feat(models): add Claude Fable 5.1 and align Anthropic prompt-cache minimums

[waleedlatif1]

Summary

• add claude-fable-5-1 to the Anthropic provider: $10/$50 per MTok, $0.25 cache read (0.025x, unlike the 0.1x on every other Claude model), 1M context, 128K output, all five effort levels, native structured outputs, summarized thinking streaming
• Fable 5.1 returns a 400 for tool_choice tool/any, so the Anthropic core now sends auto (with a warning) instead of the forced tool_choice for that model family; thinking is always on for it so a forced call would have skipped thinking anyway
• align per-model prompt-cache minimums with the current Anthropic docs: 512 for Fable 5.x / Opus 5, 2048 for Opus 4.7, 4096 for Opus 4.6 / Opus 4.5 / Haiku 4.5 (previously the provider default of 1024, and 2048 for Haiku)
• regenerate the agent streamed-thinking docs table

Type of Change

• New feature

Testing

• ran every effort level (low → max), none, legacy non-agent-events, streaming, streaming + tools, forced tool, and native structured output against the live API for both claude-fable-5-1 and claude-sonnet-5 through the provider code; all succeeded with the expected thinking / output_config / tool_choice payloads
• confirmed against the live API that Fable 5.1 rejects forced tool_choice, non-default temperature, thinking: disabled, and budget_tokens, and that the Models API reports 1M input / 128K output for both models
• bun run lint, bun run type-check, bun run check:audits, provider unit tests

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• 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	Sep 2, 2026 1:15am UTC

[greptile-apps]

Greptile Summary

Adds Claude Fable 5.1 to the Anthropic model catalog and adapts request construction for its thinking and tool-choice constraints.

• Defines Fable 5.1 pricing, token limits, prompt caching, structured output, and thinking capabilities.
• Falls back from forced tool selection to automatic selection for Fable/Mythos 5.1 models that reject forced choices.
• Aligns Anthropic and Azure Anthropic prompt-cache minimum metadata and updates tests and streamed-thinking documentation.

Confidence Score: 5/5

The PR appears safe to merge with no actionable correctness or security defects identified.

The new model follows the existing Anthropic capability and adaptive-thinking paths, the forced-tool fallback is an intentional response to an upstream API restriction, and the cache-minimum changes do not alter request construction.

Important Files Changed

Filename	Overview
apps/sim/providers/anthropic/core.ts	Adds Fable/Mythos 5.1 forced-tool compatibility handling while preserving existing request construction for other models.
apps/sim/providers/models.ts	Registers Claude Fable 5.1 and updates per-model Anthropic and Azure Anthropic prompt-cache capability metadata.
apps/sim/providers/anthropic/core.request.test.ts	Verifies forced tool choice remains enabled for supported models and is omitted with a warning for Fable 5.1.
apps/sim/providers/anthropic/core.thinking.test.ts	Extends summarized-thinking and legacy-stream coverage to Claude Fable 5.1.
apps/sim/providers/models.test.ts	Updates prompt-cache minimum assertions for Anthropic and Azure Anthropic Haiku 4.5.

Sequence Diagram

sequenceDiagram
  participant C as Provider caller
  participant A as Anthropic core
  participant API as Anthropic API
  C->>A: Request with model, thinking level, and tools
  A->>A: Resolve model capabilities
  alt Fable or Mythos 5.1 with forced tool
    A->>A: Warn and omit forced tool_choice
  else Model supports forced tool selection
    A->>A: Include requested tool_choice
  end
  A->>API: Create message with adaptive thinking
  API-->>A: Text or tool-use response
  A-->>C: Normalized provider response

Loading

_{Reviews (1): Last reviewed commit: "feat(models): add Claude Fable 5.1 and a..." | Re-trigger Greptile}

[cubic-dev-ai]

No issues found across 6 files

Confidence score: 5/5

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

<sub>Heads up: you’re close to your included review allowance. Set a flex budget so reviews don’t pause.

Re-trigger cubic</sub>