Pricing and billing
Per-model pricing
Pricing is dynamic and subject to change. Current per-token rates:
Cached input applies to repeated prompt prefixes marked with
cache_control: 10% of the input price for Hal 1.0 and Clarke 1.0, 20% for Tycho 1.0.
For current rates, see radium.cloud/pricing.
How billing works
Billing is per token, measured on every request. Input tokens include the prompt, system message and any tool definitions. Output tokens include the completion, reasoning tokens and tool call arguments. Repeated prompt prefixes marked withcache_control are billed at the cached input rate.
View usage in the dashboard at deploy.radium.cloud.