Pricing model
Public Models use metered inference pricing: recorded input and output usage is evaluated against the published catalog rates. Compute is different because it bills active GPU time for the instance you launch.
Billing terms
| Term | Definition |
|---|---|
| Rate reference | Catalog rates are stated in EUR per one million input or output tokens. This common unit makes model and regional variants directly comparable. |
| Usage measurement | For successful inference, the platform records the input and output usage reported by the provider and applies the corresponding published catalog rates. |
| Streaming | Streaming follows the same usage measurement. The platform aggregates the final usage payload emitted by the provider at the end of the stream. |
| Failed calls | Calls that fail before the provider records inference usage do not create a usage charge. Partial responses use the usage recorded before the interruption. |
| Ledger | Every public-model call is recorded as a ledger entry keyed under inference/public/<model-name>/<id> and grouped under the public-model resource group on the billing page. |
Limits and availability
- Chat only: The current catalog supports chat completions. Embeddings and image generation are not exposed as public models yet — use Compute for those workloads.
- Provider failover: Models with more than one provider (e.g. deepseek-v3.2) are routed through the platform’s public-model router. The provider list is configured per model and tried in priority order; a 502 from the first provider triggers a retry on the next.
- Regional residency: Variants ending in -european are pinned to a single AWS region. The global variants can be served from any region the provider supports.
- No scheduling controls: Public models have no schedule, start/stop, or smart constraints. They are always available as long as the provider is healthy.
