Guides

Practical guides to inference pricing, capacity, and running open models.

Pricing and sizing

Concurrency vs token pricing
Compare the pricing models and find the better fit for your workload.
How much concurrency do I need?
Count simultaneous model calls, choose a plan, and know when to add capacity.

Running open models

Renting GPUs vs managed inference
Understand the hardware, costs, and ongoing work behind serving open models.

Using LunaRoute with your tools

Using Claude Code with LunaRoute
Keep your workflow and Claude plan. Run longer sessions on fixed-price capacity.

Find your capacity.

Compare plans by priority concurrent requests.

See plans and pricing