Switching Providers in Coding Agents Balloons Costs by Losing Context Cache
blelbach · x · 2026-07-24
Kevin Gray points out that input tokens dominate costs in coding agents. He advises against using routers like OpenRouter, as switching providers causes a loss of context caching, drastically increasing inference costs. He recommends using cheap and fast models like Grok, Gemini, or Kimi directly.
More from coding & agent
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- Morgan Stanley and US banks block third-party AI agents over credentials — thione · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26
- 250 Builders Hack With Codex at Berlin Community Hackathon Ahead of OpenAI DevDay — paw_lean · 2026-10-26