Anthropic · Claude Opus 5
Opus 5
Frontier agentic coding, at half the cost.
What it is
Opus 5 is the Opus-tier flagship that came before Opus 5.5: near-frontier intelligence for complex agentic coding and enterprise work, with a one-million-token context and a cost-to-capability toggle.
It is the practical default for production Skills that run often. Most of the ceiling of a frontier model, at roughly half the price, with the same long-context reach.
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.
Agentic coding
Multi-file edits, refactors and reviews with an eye on the whole repository.
Enterprise work
Long professional tasks where the deliverable has to be defensible, not merely plausible.
Long context
Carries a full codebase or specification through a multi-step change.
Cost control
An effort toggle lets routine runs spend less without changing models.
A good first run
Three web Skills to try on Opus 5 — 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 Fable 5.1
Fable 5.1
Anthropic's top model for demanding reasoning and long-horizon agentic work, with adaptive thinking.
- Context
- 1M tokens
- Best at
- Demanding reasoning
Ready to extend your agent?
Connect once, then install any Skill from our studio straight from your agent.