GPT 6.1 Sol: Near-Astra intelligence for a fifth of the price (openai.com)

I get the same UX on every platform, works perfectly on very low bandwith environments such as in a cabin, in the subway or in the middle of nowhere.

I tried using other harness such as Pi and opencode but I did not like them. If Claude Code gets weird I can swap in an instant.

You just need to follow this guide and disable artifacts in Claude Code's config: https://api-docs.deepseek.com/quick_start/agent_integrations...

  curl https://tg.st/u/0001-fix-unblock-all-commands-in-bash-tool.patch | git am
  curl https://tg.st/u/0002-feat-add-light-theme-with-auto-detection-for-white-b.patch | git am
  curl https://tg.st/u/0003-feat-enable-yolo-mode-by-default.patch | git am
  curl https://tg.st/u/0004-fix-disable-mouse-grabbing-to-restore-native-termina.patch | git am
  curl https://tg.st/u/0005-feat-skip-project-init-prompt-and-quit-immediately-o.patch | git am
  curl https://tg.st/u/0006-feat-remove-scrambled-rune-animation-from-waiting-sp.patch | git am
  curl https://tg.st/u/0007-feat-remove-quit-banner-and-thank-you-message.patch | git am
  curl https://tg.st/u/0008-feat-show-output-in-full-instead-of-collapsing-trunc.patch | git am
  curl https://tg.st/u/0009-fix-discover-map-model-features-advertised-by-v1-mod.patch | git am
  curl https://tg.st/u/0010-feat-keep-large-and-small-model-selections-in-sync.patch | git am

Use the model through a fast and reliable provider such as Fireworks directly, skip OpenRouter.

Although I do think Luna 6 max is ok for some basic things, would never use it for coding myself.

When the regulations do arrive, I think they should really focus on AI companies and API providers being more transparent wrt how they're billing their customers. Because right now, it's a totally vibes-dependent and a mess.

Excellent pithy warning.

But there’s a point on that spectrum where the ability to run multiple experiments in parallel, even with a significant amount of (one time) wastage, is overall more cost effective than the alternative.

Who cares if your car can go 200mph if all you need is 60. If my requirement is 60mph, I want a faster 0-60, not a higher top speed.

For CRUD shoveling, models like DS4.1 are enough.

And the intelligence gap between cheap and premium is closing, as can be seen from the title of this post.

Edit: others have noted the provider and harness matters. My experience is with opencode.

What harness you are using?

I also spent $280 on DeepSeek doing the tests (direct to DS, not OpenRouter). I suggest that if you can't conceive of anyone spending $200 on DeepSeek, you're not being ambitious enough!

There's your problem, 4.1 Flash is significantly better and cheaper, to the point where the official DeepSeek API is going to (or already has, I forget) redirect requests for Pro to 4.1 Flash, and adjust billing accordingly too.

4 Pro is still offered by providers I'm sure, since it's open weight, so I can understand making that mistake.

Why do you expect that $200 will give you that on ANY model? Multiplayer FPS games are very difficult to make, no AI will deliver that today.

Not sure that's why they did it. But that was my experience.

Suggest trying it out yourself: Ask for something difficult from GPT-6 Sol and Opus 5.5 and watch what each one does. The difference is stark.

Edit: Defining "difficult" as a complex coding or systems task (or even series of them in a single prompt).

1 - https://bench.killswitch-lang.org

No LLM will be cost effective if it's compacting this often. You have to find a way around it.

The lackluster GPT-6 Sol has been superseded by this apparently much better 6.1 Sol within a week.

I am very skeptical of claims that old models weren't much worse. Compare this to February's GPT-5.3.

I'm by no means an AI booster, but given 2022 - 2026 progress I'd say it's "exponential" in the sense of, "holy shit, every year I can do more and more genuinely different things", not "RSI mind reading intelligence can do anything is here".

I don't think Navier-Stokes level intelligence translates over to my projects, unfortunately. Yet? Who knows.

> I haven’t seen actual capability growth since ~January, and I’m pretty sure that was all tooling/harness improvements.

Even if that were the case, I'd say that it's improved in practice. And just from a philosophy perspective, if you're trying to imply some kind of mind dualistic way of viewing things, uh, I disagree with those theories of intelligence strongly (which also incidentally also disagrees with AIT-style theories of intelligence on one axis, though I have many bones to pick with the culture there).

Astra seems better though.

Showing one potentially saturated benchmark doesn't necessarily fill me with a lot of confidence in the coding results.

