Claude Platform release notes

3 items in the render window (newest 100 + all corrections; not this source's all-time total) · status healthy · last successful fetch 2026-11-21 19:16 UTC
Feed for this sourceRSS
WORTH KNOWING PRICINGAPI Claude Platform release notes · 2026-11-18 20:32 UTC

US-only inference costs 1.1x for models after 1 February 2026

Do:Review whether your compliance requirements mandate US-only inference.
WHAT CHANGEDAnthropic introduced an inference_geo parameter for data residency controls. US-only inference costs 1.1x the standard price for models released after 1 February 2026. This applies to Claude Opus 4.6 and future models.
WHY IT MATTERSEvery request using US-only inference on Opus 4.6 or later models costs 10% more than the standard multi-region price. If you route all traffic through US-only inference, your bill increases by 10% for those models.
WHAT TO DOReview whether your compliance requirements mandate US-only inference. If not, omit the inference_geo parameter to use standard pricing. If US-only is required, reforecast costs at 1.1x the published rates for Opus 4.6 and models released after 1 February 2026.
Model-reported confidence 95% (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#february-5-2026
 Thu, 05 Feb 2026 00:00:00 GMT
 
-We’ve launched Claude Opus 4.6, our most intelligent model for complex agentic tasks and long-horizon work. Opus 4.6 recommends adaptive thinking (thinking: {type: "adaptive"}); manual thinking (type: "enabled" with budget_tokens) is deprecated. Opus 4.6 does not support prefilling assistant messages. Learn more in What’s new in Claude 4.6.
+We’ve launched Claude Opus 4.6, our most intelligent model for complex agentic tasks and long-horizon work. For Opus 4.6, we recommend adaptive thinking (thinking: {type: "adaptive"}); manual thinking (type: "enabled" with budget_tokens) is deprecated. Opus 4.6 does not support prefilling assistant messages. Learn more in Claude Opus 4.6.
 The effort parameter no longer requires a beta header and now supports Claude Opus 4.6. Effort replaces budget_tokens for controlling thinking depth on new models.
 We’ve launched the compaction API in beta, providing server-side context summarization for effectively infinite conversations. Available on Opus 4.6.
 We’ve introduced data residency controls, allowing you to specify where model inference runs with the inference_geo parameter. US-only inference is available at 1.1x pricing for models released after February 1, 2026.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.45
triage reasoningMultiple breaking changes, deprecations, new APIs, and pricing tier introduced for production model.
signalsdeprecation announced: manual thinking (type: 'enabled' with budget_tokens) · new feature: adaptive thinking recommended for Opus 4.6 · breaking change: Opus 4.6 does not support prefilling assistant messages · API change: effort parameter no longer requires beta header · new feature: compaction API in beta · new feature: data residency controls with inference_geo parameter · pricing change: US-only inference at 1.1x pricing for models after Feb 1, 2026
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)
ACTION NEEDED MODELAPIPRICING Claude Platform release notes · 2026-11-18 20:32 UTC

Claude Opus 4.7 includes API breaking changes versus Opus 4.6

Do:Read the migration guide at https://platform.claude.com/docs/en/release-notes/overview before upgrading any Opus 4.6 integration to Opus 4.7.
WHAT CHANGEDClaude Opus 4.7 launched 16 April 2026 with API breaking changes versus Opus 4.6, an updated tokenizer, and pricing maintained at $5 input / $25 output per MTok. Maximum image resolution increased from 1,568 to 2,576 pixels on the long edge; images might use up to approximately 3x more image tokens than on prior models. Task budgets launched in beta, requiring the task-budgets-2026-03-13 beta header.
WHY IT MATTERSExisting code calling Opus 4.6 will break when upgraded to Opus 4.7. Image-heavy workloads may see input token consumption increase by up to approximately 3x at the same per-token price, raising total cost.
WHAT TO DORead the migration guide at https://platform.claude.com/docs/en/release-notes/overview before upgrading any Opus 4.6 integration to Opus 4.7. Reforecast image workload costs assuming up to 3x token consumption for high-resolution images.
Model-reported confidence 95% (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#april-16-2026
 Thu, 16 Apr 2026 00:00:00 GMT
 
