Plan, structure, and refine prompts for Anthropic’s Fable 5 model — the newest Claude flagship. Specs, pricing, access channels, templates, and a free chat workspace in one independent place.
Free streaming chat — no account needed. Open the Chat →
fable5.io is an independent community resource — not affiliated with Anthropic. No official Fable 5 access is sold here; the free chat is this site’s own assistant, not the Fable 5 model itself.
Claude-style, full-screen streaming chat: Markdown answers and history saved in your browser. No account, no cost — practice your Fable 5 prompt ideas live before spending tokens.
Fable 5 costs $10 per million input tokens and $50 per million output — double Opus 4.8 — with a 1M-token context window.
Where Fable 5 is live right now — the Claude apps, the Claude API, AWS, Google Cloud, Microsoft Foundry, GitHub Copilot, and OpenRouter — with a date for every channel.
Copy, customize, and paste prompts built for Fable 5 chat — creative writing, research, coding, marketing, learning, productivity, and safety review.
Context window, output limits, and API pricing for Fable 5 next to Claude Opus 4.8 and Sonnet 4.6 — public data, clearly dated and sourced.
| Spec | Fable 5 | Opus 4.8 · Sonnet 4.6 |
|---|---|---|
| Context window | 1M tokens | 1M · 1M |
| Max output | 128K tokens | 128K · 64K |
| Input price / 1M tokens | $10 | $5 · $3 |
| Output price / 1M tokens | $50 | $25 · $15 |
| Thinking | Adaptive only | Adaptive |
| Tier | Flagship — above Opus | Opus · Sonnet |
Public specs as of June 10, 2026, from Anthropic’s announcement and API docs. Independent site — verify with official sources before budgeting.
fable5.io helps researchers, writers, and developers keep Fable 5 AI prompts, assumptions, and source notes organized before they test anything in a real model environment.
Plan how Fable 5 research fits with your current AI tools. The workflow map keeps prompt drafts, source checks, safety review, and comparison notes in a repeatable loop.
A plain-language guide to Anthropic’s Fable 5 model: what it is, what it costs, how to access it, and how to prompt it well. Facts dated June 10, 2026.
Claude Fable 5 is Anthropic's flagship AI model, released on June 9, 2026. Anthropic describes it as a Mythos-class model made safe for general use: its capabilities exceed any model the company has previously made generally available, with state-of-the-art results in software engineering, knowledge work, vision, and scientific research. New safeguards block responses in specific high-risk areas, and a small share of sensitive queries are answered by Claude Opus 4.8 instead.
Fable 5 offers a 1M-token context window and up to 128K output tokens. API pricing is $10 per million input tokens and $50 per million output tokens — double Opus 4.8 — with a 90% input discount on cached prompt content. The model uses adaptive thinking only: classic sampling knobs like temperature and top_p are removed, so output style is steered through prompting, and an effort parameter (low to max) trades depth against speed and cost.
Official channels: the Claude apps on paid plans (included on Pro, Max, Team, and seat-based Enterprise until June 22, 2026, then via usage credits), the Claude API under the model ID claude-fable-5, AWS, Google Cloud, and Microsoft Foundry, and GitHub Copilot. Routers such as OpenRouter list it as anthropic/claude-fable-5. Be cautious of anyone selling Fable 5 access keys outside these channels — you never need a third-party reseller.
Fable 5 follows instructions more literally than older models, which rewards precise prompts: state the role, one line of context, the task, the output format, and hard constraints. For long agentic tasks, put the full specification in the first message rather than drip-feeding it. Because sampling parameters are gone, ask for variation explicitly when you want it. The free Chat on this site is a quick place to practice, and the Playground refines a single prompt before you spend Fable 5 tokens.
Choose by task value: Fable 5 ($10/$50 per million tokens) is the ceiling for hard, high-stakes work; Claude Opus 4.8 ($5/$25) remains extremely strong at half the price; Sonnet 4.6 ($3/$15) balances speed and intelligence; Haiku 4.5 ($1/$5) handles fast, simple tasks. All current models share the adaptive-thinking API surface, so the same well-structured prompt ports across tiers — run it on a cheaper model first and escalate only when quality demands it.
fable5.io is not an Anthropic property — it is an independent workspace that aggregates public Fable 5 information with dates and sources: the Anthropic announcement, the Claude API docs, and the OpenRouter catalogue. Specs and pricing can change after publication, so every figure here is dated, and official sources always win on conflict. Spotted an error? Use the contact link in the footer to report it.
“Turn a loose Fable 5 AI idea into a repeatable prompt plan with role, task, format, constraints, and review notes.”
fable5.io is an independent resource. Not affiliated with any official Fable 5 publisher.
Independent resource. Not affiliated with Anthropic.