We’re currently spinning up operations and looking for capacity. We should be listing on OpenRouter soon.
Work with us directly
If you have special requirements, we would be happy to work with you directly.
Volume pricing
If you serve heavy, sustained traffic—say, coding agents for thousands of users—contract with us directly for a discount on per-token rates.
Dedicated deployments
Reserved capacity for your model or fine-tune, with predictable latency.
Reserved throughput
Guaranteed tokens per second and rate limits sized to your traffic, so your product doesn’t slow down at peak.
GPU capacity
We’re buying capacity. If you have GPUs to rent, get in touch with the GPU type and count, location, interconnect, available date, term, and price per GPU-hour.