The Orchestrator › Models › Anthropic

Anthropic: Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model for the most demanding technical work, with gains over Fable 5.1 in coding, reasoning, and vision. In prerelease testing it completed otherwise-infeasible...

Specifications

ProviderAnthropic
Model IDanthropic/claude-fable-5.2
Context window1M tokens (1,000,000)
Modalitiestext + image + file → text
TokenizerClaude
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-11-09
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningMandatory

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouteranthropic/claude-fable-5.2$8.00$40.001M
batchOpenRouteranthropic/claude-fable-5.2:batch$4.00$20.001M
standardTrustedRouteranthropic/claude-fable-5.2$8.44$42.201M
standardVercel AI Gatewayanthropic/claude-fable-5.2$8.00$40.001M
fastVercel AI Gatewayanthropic/claude-fable-5.2:fast$16.00$80.001M
batchVercel AI Gatewayanthropic/claude-fable-5.2:batch$4.00$20.001M
standardCloudflareanthropic/claude-fable-5.2$8.00$40.00—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$8.00$40.00—
2026-11-14$8.00$40.001M
2026-11-14$8.44$42.201M
2026-11-14$8.00$40.001M

Capabilities

Vision (image input)File inputAgentic tool useStructured outputsReasoning (always on)1M+ context windowControllable reasoningNo content storage (attested)Zero data retentionNo training on inputs (attested)

Trust flags come from TrustedRouter's per-provider attestations.

Supported parameters

include_reasoning, max_completion_tokens, max_tokens, reasoning, reasoning_effort, response_format, stop, structured_outputs, tool_choice, tools, verbosity