produced it.

Sources

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.

Related