---
id: "anthropic/claude-fable-5.1"
also: ["anthropic/claude-fable-5.1-20260831", "requesty/anthropic/claude-fable-5.1", "vercel/anthropic/claude-fable-5.1"]
card_usd_per_m: "10.0 in, 50.0 out, at anthropic"
cheapest_list_usd_per_m: "10.0 in, 50.0 out, at amazon-bedrock on openrouter"
cheapest_effective_usd_per_m: "1.303 in, 50.0 out, at anthropic on requesty"
context: 1000000
max_output: 128000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-09-01"
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", "temperature", "tool_choice", "tools", "verbosity"]
endpoints: 10
gateways: "openrouter (4), requesty (3), vercel (3)"
no_training: 10
trains: 0
retains_prompts: 10
intelligence: 50
coding: 80.7000
agentic: 57.2000
---
# Anthropic: Claude Fable 5.1

Claude Fable 5.1 is Anthropic's most capable model, improving on Claude Fable 5 across agentic coding, long running agentic workflows, and knowledge work such as large code refactors, front end and visual code generation, and finance and analysis tasks. It ships a 1M token context window by default with 128K max output, is more token efficient and concise than Fable 5, and supports per message effort control. It is a Mythos class model with robust safeguards.