Ask HN: Which model do you use with Pi coding agent?

#1

Post by theaniketmaurya » Tue, Jul 21, 2026, 1:23 PM UTC

I use Pi coding agent with OpenAI GPT-5.6 Sol but have been finding that GPT-5.6 is slower than Claude Code. Do you use any other model like one of the hosted OSS ones?

Re: Ask HN: Which model do you use with Pi coding agent?

#2

Post by slipwalker » Tue, Jul 21, 2026, 5:06 PM UTC

GLM 5.x coding plan from z.ai, and opencode go plan.

Re: Ask HN: Which model do you use with Pi coding agent?

#3

Post by freddiehdxd » Tue, Jul 21, 2026, 5:43 PM UTC

GPT-5 / GPT-5.5 Claude Opus / Sonnet Gemini Kimi K2 DeepSeek Grok

Re: Ask HN: Which model do you use with Pi coding agent?

#4

Post by softwaredoug » Tue, Jul 21, 2026, 6:11 PM UTC

I think GPT 5.6 Luna works great honestly for most boring coding tests. And saves money.

Re: Ask HN: Which model do you use with Pi coding agent?

#5

Post by theaniketmaurya » Sat, Jul 25, 2026, 11:49 AM UTC

freddiehdxd wrote: post #3

GPT-5 / GPT-5.5 Claude Opus / Sonnet Gemini Kimi K2 DeepSeek Grok

Do you pay for the API with Opus? since i think we can't use subscriptions with non claude code agents