Chat & Reasoning Model · Anthropic

Claude Fable 5

Claude Fable 5 is Anthropic's newest, most capable broadly available model for hard long-horizon agentic work. In TeamDay it is the recommended model on the Claude Code harness, with reasoning effort selectable from low up to max.

Use Claude Fable 5 in TeamDay →All models

At a glance (verified 2026-07-18)

Vendor: Anthropic
Type: Chat & Reasoning Model
Pricing: Base: $10 in / $1 cache hits / $50 out per 1M tokens. Cache writes: $12.50 5m / $20 1h.

Best for

Long-horizon agentic workAutonomous codingDeep researchMulti-hour missions

How to use Claude Fable 5 in TeamDay

Pick Claude Fable 5 in TeamDay's chat model picker on the Claude Code harness — it is the recommended default for the hardest missions.

Harness: claude-code →Max →Daisy →

Frequently asked questions

How much does Claude Fable 5 cost?

Base API pricing is $10 per 1M input tokens, $1 for cache hits, and $50 per 1M output tokens; cache writes cost $12.50 (5-minute) or $20 (1-hour) per 1M tokens.

What is Claude Fable 5 best at?

It is Anthropic's most capable broadly available model for hard long-horizon agentic work — sustained autonomous coding and research missions rather than quick one-shot chat.

Can I use Claude Fable 5 in TeamDay?

Yes — it is the recommended model on TeamDay's Claude Code harness, with selectable reasoning effort (low, medium, high, xhigh, max; high is the default).

Claude Opus 4.8 — Chat & Reasoning Model
Claude Sonnet 5 — Chat & Reasoning Model
GPT-5.6 (Sol, Terra, Luna) — Chat & Reasoning Model
Kimi K3 — Coding Model

Claude Fable 5is one of the models TeamDay's AI employees already run — no API keys, no infrastructure.

Hire your first AI employee →