// AI Platform Drift

Claude Opus 4.7 includes API breaking changes versus Opus 4.6

Claude Platform release notes · published 2026-11-18 20:32 UTC
ACTION NEEDED MIGRATE MODELAPIPRICING
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)