Hacker News Reader

Comment by ryanSrich | Hacker News Reader

For anyone on the fence, I was a hardcore CC user since it was released. I made the full switch to 5.6 sol and Codex about a month ago.

It's the better experience. The limits are way higher (I almost never burn through my $200/m plan), and the output is better than Opus 4.8 (Opus 5 is completely unusable for me).

View on HN

I had a very similar experience. The combination of Claude going down frequently and the hype around open source models was enough for me to swap my harness from Claude Code to OpenCode. Then it became trivial to test out different models, and now the rest is history. Currently using OpenCode with z.ai and Codex $200/m plans for all my work atm.

You're underselling how good/reliable 5.6 sol is. It's in the fable discussion league not Opus4.8

I haven't used fable since they brought it back. But based on my experience before they removed it, I would agree that sol is pretty close.

Also try a hundred bucks on Openrouter and experiment with the Chinese models like Deepseek, Kimi, GLM. $100 will last a good while, and it isn't tied to a single model or provider.

I burned though $50 on OpenRouter in three days, this is with selective model routing based on tasks/strict AGENTS.md. A Claude 20x sub running Sonnet 5/Opus 5 and light Fable usage gets me through the month. It wasn't even close even though I wish it were.

Damn that's crazy. I put in $10 on the 5th of August and still have $1.99 left today, the 18th. I use Deepseek Flash almost exclusively.

Deepseek Flash is somewhere around the OpenAI Luna level though.

That's not bad (and nor is Luna!) but Opus/Sol are just massively better especially once you start doing agentic tasks.

See for example https://x.com/zainhas/status/2085567832268656755

Agreed, it's not SOTA but I'm happy with the trade off. My preference is to use mostly local models and augment them with Deepseek. It's been a pretty great equilibrium.

I have the $100 plan on OpenCode Zen, which I imagine is similar. I burn through it ridiculously fast. I haven't run the numbers, but it felt about the same as an Anthropic $20 plan

Yeah. Same. Deepseek Flash goes a long way, but it’s not capable enough for many tasks, so I end up defaulting to my Codex sub and just use Sol.

As a counter point, I've been using CC since December and I've never really had any problems with it. It's always done exactly what I want it to and I continue to be blown away by its capabilities, regardless of which of their models I've used. I also almost never burn through my $200/m plan.

Yep, switched from CC to 5.6 Sol. Not using it in my day job (only side projects), but I can crank 5.6 Sol on Extra High "fast mode" and never have to worry about credits.

Not doing crazy multi agent swarms, but have yet to hit any limits during pretty intense weekend sessions.

If you aren't using the full $200, you are losing money every month

What thought process gets you to that conclusion?

It's clearly not right if you compare it to API prices. It's even less right if you compare to a SWE salary.

Yes not using the full $200 means you aren't tokenmaxxing, but that seems about the most you can conclude from it.

I use Claude and Antigravity CLI as an (Arch) Linux desktop system administrator a lot lately. Is Codex useful for that too?

Not sure what Antigravity is, but Sol is good at sysadmin tasks.

Antigravity (at least Antigravity CLI which I use) is the CLI coding (?) agent harness from Google that uses Gemini as the model. There are other models available but I haven't tried them.

Reply on news.ycombinator.com