undefined | Better HN

0 pointsnicce1y ago0 comments

1. You can get all the models by buying Kagi subscription (excluding o1). Includes DeepSeek models. You can also feed the assistant with search data that you can filter.

2. If you have GitHub Copilot, you get o1 chat also there.

I haven't seen much value with OpenAI subscription for ages.

0 comments

sureglymop1y ago

I have Kagi Ultimate and it is nice for this. But a cheaper suggestion would be to use OpenRouter and then use these models via Fireworks or TogetherAI. It also integrates into much more applications. AFAIK Kagi doesn't document a user facing API for the assistant feature.

phaedrix1y ago

Unfortunately those are both 10-15x the cost of deepseek direct.

Deepinfra is pretty cheap though as a deepseek provider.

sureglymop1y ago

Sure. I meant moreso that this would be cheaper than Kagi while providing the same selection of models.

As for deepseek, I couldn't even sign up because my email domain is not on their whitelist. To just try it out for now I don't mind the increased cost.

pants21y ago

That's because DeepSeek is subsidizing their API massively to get more training data.

j / k navigate · click thread line to collapse

0 pointsnicce1y ago0 comments

1. You can get all the models by buying Kagi subscription (excluding o1). Includes DeepSeek models. You can also feed the assistant with search data that you can filter.

2. If you have GitHub Copilot, you get o1 chat also there.

I haven't seen much value with OpenAI subscription for ages.

0 comments

sureglymop1y ago

phaedrix1y ago

Unfortunately those are both 10-15x the cost of deepseek direct.

Deepinfra is pretty cheap though as a deepseek provider.

sureglymop1y ago

Sure. I meant moreso that this would be cheaper than Kagi while providing the same selection of models.

As for deepseek, I couldn't even sign up because my email domain is not on their whitelist. To just try it out for now I don't mind the increased cost.

pants21y ago

That's because DeepSeek is subsidizing their API massively to get more training data.

j / k navigate · click thread line to collapse