Source record
The source recommends routing difficult analytical work to smarter models while using Sonnet 5 for straightforward tasks that still need capability.
Anthropic just released Claude Sonnet 5, and while it is a very impressive model in a lot of ways, it's not quite what Anthropic says it is. So I just want to talk about what we know so far about Sonnet 5, when you should be using it, and when you should not be using it. First, let's talk about cost.
8, but at a much lower cost. And this is true if you're talking about the cost per token. 8 costs.
8 costs. However, for difficult tasks like software engineering tasks, sonnet uses way more tokens, and you can see this on the graphs that anthropic put out. 8 at a slightly higher cost.
But that doesn't mean sonnet 5 is useless. 6 for anything, you should definitely be using Sonic 5 now. 8 at a lower cost.
8 and slightly faster. So I don't recommend giving Sonic any kind of difficult analytical work. It Was the kind of work you would only give to a very smart person.
I would only give it to a very smart model, but for straightforward tasks where you still want a capable model, it seems like sonnet 5 is going to be fantastic. There are still two big elephants in the room fable 5 and Opus 5. Fable 5, of course, is Anthropic's biggest model.
It's by far the smartest model in the world right now, and we should
in the room fable 5 and Opus 5. Fable 5, of course, is Anthropic's biggest model. It's by far the smartest model in the world right now, and we should get it back today.
What we don't know is if anthropic is going to force us to pay for usage or if they're going to continue letting us use it on the subscription. If you don't know, the subscription rate is heavily subsidized. On a match plan, you only pay about 4% of what you would pay if you were paying for usage.
So that decision will determine whether many of us can afford to use what I think everyone agrees is a very powerful model. However, it's also quite odd that we're getting Sonnet 5 and Cable 5 before getting Opus 5, Opus being the model that sits in between those two classes. I suspect we'll be getting that model soon, but also it'll probably spark a government security review.
The source recommends routing difficult analytical work to smarter models while using Sonnet 5 for straightforward tasks that still need capability.
Separate AI workflows by complexity: reserve top-tier models for hard analysis and software reasoning, and use cheaper capable models for straightforward writing or production tasks.
This source is connected to Model routing by task difficulty.
I don't recommend giving Sonic any kind of difficult analytical work. It Was the kind of work you would only give to a very smart person.