[waleedlatif1]

Summary

• Add claude-fable-5-2: $8 / $40 per MTok, $0.20 cache read, 1M context, 128K max output, released 2026-11-09
• Adaptive thinking only (low → max, default high, summarized stream); forced tool_choice disabled (API returns 400 for any/tool); native structured outputs; 512-token cache minimum
• Move featured from Fable 5.1 to 5.2 and mark Fable 5.1 legacy, matching Anthropic's model overview
• Regenerate the Agent block streamed-thinking docs table

Type of Change

• New feature

Testing

• Verified every field against Anthropic's models overview, Fable 5.2 page, pricing, effort, thinking, prompt-caching, and structured-outputs docs; cross-checked price and context with OpenRouter
• vitest on providers/models.test.ts, providers/anthropic/core.test.ts, providers/utils.test.ts (285 passing)
• check:agent-stream-docs, biome on changed files; full audits and type-check run in CI

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing (new tests pass the test-audit authoring gate)
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated
docs	Ready	Preview	Nov 9, 2026 7:42pm UTC

[cubic-dev-ai]

No issues found across 3 files

Confidence score: 5/5

• Automated review surfaced no issues in the provided summaries.
• No files require special attention.

_{Turn on auto-fix | Re-trigger cubic}

[greptile-apps]

Confidence Score: 5/5

[Medium impact] This PR appears safe to merge; no actionable issues were found.

Summary

Adds claude-fable-5-2 with pricing, token limits, prompt caching, native structured outputs, and summarized thinking.

• Claude Fable 5.2 joins the model list as featured, while Fable 5.1 becomes legacy.

No actionable issues found.

_{Reviews (1) · Last reviewed commit: "feat(models): add Claude Fable 5.2" · Reviewed by Greptile}