261–270 of 279 posts
Earlier quoted context omitted.
I recommend nvidia nim for completely free dev access for young people.
It's free, but not unlimited. Besides rate limits, new sign-ups get 1000 credits (requests), and once those are gone, they're gone for good. Only business accounts might get a couple of free refills.
Earlier quoted context omitted.
Proving my point. Your prompt gets sent through TR, to another provider on the other end. There are zero guarantees beyond "trust me bro" that the inference provider isn't taking your prompts and selling them to promptbase or one of a dozen other similar services. Venice claims no logs, which may or may not be true, but what happens to your prompt after they proxy it to the service running the GPUs? From their websit…
TR is end to end encrypted to the provider, and we offer providers like Tinfoil that are also end to end that we also attested using Secure Enclaves. OpenRouter doesn't provide that guarantee. This is entirely transparent. TR is also 100% open source. It'd be nice if you acknowledged the value of this.
Earlier quoted context omitted.
it's here: https://trustedrouter.com/providers
Proving my point. Your prompt gets sent through TR, to another provider on the other end. There are zero guarantees beyond "trust me bro" that the inference provider isn't taking your prompts and selling them to promptbase or one of a dozen other similar services. Venice claims no logs, which may or may not be true, but what happens to your prompt after they proxy it to the service running the GPUs? From their websit…
Earlier quoted context omitted.
Proving my point. Your prompt gets sent through TR, to another provider on the other end. There are zero guarantees beyond "trust me bro" that the inference provider isn't taking your prompts and selling them to promptbase or one of a dozen other similar services. Venice claims no logs, which may or may not be true, but what happens to your prompt after they proxy it to the service running the GPUs? From their websit…
You need to learn about Secure Enclaves
I went to AMD's offices and learned about them from the greybeards that built it.
If you think that's the end all solution, you're wrong. Tip of the iceberg...
https://www.amd.com/en/resources/product-security/bulletin/a...
Earlier quoted context omitted.
To put that in perspective, if you assume a token is 4 bytes, that’s about 164 MB/s of traffic, which sounds a bit less staggering.
Dealing with a lot of traffic for a small team isn't hard in itself. If it is easy to parallelise you just need to horizontally scale. And most concerns can be added as sidecars or middleware. Rate limits, auth, etc. Basically this is a kubernetes cluster. For a 3 person startup hard. For 50 pretty managable.
Earlier quoted context omitted.
The value of openrouter isn't as a middleman for users of claude, gemini or chatgpt, it's for those looking to find a model that fills the use case at a lower price than the top 3.
Except the latency is significant and not suitable for clients with advanced agent features. The experience between using a frontier model via first party API and the best open weight models via OpenRouter is night and day. Can't get any real work done with it.
Earlier quoted context omitted.
Would you recommend Kagi Ultimate over OpenRouter? I'm already a customer of Kagi and would rather give them my money, but only if I'm not really compromising.
> Would you recommend Kagi Ultimate over OpenRouter? For personal use, yes. The all-in pricing model encourages experimentation. And the privacy pitch seems tighter.
The difference between GLM 5.1, ChatGPT 5.4 and Opus don't really matter to me when I'm asking/talking, but programming is a different beast that needs a harness.
OpenRouter’s founder jumping from NFTs to AI has to be studied. Seriously the goat of sector rotation
Tokenrouter! (already taken).
Earlier quoted context omitted.
What differentiation are looking for? We have good documentation of every provider and what their data retention stance is, and you can figure allow/blocklists for all providers. Check out the Guardrails section under settings and tell me what’s missing!
I’m specifically looking for it on the model page before I click into it if there’s any valid provider for it