Framer AI AgentsDesign and publish professional sites with AI
Promoted
Congrats on launch @emirsoyturk I’ve been using it for the past week, and I’ve genuinely been impressed with the results. The speed improvements on GLM 5.2 are noticeable right away, and it’s already become part of my workflow. Great product.
Report
Latency felt noticeably snappier than what I usually get from other inference providers, and I love that nothing gets stored. Refreshing to see a team actually prioritize both speed and privacy at the same time.
@selim321016 Amazing! We are working hard to optimize models specifically for long-context agentic workflows.
Report
Love that there's no request retention here, that's a real differentiator for anyone dealing with sensitive data. One thing that would help me evaluate it faster though: a small public latency dashboard comparing Zro to other inference providers on common open models. Even just a simple weekly update with p50 and p95 numbers across regions would make it way easier to decide if it's worth migrating workloads over.
@hannah_parker5 That’s true. Privacy alone may not be enough for some users. The most important real-world metric is cost per completed task. Models are getting smarter, and using them is becoming easier and cheaper every day.
Open-weight models are already competitive in both intelligence and cost, and they’re improving quickly on both fronts.
Speed is another important factor. The SGLang team and we at MoonMath are working hard to improve these models, especially for long-context agentic workflows.
Latency felt noticeably snappier than what I usually get from other inference providers, and I love that nothing gets stored. Refreshing to see a team actually prioritize both speed and privacy at the same time.
Zro
@selim321016 Amazing! We are working hard to optimize models specifically for long-context agentic workflows.
Love that there's no request retention here, that's a real differentiator for anyone dealing with sensitive data. One thing that would help me evaluate it faster though: a small public latency dashboard comparing Zro to other inference providers on common open models. Even just a simple weekly update with p50 and p95 numbers across regions would make it way easier to decide if it's worth migrating workloads over.
Zro
@selinkutbag9gj Good idea, thanks for the feedback!
I've been using Zro for about a month, it's great!
Very fast and reliable
Zro
@adi_milstein Thank you! Is there anything we can do to make your experience even better?
The API speed of response is really fast. Been used for a while and very satisfied by the quality of the API.
Zro
@peter_chen21 Thanks! We're actively working on adding more models and faster responses. Do you have any features/models that you'd like to see added?
@jeremy_felder Thanks! I think Deepseek V4 Pro would be a nice model.
Zro
@peter_chen21 Perfect, we're actively working on optimizations for it. No exact launch date for it yet but soon 🙂
@jeremy_felder That's super awesome!
"openai keeps cutting prices every few months, not sure privacy alone convinces people to switch providers".
Zro
@hannah_parker5 That’s true. Privacy alone may not be enough for some users. The most important real-world metric is cost per completed task. Models are getting smarter, and using them is becoming easier and cheaper every day.
Open-weight models are already competitive in both intelligence and cost, and they’re improving quickly on both fronts.
Speed is another important factor. The SGLang team and we at MoonMath are working hard to improve these models, especially for long-context agentic workflows.
Fastest API I have ever used so far.
Zro
@yamancan Happy to hear that! More improvements are on the way.