Provisioned Throughput
A capacity reservation billing model for Amazon Bedrock in which users purchase fixed throughput for a specific model to obtain stable latency and throughput guarantees.
Timeline (last 90 days)
Gemini Omni is now generally available, backed by Google Cloud's enterprise-grade infrastructure and security capabilities, supports Provisioned Throughput, and outputs carry an imperceptible SynthID watermark.
Provisioned Throughput is an hourly-billed capacity reservation model in which users purchase fixed input and output token processing capacity for a specific model (measured in Model Units), usually with a minimum commitment period and strongly tied to a specific model version.
Model discontinuation means that already-purchased Provisioned Throughput reserved capacity cannot be migrated to a new model and must be re-ordered.
For enterprise customers, vendors usually offer customized contract pricing, including options such as Provisioned Throughput.
All Facts (4)
Gemini Omni is now generally available, backed by Google Cloud's enterprise-grade infrastructure and security capabilities, supports Provisioned Throughput, and outputs carry an imperceptible SynthID watermark.
50%UnverifiedProvisioned Throughput is an hourly-billed capacity reservation model in which users purchase fixed input and output token processing capacity for a specific model (measured in Model Units), usually with a minimum commitment period and strongly tied to a specific model version.
50%UnverifiedModel discontinuation means that already-purchased Provisioned Throughput reserved capacity cannot be migrated to a new model and must be re-ordered.
50%UnverifiedFor enterprise customers, vendors usually offer customized contract pricing, including options such as Provisioned Throughput.
50%