Anthropic Claude Fable 5.1
Anthropic's Fable model for the most demanding reasoning and long-horizon agentic work, with always-on adaptive thinking, vision, and a 1M-token context window.
From Anthropic, Claude Fable 5.1 is a cloud text model. It is multimodal: alongside a text prompt it accepts images, then replies with generated text. Its context window handles up to 1M input tokens and up to 128K output tokens, and it supports adjustable reasoning effort for harder problems. Generation can be tuned with system instructions. It runs through OpenRouter and Anthropic using your own API key, from $10.00 per million input tokens.
- Released
- this month (Sep 2026)
- Pricing
- $10.00 / 1M in · $50.00 / 1M out
- Inputs
- Text, Images
- Context window
- 1M in · 128K out
- Reasoning
- Adjustable effort
- Controls
- System prompt
Examples
Generated with Claude Fable 5.1 via OpenRouter. The same three prompts run against every text model in the catalog, shown verbatim, so the only thing that changes between two models’ answers is the model.
Explain what an API is to someone who has never written code. Do not use a restaurant or waiter analogy. Plain prose only — no headings, bullet points, or markdown formatting. Maximum 50 words.
An API is a set of agreed-upon rules that lets one piece of software ask another for information or actions, like a wall socket: you don't need to understand the power plant, you just plug in a standard shape and electricity arrives reliably.
A two-person startup is deciding whether to build their own user authentication or use a hosted provider. Give them a clear recommendation, then the single strongest argument against your own recommendation. Plain prose only — no headings, bullet points, or markdown formatting. Maximum 150 words.
Use a hosted provider. With two people, every hour spent on password hashing, session management, MFA, account recovery, rate limiting, and breach response is an hour not spent on the product that actually differentiates you. Authentication is a solved problem with well-audited implementations, the failure modes are catastrophic and public, and services like Auth0, Clerk, Supabase Auth, or Firebase Auth cost nothing at your scale. Pick one with a clean migration path (exportable password hashes, standard OIDC) so you're not trapped later. The strongest counterargument is vendor lock-in combined with pricing cliffs. Hosted auth providers have a history of steep price increases once you cross user thresholds, and by then your user model, sessions, and integrations are entangled with their APIs. Migrating live users off a provider without forcing password resets is genuinely painful, so the "cheap now" decision can become an expensive, distracting rewrite precisely when you least want one.
Write a briefing for a non-technical executive explaining why their company's spending on AI is hard to predict, and what they can do about it. Cover at least three distinct causes. Plain prose only — no headings, bullet points, or markdown formatting. Write exactly 205 words.
Your AI spending is hard to forecast for three reasons. First, most AI services charge by usage rather than a flat fee, so costs rise and fall with how often employees and customers use the tools. A feature that proves popular can double its bill in a month, and nobody can reliably predict adoption in advance. Second, the vendors themselves change prices frequently. Newer models arrive every few months, older ones are retired, and rate cards shift, so a budget built on today's numbers may be obsolete by the next quarter. Third, internal experimentation is largely invisible. Teams spin up pilots, connect tools to the same corporate account, and rarely shut anything down, which means spending accumulates quietly across many small projects. You can bring this under control. Insist that every AI initiative has a named owner and a monthly spending cap enforced through the vendor's billing controls, not through good intentions. Require finance to receive a single consolidated report of AI costs by team, refreshed weekly. Ask technical leaders to tie each project to a measurable business outcome so that low-value experiments are retired promptly. Finally, budget in ranges rather than fixed figures, and review those ranges every quarter as usage and pricing evolve.
Anthropic
Anthropic builds the Claude family of large language models, focused on safety, helpfulness, and honesty.
www.anthropic.com ↗