← Back to context

Comment by redlock

9 days ago

Doesn't OpenRouter ranking include pricing?

Not really a good measure of quality or performance but of cost effectiveness

1 comment

redlock

Reply
mbesto  9 days ago

I mean it literally says on the page:

"Shown are the sum of prompt and completion tokens per model, normalized using the GPT-4 tokenizer."

Also, it ranks the use of Llama that is provided by cloud providers (for example, AWS Lamda).

I get that OpenRouter is imperfect but its a good proxy to objectively make a claim that an LLM is "the weakest ever"