Get affordable AI #inference with data residency and privacy controls.
Or get paid to host #ai inference on your computer or dedicated #GPU rig with our OSS.
We've decided to offer inference for Qwen-3-Coder-30B-A3B
We're charging $0.067 / $0.267 per million tokens.
Giving away free tokens to get started, no card required.
OPENAI_BASE_URL=https://t.co/cKcj9Z5cXg
Give it a try, let us know how it works out for you!
Programmers and production workloads, we've got affordable inference for you!
Join Scalattice and start with Free tokens today.
Qwen-3-coder-30b-a3b is available on Scalattice alongside our affordable open weights inference.
Programmers and production workloads, we've got affordable inference for you!
Join Scalattice and start with Free tokens today.
Qwen-3-coder-30b-a3b is available on Scalattice alongside our affordable open weights inference.
Hi @wcheung2180 we understand your frustration, however we are offering hosted inference for Qwen3.8 27
It is free to download a model file, but that is different from hosting it.
Many companies and products don't want to self-host, and in that case, they turn to companies like Scalattice, Vast AI, OpenRouter, etc.
We are not intending to exist as a tax on people who don't know how to download, that isn't our business model.
We prioritise providing the most affordable hosted inference possible.
Hi Sebastian,
Engineering at Scalattice here, we just ran a few benchmarks on this new Ornith-1.5 offering on our network and here is how it went!
We ran 10 concurrent streams on the network for each SKU.
9B (8GB): holds 10 overlapping chats. Short replies in single-digit seconds. No rate limit.
35B (24GB): holds 10 overlapping chats. Short replies in tens of seconds. No rate limit.
We publish our precise data once we've collected at least a week of continuous benchmarking, but overall the model is performing to standard and exceeding in ~10% of instances.
Feel free to time it yourself too! We'd love to hear your experience: ornith-1.5-9b / ornith-1.5-35b-a3b on https://t.co/5XwAyH2q3o.
We all want an inference API that just doesn't slow down.
And a budget that isn't gone before the top-up invoice arrives.
We can finally have both!
With an OpenAI-Compatible API, and the most affordable open-model inference in the world, Scalattice is inference for everyone.
We all want an inference API that just doesn't slow down.
And a budget that isn't gone before the top-up invoice arrives.
We can finally have both!
With an OpenAI-Compatible API, and the most affordable open-model inference in the world, Scalattice is serving the best of both worlds.
https://t.co/EikM95Y1S8
Hi Talha, our API offers a variety of security tiers per request, to answer your question better we have included a link to our documentation below.
Our pricing model is designed to help new developers get the affordable inference they need, and we pledge to keep it that way!
https://t.co/qdmw8kAKyn
Customers want to remember your product, not the UX of your software.
Enrich your software with affordable inference to drive chat based navigation.
With an OpenAI-Compatible inference API, Scalattice is the perfect provider for your inference needs.