OpenAI · GPT-6
GPT-6 Astra
From prompt to polished, end to end.
What it is
GPT-6 Astra is built for end-to-end agentic work. It plans, reasons, writes and runs code, operates a computer, and carries a task from a single prompt to a finished result.
Where a chat model answers, Astra acts. It breaks a goal into steps, uses tools and a browser the way a person would, checks its own work and recovers from mistakes. A context window of roughly one million tokens keeps an entire codebase, long document or full project brief in view.
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.
End-to-end delivery
Takes a goal from plan to finished artifact instead of returning a single answer.
Code and tools
Writes and runs code, browses, and uses the tools a project already depends on.
Long context
Holds a whole codebase, dataset or brief in view while the task runs.
Self-checking
Tests its output, notices what broke and iterates before handing the work back.
A good first run
Three web Skills to try on GPT-6 Astra — 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
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
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.