Theo-brainUnofficial. Not affiliated with Theo or t3.gg.
Sign inYou

Matching the model to the job

Technique

Pick models by what a whole task costs, not by price per token. For bulk reading, input price matters most. For agent coding, caching (cheap reuse of already-read text), reliability and token efficiency matter more. You can also give a specialist job, such as design, deep review or game assets, to a model that is stronger at it.

Theo's current stance

Theo's default is Opus 5.5 for most work. He makes exceptions for specific jobs, such as Fable for front-end design and OpenAI models for deeply thorough review. For games, he's trying Astra as play tester and Fable as builder.

Try it

  1. Use Opus 5.5 for day-to-day coding tasks.
  2. Switch to Fable for a marketing page or a big design overhaul.
  3. For a deep codebase audit, try an OpenAI model.
  4. Compare models on total cost per finished task, and decide what quality the job needs first.

First seen

26:02
I think Opus is probably the right default for the vast majority of stuff. But you should not be as scared to reach to Fable for front end still, especially when you're doing like a marketing page or some big design overhaul.

My new favorite model.

Every mention

19:58
Once again, if you want the absolute best, it's probably a combination of using an OpenAI model for asset gen and 3D asset creation and then using anthropic models to actually make the game pleasant to play because uh yeah, open II still not…

Astra 6.2 Is Unusable

32:18
Still figuring out what goes where exactly. It does seem like 62 Astra is really good at play testing, so I might have it be the play tester and then keep using Fable as the implement.

Astra 6.2 Is Unusable

7:14
At that point, optimizing for the cheapest model for the input token read is probably the right call. If you're doing agentic dev work, things like caching, reliability, and token efficiency suddenly matter a hell of a lot more.

I thought AI was gonna get cheaper?

7:58
Like if you're happy with a 45 to a 46 as the score here, your cost will be 82 cents per task. Where if you want to bump up into the 50s, suddenly it's $3.26. So for just a few more points, you're spending three times more money.

I thought AI was gonna get cheaper?

24:44
This is now going to be 61 Soul high fast because I think it's a really good balance of speed, capability, and performance in general when I'm trying to do tasks where I'm managing the machines in my network.

I love Ultrafast (it's unusable)

26:02
I think Opus is probably the right default for the vast majority of stuff. But you should not be as scared to reach to Fable for front end still, especially when you're doing like a marketing page or some big design overhaul.

My new favorite model.

22:23
…planning on using this model to very thoroughly review code and find every single thing wrong with it or suggest sweeping improvements to your codebase, might not be as strong at those things as OpenAI's Frontier is.

My new favorite model.

Theo Daily is unofficial and not affiliated with Theo or t3.gg. Written by Claude Opus 5.5 from each video's transcript.