AI News
Source-checked updates on AI models and coding tools, with practical notes on pricing, migration, and what to test next.
Claude Sonnet 5.5 vs GPT-6.1 Sol: same base price, different trade-offs
Sonnet 5.5 and GPT-6.1 Sol arrived on September 28–29 with matching base API rates. Compare access, long-context costs and integration changes before your first trial.
GPT-5.5 has retired from Codex: check saved model settings
Find saved GPT-5.5 selections in Codex defaults, agents, scheduled tasks and scripts, then verify an available replacement after the October 14 cutoff.
Claude Opus 5.5 pricing: calculate the whole agent run
Opus 5.5 has lower API token rates than Opus 5. Here is how to count cache use, retries and accepted work before predicting an agent's real cost.
Claude Opus 5.5: what to check before switching a production agent
Opus 5.5 changes more than the model ID. Check thinking, tool choice, fallback conversations and computer use before moving an agent to production.
GPT-6 Sol or Luna in Codex? Choose by the work you need checked
Sol and Luna serve different jobs. Here is a practical way to route complex coding and focused repeatable work while measuring review time and retries.