Model index
Every model on the fleet
Open weights run on clusters we own; proprietary models come through official commercial channels. The two are listed separately on purpose. Specs as deployed, changes in the changelog.
On our own GPUs
Officially released open weights, running on cards we bought. Weight version and precision are published, so you can re-test them.
Official commercial channel
Proprietary models cannot be self-hosted, so we provide access through the vendor’s official commercial licensing: contract, invoice, audit trail. No account pools, no reverse-engineered client protocols.
Need a different model?
If it ships open weights, we can almost certainly host it. Send the model and your expected volume; we’ll size the capacity and reply with a date.