-We’ve launched Claude Opus 4.7, our most capable model for complex reasoning and agentic coding, at the same $5 / $25 USD per MTok pricing as Opus 4.6. See What’s new in Claude Opus 4.7 for capability improvements, new features, and the updated tokenizer. Opus 4.7 includes API breaking changes versus Opus 4.6; see the migration guide before upgrading.
+We’ve launched Claude Opus 4.7, our most capable model for complex reasoning and agentic coding, at the same $5 / $25 USD per MTok pricing as Claude Opus 4.6. See Claude Opus 4.7 for its specifications. Opus 4.7 includes an updated tokenizer and API breaking changes versus Opus 4.6; see Migration guides before upgrading.
 Claude in Amazon Bedrock is now open to all Amazon Bedrock customers. Claude Opus 4.7 and Claude Haiku 4.5 are available self-serve from the Bedrock console through the Messages API endpoint at /anthropic/v1/messages, in 27 AWS regions with global and regional endpoints.
 We’ve launched task budgets in beta on Claude Opus 4.7. Give Claude an advisory token budget for a full agentic loop (thinking, tool calls, tool results, and output) and the model sees a running countdown, using it to prioritize work and finish gracefully as the budget is consumed. Include the task-budgets-2026-03-13 beta header in your requests.
 Claude Opus 4.7 supports high-resolution image input, raising the maximum image resolution from 1,568 to 2,576 pixels on the long edge for improved performance on computer use, screenshot understanding, and document analysis. High-resolution support is automatic and requires no beta header; images might use up to approximately 3x more image tokens than on prior models.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.45
triage reasoningNew model with breaking API changes, new features, and changed image token economics require engineering action.
signalsnew model released (Claude Opus 4.7) · API breaking changes documented · new feature: task budgets (beta) · image resolution limit increased (1568 → 2576 pixels) · image token consumption changed (up to 3x more) · new beta header required (task-budgets-2026-03-13) · pricing maintained at $5/$25 per MTok
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)
WORTH KNOWING APIPRICING Claude Platform release notes · 2026-11-17 20:56 UTC

Anthropic launches linked billing beta for customer-paid API usage

Do:Review the linked billing documentation at the release notes URL to determine whether customer-paid usage fits your application's billing model.
WHAT CHANGEDAnthropic released linked billing in beta on 17 November 2026 with the user-profiles-billing-2026-10-01 header. The /v1/messages and /v1/chat/completions endpoints now accept a billing_policy parameter that controls whether the app developer or the end customer's Claude organization pays for each request. Customers can set spend caps and unlink apps through the Claude Console. This works only for customers whose organizations pay Anthropic directly for API usage.
WHY IT MATTERSApplications can now shift API costs to end users who have their own Claude organizations, changing the economics of building on Claude. Customer spend caps and unlinking controls mean billing responsibility can change at runtime, requiring applications to handle payment failures differently than before.
WHAT TO DOReview the linked billing documentation at the release notes URL to determine whether customer-paid usage fits your application's billing model. If implementing, add handling for the billing_policy parameter and test failure modes when customers hit spend caps or unlink.
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
+## Claude Platform release notes — November 17, 2026
+https://platform.claude.com/docs/en/release-notes/overview#linked-billing
+Tue, 17 Nov 2026 00:00:00 GMT
+
+We’ve launched Linked billing in beta with the user-profiles-billing-2026-10-01 beta header. Your customers can now pay for the Claude usage in your app through their own Claude organization. Once a customer links their organization, set billing_policy on each /v1/messages or /v1/chat/completions request to choose who pays. In the Claude Console, customers can set a spend cap for your app or unlink your app. Linked billing works for customers whose organization pays Anthropic directly for API usage.
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.92, needed 0.45
triage reasoningNew billing feature with API changes and beta header affects how teams implement payment collection.
signalsnew feature launch (Linked billing in beta) · new API parameter (billing_policy on /v1/messages and /v1/chat/completions) · new beta header (user-profiles-billing-2026-10-01) · changes billing responsibility model and customer control · affects how engineering teams structure payment flows
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)