Thunder Compute Alternatives for Inference
Serving or batch-running a model for generation, where throughput per dollar decides the bill.
What inference actually needs
Why people look past Thunder Compute for this
Little state to carry, so this is the job that moves most freely on price. The cost is the weight pull and the warm-up on the new box, not lost work. That is exactly the gap Thunder Compute does not close: Thunder Compute has the better local-editor story, full stop: a real VS Code, Cursor and Windsurf extension with a connect button, which we do not have. Aquanode's argument is not the editor: it is that a Thunder snapshot stays inside Thunder, while an Aquanode snapshot restores onto a different provider.
To be fair, Thunder Compute's real strength is real: A genuine local IDE integration: an installable VS Code / Cursor / Windsurf extension that connects you to a remote GPU from the editor. Aquanode has no editor extension. Our CLI writes a managed SSH alias and that is all; Remote-SSH working at all is a side effect of the alias existing, not a feature we built.
Live rates for the GPUs inference wants
Live per-GPU rates from Aquanode's marketplace. Refreshes hourly.
How you run it here today
Run it today with the seeded vllm-batch job recipe — a real, publicly-imaged container Aquanode can queue directly, not a template we're promising to build later.
Restoring an environment requires a snapshot that already exists. Stopping a deployment yourself captures it on the way out, so you can bring it back later on any provider. A provider-side termination is different: it is only recoverable if you had already switched automated snapshots on for that deployment, and it costs you the work since the last one. Automated snapshots are opt-in, nothing runs until you start it, and with none running there is nothing to restore.
More alternatives pages
Other workloads on Thunder Compute
Inference alternatives to other clouds
