Ten cents a million. Now read the second line.
In October, Anthropic and OpenAI each put a small, fast model at $0.10 per million input tokens. Haiku 5.5 charges five times more once a prompt passes 100k tokens. The Decisions API charges nothing for output, and its page says long-context multipliers apply without saying how big they are. Meanwhile GitHub retired six Copilot models on October 19. This issue has a swap table and a 20-minute audit of your own bill.
What changed
Codex, browser workflows, GPT-5.5, and agentic work moved closer to daily practice.
What to try
A concrete browser-based AI-agent task you can test on your own project this week.
What to read
The technical system-card signal behind stronger planning, tool use, and verification.