Anthropic · Claude Fable 5.1
Fable 5.1
Anthropic's most capable model.
What it is
Fable 5.1 is Anthropic's most capable model, built for the hardest reasoning and the longest agentic runs. A one-million-token context and adaptive thinking let it hold focus across multi-step builds.
Reach for it when the brief is ambiguous, the evidence is scattered, or the answer has to be argued rather than assembled — the cases where a Skill needs judgment more than speed.
Profiles describe the model, not a guarantee: the Skill folder is what makes the work repeatable, and the agent's settings decide what the model can reach.
What it's best at
The work this engine is built for, and where it earns its place in a run.
Demanding reasoning
Works through ambiguous briefs and conflicting evidence instead of assuming the easy reading.
Long-horizon work
Keeps a multi-step build coherent from the first decision to the final check.
Adaptive thinking
Spends more effort where the problem is hard and less where it is settled.
Large-context synthesis
Reads across long documents and disconnected sources, then produces one argument.
A good first run
Three slides Skills to try on Fable 5.1 — each one a folder of instructions the model can pick up straight away.
Other models
The rest of the engine room.
Anthropic · Claude 5.5
Opus 5.5
Anthropic's newest frontier model, built to carry long, multi-step work from one prompt to a finished result.
- Context
- 1M tokens
- Best at
- Agentic coding
OpenAI · GPT-6
GPT-6 Astra
OpenAI's frontier model for end-to-end agentic work, reasoning across a task rather than a single turn.
- Context
- ≈1M tokens
- Best at
- End-to-end work
Anthropic · Claude Opus 5
Opus 5
Anthropic's Opus-tier flagship: near-frontier intelligence for complex coding and enterprise work.
- Context
- 1M tokens
- Best at
- Complex coding
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.