Models

Frontier language models developers build with and run their coding agents on

4 resources
C

Claude Fable 5.1

Paid

Anthropic's most capable generally available model, released September 1, 2026, for long-running agentic coding, multistep research, and document work. 1M-token context, 128K output, adaptive thinking that is always on.
G

GPT-6 Astra

Paid

OpenAI's flagship model, announced September 3, 2026, for complex reasoning, coding, computer and browser use, research, and document creation. 1.05M-token context, 128K output, reasoning effort from low to max.
G

Grok 4.6

Paid

SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, released August 12, 2026. A post-training upgrade over Grok 4.5 tuned for agents that stay on a task across many steps, with a 500K-token context window.
S

SWE-2

Paid

Cognition's most advanced coding model, released September 10, 2026. Post-trained with RL from Kimi K3, it scores 50.0% on FrontierCode 1.1 Main, within a point of Claude Fable 5.1 at 64% lower cost, and ships in medium, high and max effort levels.