Claude Fable 5.2

anthropic/claude-fable-5-2

Maker: Anthropic, United States
Released: 2026-11-09
Knowledge cutoff: 2026-06
Family: claude-fable
Weights: closed
Tasks: text.chat, text.reasoning, code, vision.understand, vision.extract
Cheapest offering: Anthropic, about $0.02 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
Anthropic	`claude-fable-5-2`	ganot before 2027-11-09	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Input, priority tier: $16 Output, priority tier: $80 Cache read, priority tier: $0.4 Cache write (5 min), priority tier: $20 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max input: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` probed 2026-11-10 `input.pdf` probed 2026-11-10 `output.text` claimed `tools` claimed `structured_output` probed 2026-11-10 `reasoning` native `batch` native `citations` native `web_search` native `code_execution` native `tool_choice` claimed `prompt_caching` claimed `computer_use` claimed `no_training` claimed
Azure OpenAI	`claude-fable-5-2`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Amazon Bedrock	`anthropic.claude-fable-5-2`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed `computer_use` claimed
Amazon Bedrock	`global.anthropic.claude-fable-5-2`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed `computer_use` claimed
Amazon Bedrock	`us.anthropic.claude-fable-5-2`	ga	Input: $8.8 Output: $44 Cache read: $0.22 Cache write (5 min): $11 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed `computer_use` claimed
OpenRouter	`anthropic/claude-fable-5.2`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Cache write (1 h): $16 Since 2026-11-10	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` probed 2026-11-10 `input.pdf` native `output.text` claimed `tools` probed 2026-11-10 `structured_output` probed 2026-11-10 `reasoning` probed 2026-11-10 `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`anthropic/claude-fable-5.2:batch`	ga	Input: unknown Output: unknown Input, batch tier: $4 Output, batch tier: $20 Cache read, batch tier: $0.1 Cache write (5 min), batch tier: $5 Cache write (1 h), batch tier: $8 Since 2026-11-10	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` native `output.text` claimed `tools` claimed `tool_choice` claimed `structured_output` claimed `reasoning` claimed `prompt_caching` claimed
Claude on Vertex AI	`claude-fable-5-2@default`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Input, priority tier: $16 Output, priority tier: $80 Cache read, priority tier: $0.4 Cache write (5 min), priority tier: $20 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Google Vertex AI	`claude-fable-5-2@default`	ga	Input: $8 Output: $40 Cache read: $0.2 Cache write (5 min): $10 Input, priority tier: $16 Output, priority tier: $80 Cache read, priority tier: $0.4 Cache write (5 min), priority tier: $20 Since 2026-11-10 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 128,000 tokens	`input.text` claimed `input.image` claimed `input.pdf` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:frontiermath`	1.000	0.9509	2026-11-06	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:gpqa_diamond`	0.974	0.9388	2026-11-06	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

anthropic.claude-fable-5-2
anthropic/claude-fable-5.2
anthropic/claude-fable-5.2:batch
claude-fable-5-2
claude-fable-5-2@default
global.anthropic.claude-fable-5-2
us.anthropic.claude-fable-5-2
~anthropic/claude-fable-latest

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/anthropic/claude-fable-5-2' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=anthropic,azure-openai,bedrock,openrouter,vertex-anthropic,vertex' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-10.2 of 2026-11-10. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).