Post
But how are you going to make it fixed price if you dont throttle? Their costs are not fixed
0 reposts0 likes
it is a similar model to the one synthetic uses. they limit you to 500 req/h and only 1 concurrent req/model so you spread the load across different models. it currently is $7/m and referral gives you $10 🙂 (maybe not now that they have this offer going on, not sure) synthetic.new?referral=ir6...
synthetic.newSynthetic | Run LLMs, privatelyChat with open-source models privately