Barathkanna
Joined 2 years ago
Karma
132
Submissions
87
Member since
Jul 13
Recent submissions
Comment · 7 months ago
Sounds like a plan, But what if you can just pay a fixed cost every month and not worry about anything?
Comment · 7 months ago
That’s true, but AI is interesting because consumption-based pricing introduces a lot more variance than typical SaaS infrastructure. One user action can trigger dozens of model calls in an agent workflow. That’s partly why we started experimenting with models like https://oxlo.ai where the pricing flips back to a fixed subscription and we absorb the usage spikes.
Comment · 7 months ago
Local models help remove token cost uncertainty, but they shift the problem to infrastructure and ops. GPUs, scaling, maintenance, and latency can add up quickly depending on the workload. For many builders it ends up being a tradeoff between predictable infra cost and flexible API usage.
Comment · 7 months ago
That’s great. Real-time tracking is a big step already. The tricky part we kept running into was the variance itself, especially with retries and agent loops. That’s partly why we started experimenting with Oxlo.ai (https://oxlo.ai) where the pricing model absorbs that variance so builders don’t have to constantly model token risk.
Comment · 7 months ago
One underlooked source of variance is retries from formatting failures. In many agent systems the loops dominate the cost, not the raw token length.
We ran into the same issue building agent workflows, which is why we started building https://oxlo.ai — experimenting with a flat subscription model where we absorb the token variance so builders don’t have to constantly model token risk.
Comment · 7 months ago
Agreed. The real cost unit becomes the whole agent workflow, not a single LLM call. One user action can trigger dozens of calls.
We ran into the same issue and ended up building https://oxlo.ai to make the cost side more predictable for agent workloads.
Comment · 7 months ago
Exactly. That’s actually why we started building Oxlo.ai. Early stage builders usually just want to experiment without worrying too much about token cost spikes.
Comment · 7 months ago
True, but for early stage builders it’s harder to design those guardrails upfront. A lot of the time you only discover the retry patterns and cost spikes once real users start hitting the system.
Comment · 7 months ago
Local models solve the marginal cost problem, but they move the complexity into infrastructure and throughput planning instead.
Currently experimenting with ways to make AI deployment as seamless as web deployment. Also building Oxlo, a global platform that lets developers launch and test AI models on GPU instances (free tier for small models, like Vercel but for AI).
Background in Rust, Substrate, Linux systems, and computer vision pipelines. Focused on building practical infrastructure that scales — from decentralized edge nodes to secure on-prem inference for smart cities.
Always interested in discussing: distributed compute, model serving, real-time AI, hardware acceleration, and deep-tech company building.