Not by cost per task, just cost per token. But they're spending way more tokens per task, so it doesn't work in their facor.
I still use them because they aren't as squeamish about random things American CEOs don't like like decompilation.
I still use them because they aren't as squeamish about random things American CEOs don't like like decompilation.
They are not most expensive per Task. DeepSeek 4.1 flash is bloody efficient.
I currently did run a test myself: - Use the pay as you go offer on OpenRouter on the same task on two different project: Perf optimisation on C++ codebase both with Anthropic and DeepSeek.
- I exploded my 15$ budget in a half-week with Anthropic.
- I did two weeks and half with DeepSeek.