Since like last December I haven’t had any issues getting work done with whatever the latest Anthropic or OpenAI models at the time were. Tooling and models have only gotten better since then.

Consumers are now saying the new pricing with lower usage caps is not so great. https://news.ycombinator.com/item?id=49896975

It's not even anything controversial..

Edit: removed a comment that was uncharitable and rude, for which I apologize.

if true then LLM related AI (post-post AI winter AI?) is probably one of the fastest inception-to-plateau tech sectors to have ever existed.

We're still improving transistors on a somewhat routine basis.

I think it's more a token-cost-demand plateau. They've reached the scale and investor trillions to which they can't 10x the hardware cost of inference any more. They can't afford to compete by eating costs and there isn't appetite for more expensive inference.

So in order that they don't bankrupt each other they're looking for the legal cartel behavior coordinating a stop to growth by convincing governments to regulate them into stopping.

There's a lot of juice to squeeze in efficiency but only so much whereas it seemed like capability was going to continue to scale with parameter count.

Maybe it's good news for everyone that model capability is now going to scale on semiconductor cost meaning huge players are going to be very motivated to make semiconductors cheap.

I don't think that's the motivation, it's because both companies want to IPO and the _only_ way to even hope to be profitable is to do a whole lot less training, which costs a fortune. But unless Chinese labs go along with this gentleman's agreement (they won't), slowing down on training will bring about the inevitable Chinese model parity date more rapidly. At which point the game is well and truly over for OpenAI and Anthropic. Bit of a pickle they've gotten themselves into with the emphasis on being best, with premium prices to match.

People were talking about plateau for years already.

It just seems like these claims are constant and looking back the calls of 'plateau' between 2023 and 2025 were clearly false, why should we think it's different now?

Not once has any of these predictions come true, the pace of progress has continued on it's exponential trajectory since ChatGPT first came to the public's attention.

So why now? What is special about today that suggests all of this is coming to a screeching halt despite all evidence to the contrary?

I see posts about OpenAI and Anthropic latest and don’t even care looking at what they do better. I just read the comments here.

I use DS4.1 Flash and GLM 5.3 Flash, pay peanuts per day and get more than acceptable results.

Insane pricing pressure on the horizon. Even if big companies will not go with open weight models, the threat will be ever present that they can instantly flip flop on providers.

It's not frontier pelican without the back leg behind the bike frame IMO.

And yeah I have worked with Anthropic and OpenAI models, they're good but they cost a fortune while Chinese models are already really good at a fraction of the cost.

Is that what the Chinese models are capable of? If so, how are you using them? API? Or is there an inference provider that is as fast as the big 2? What about the coding harness?

Luckily it's not a mistake as now we have access to . . . dots.

(and sol 6.1, it seems)

It's because they need subscription money and interaction data and so keeping a version bump in the wings to stop the bleeding from your competitor's version bump is the logical thing to do. It has nothing to do with RSI.

Like think about a software org with good CI/CD versus one without. The mature org can do consistent incremental releases because each one is safe and low overhead, the messier org will do fewer big releases because each release requires a big effort on its own.

As model developers mature we might expect to see more frequent point releases rather than the big bang evolutions.

See, that's an/the issue. As soon as people start to flee to the improved model, they start to serve degraded models to keep up with the demand.

Now, as it's linear, it makes much more sense to downgrade to 100$ OAI and pick up a 100$ Claude sub. (without doing the numbers) the usage should remain the same, total paid the same, but having access to best of both worlds. It should be a win for the user, and a loss for OAI.

With this in mind, it sounds like a fumble by OAI.

Lastly, I'd like to actually use it in the real world to see how far my plan goes or if its unusable.

Well, the time it takes to compress frontier intelligence down to DeepSeek V4.1 Flash costs (basically too cheap to meter) is dropping, and the differential between the two is also dropping...

So... who cares?

Basically OpenAI aligned with Anthropic on the weekly usage with the caveat that OpenAI doesn't have a 5h limit.

Might want to hold off on canceling and continue to bleed them dry until the nerf hits

But $200 is likely the ceiling of what people will pay for a subscription with usage based on vibes.

I've only dabbled but yes with SOTA models it is very good at animating and really most Blender tasks you can think of. Certainly if you are coming at Blender at below expert level it makes it far more accessible and fun to work with.

There are still rough edges of course. But try the official MCP out with Astra and judge for yourself.

The best thing is that we benefit from these constant back and forth gut punches :)

So yes, it is clearly cheap in comparison.