LLM · Anthropic

Claude Fable 5.1

Anthropic's model overview says to use Claude Fable 5.1 for demanding reasoning and long-horizon agentic work. It lists a 1M token context window and 128K maximum output. The same overview lists Amazon Bedrock, Google Cloud, and Microsoft Foundry model IDs. The pricing page lists a base rate of $10 input and $50 output per million tokens, and says Claude 4.6 and later models include the full 1M window at standard pricing.

Checked 19 Oct 2026https://platform.claude.com/docs/en/about-claude/models/overview