Hacker News Reader

Comment by taylorfinley | Hacker News Reader

Were you using OpenRouter? I've used 1.8bn tokens in the past week from DeepSeek themselves and 99.2% were cache hits. Total cost was $18.13 usd.

View on HN

For readers wondering, OpenRouter isn’t capable of caching as effectively as DeepSeek is because they will, for instance, switch inference providers in the middle of a session.

The way I use openrouter is I find a model/provider combination I like then pin all requests for that model to that single provider.

How do you do this?

provider: { order: ['deepinfra/turbo'], allowFallbacks: false, },

https://openrouter.ai/docs/guides/routing/provider-selection

What harnesses are capable of doing this provider pinning when doing requests on openrouter? Can DeepSeek harness (dsh) do it? Or opencode etc

I stopped using opencode because it has some issues with caching, so I suppose it doesn't do this

Open code and pi can do it. Unironically, I let Claude configure these things for me.

Deepseek plugins* all the way down. It should be easy to add support for this.

Using this interesting framework called Cordis I've recent discovered.

What pests said. And you can make a preset and pass "model": "@preset/deep-seek"

If you disable all other providers but DeepSeek in your OpenRouter guardrails, is that effectively the same thing?

Sure but you still pay only OpenRouter :)

Interestingly, OpenRouter will serve inference at cost for a lot of models.

No? They charge 5.5% (I believe) on every top-up. Which is the equivalent of charging you 5.5% on every request.

Ah, so that's where the profit comes from. Very payment-processor like move, makes sense that Stripe picked them up.

How can they? If you use openrouter Deepseek fine but can’t you select the model direct from Deepseek you’re basically getting api access models that way.

Fireworks directly. At the time they were the best value of cost, speed, ZDR. They got slower on me though, but I think they are retooling, so maybe things have or will get better again. I think fireworks is primarily for when you want to do your own training on top, which I wasn't doing.

DeepSeek, DigitalOcean, GMICloud, and NovitaAI were the only OpenRouter providers that didn't lead to major performance degradation for me

Reply on news.ycombinator.com