// AI Platform Drift

Per-message effort changes now available on Google Cloud Claude models

Claude Platform release notes · published 2026-09-09 20:34 UTC
FYI VERIFY_ONLY APIMODEL
WHAT CHANGEDPer-message effort changes (beta) are now supported on Google Cloud for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5. This requires the mid-conversation-output-config-2026-07-01 beta header, matching the existing implementation on other platforms.
WHY IT MATTERSIf you run Claude on Google Cloud and want to adjust model effort mid-conversation (for example, switching between speed and quality), you can now do so without changing platforms. Previously this beta feature was unavailable on Google Cloud deployments.
WHAT TO DOIf you use Claude on Google Cloud and want per-message effort control, test the mid-conversation-output-config-2026-07-01 header with one of the three supported models in a non-production environment to verify the behavior matches your use case.
Model-reported confidence 85% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
 https://platform.claude.com/docs/en/release-notes/overview#september-3-2026
 Thu, 03 Sep 2026 00:00:00 GMT
 
-Version 1.30.0 of the ant CLI adds ant apply, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, run ant apply, and approve the plan it prints. Commit the claude-lock.json lockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. See Manage resources as code with ant apply.
+Version 1.30.0 of the ant CLI adds ant apply, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe each resource in a file, run ant apply, and approve the plan it prints. Commit the claude-lock.json lockfile it writes so that later runs, on your machine or in CI, update the same resources instead of creating new ones. See Manage resources as code with ant apply.
+Per-message effort changes, in beta, are also available on Google Cloud for Claude Fable 5.1, Claude Mythos 5.1, and Claude Opus 5, with the same mid-conversation-output-config-2026-07-01 beta header.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.72, needed 0.45
triage reasoningNew beta feature (per-message effort changes) now available on Google Cloud for specific Claude models with required API header.
signalsnew feature announcement · beta feature availability on new platform · new models listed with feature support · specific API header requirement mentioned
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)