---
id: "anthropic/claude-fable-5.2"
also: ["anthropic/claude-fable-5.2-20261109", "requesty/anthropic/claude-fable-5.2", "vercel/anthropic/claude-fable-5.2"]
card_usd_per_m: "8.0 in, 40.0 out, at anthropic"
cheapest_list_usd_per_m: "8.0 in, 40.0 out, at amazon-bedrock on openrouter"
cheapest_effective_usd_per_m: "0.6384 in, 40.0 out, at amazon-bedrock on openrouter"
context: 1000000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-11-09"
reasoning: ["max", "xhigh", "high", "medium", "low"]
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "max_completion_tokens", "max_tokens", "reasoning", "reasoning_effort", "response_format", "stop", "structured_outputs", "tool_choice", "tools", "verbosity"]
endpoints: 9
gateways: "openrouter (5), vercel (3), requesty (1)"
no_training: 9
trains: 0
retains_prompts: 9
intelligence: 64.6000
---
# Anthropic: Claude Fable 5.2

Claude Fable 5.2 is Anthropic's most capable model, built for demanding reasoning and long horizon agentic work such as agent sessions that run for hours, multistep deep research, and analysis carried through to a finished document, spreadsheet, or deck. It improves on Claude Fable 5.1 in coding, reasoning, and vision, ships a 1M token context window with 128K max output, and uses adaptive thinking that is always on. It is a Mythos class model with robust safeguards.