Daniel Bedoya

@eclectic_dev @dhh @FireworksAI_HQ @opencode Sign up there: fireworks.ai Buy tokens and connect with opencode with the API key. #fireworks-ai" target="_blank" rel="nofollow noopener">opencode.ai/docs/providers…

@dhh @FireworksAI_HQ @opencode is that through openrouter? cause I'm not getting the 200 tps

Kimi K2.5 continues to be my daily driver for all the basic stuff where I don't need PhD-level intelligence. I just need it done quickly. Running it at 200 tps through @FireworksAI_HQ within @opencode is just such a delight.

@alexandroff_h @Shpigford Codex 5.3 and Opus 4.6 are rivals (In my short experience Codex is a bit better on complex scenarios and big codebases). Codex 5.3 >>>>> Kimi 2.5

@Shpigford Is codex better than cloude or Kimi?

can someone explain to me why i wouldn't just pick "extra high" every time? is it basically "greater reasoning" = "longer response times"?

@Lsenerman @thdxr @adamdotdev Is working now. Thanks a lot

@Lsenerman @thdxr @adamdotdev IS IT????????? I installed that when all the controversy with Anthropic happened. No idea that it was working again out of the box. Will try, thanks

Hello there @adamdotdev @thdxr I'm getting this error on both desktop and cli opencode. I tried downgrading to v1.1.35 and nothing works, any idea? I did not found anything on GH issues about it. Thanks

@Lsenerman @thdxr @adamdotdev Thanks @Lsenerman . Yeah, I see that there was a release of that plugin 1 hour ago and got this issues. Any idea how can we use the 0.0.9 version instead the 0.0.10?

@thdxr @danielb0901 @adamdotdev Its the anthropic plug in, once removed from config it starts workin again.

@thdxr @adamdotdev Just opencode.json? or what else?

@danielb0901 @adamdotdev can i see your config?

@adamdotdev @thdxr BTW. I cleared the cache on ~/.cache/opencode. I'm using macOS. Does not works either

@adamdotdev @thdxr Tried with 4 providers and different models and I get that lol

@housecor Another two options: - Spokenly: spokenly.app (better UI and performance on Mac OS & iOS imo) - Handy: handy.computer - Open source and extendable Both can use Nvidia Parakeet. After using those two and also superwhisper, I find Spokenly faster (no idea why)