| ▲ | taylorfinley 4 hours ago |
| 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. |
|
| ▲ | faitswulff 3 hours ago | parent | next [-] |
| 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. |
| |
| ▲ | Computer0 3 hours ago | parent | next [-] | | 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. | | |
| ▲ | swingboy 3 hours ago | parent | next [-] | | If you disable all other providers but DeepSeek in your OpenRouter guardrails, is that effectively the same thing? | | | |
| ▲ | roarkeful 3 hours ago | parent | prev [-] | | How do you do this? | | |
| |
| ▲ | gigatexal 40 minutes ago | parent | prev [-] | | 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. |
|
|
| ▲ | rapind 2 hours ago | parent | prev [-] |
| 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. |
| |
| ▲ | ampdot an hour ago | parent [-] | | DeepSeek, DigitalOcean, GMICloud, and NovitaAI were the only OpenRouter providers that didn't lead to major performance degradation for me |
|
