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.

Original post →

More from coding & agent

coding & agent channel →