Amazon Bedrock pricing page (per-provider on-demand/batch/provisioned model tables)

Fetched 2026-10-14. Page is a per-provider tab set (Anthropic, Meta, DeepSeek, OpenAI, Qwen, Mistral, xAI, Z AI, others) with per-region selectors; most price cells render client-side and did not extract. Confirmed structure: on-demand and batch pricing per model per region, batch 50% below on-demand for select FMs, provisioned throughput and the newer Standard/Flex/Priority/Reserved service tiers. Llama 2 Chat 70B $1.95/$2.56 visible in the legacy table. Use the Bedrock console or per-region pages for a specific quote - this record exists so the service record can honestly cite 'per-model, per-region list table' as its basis.