Bedrock Adds In-Region Claude Inference in Seoul and Singapore for Data Residency
AWS ML Blog · rss · 2026-09-30
Amazon Bedrock now offers in-region inference in Seoul (ap-northeast-2) with Claude Opus 5 and Sonnet 5, and in Singapore (ap-southeast-1) with Claude Sonnet 5. Inference requests and data are processed entirely within the single Region you call and never leave it—suited to strict data residency requirements in financial services, healthcare, and the public sector.
Unlike cross-Region inference, there is no routing layer: requests are served solely by that Region, with throughput bounded by its capacity and per-Region quotas. Billing follows standard on-demand pricing, and CloudWatch metrics and CloudTrail logs are scoped to the same Region.
The post shows how to test models in the Bedrock console Playground and call them with direct model IDs (e.g., anthropic.claude-opus-5) via the Anthropic Messages API, InvokeModel, and Converse API, with Python examples; the bedrock-runtime endpoint is recommended for new applications.
More from Infra
- DeepSeek open-sources DeepGEMM Ascend port, hitting 99.8% of hardware limit on GEMM — zheanxu · 2026-09-30
- AI intelligence-cost Pareto frontier shifted fast: GPT-5 mini at 17 ($0.05) to Claude Opus 5.5 at 58 ($5.98) — ArtificialAnlys · 2026-09-30
- Google's Project Suncatcher to fly TPUs in space for the first time on Oct 1 — allisondman · 2026-09-30
- Photon 2.6 ships FP8 + speculative decoding, runs Qwen3.5 27B at 400+ tok/s on B200 — Bedrovelsen · 2026-09-30
- SGLang turns Qwen3.8-27B into a decision model that beats Pokémon FireRed at sub-100ms — zhaoran_wang · 2026-09-30
- Agentic AI turns CPUs into the overlooked bottleneck as CPU:GPU ratios shift upward — AccBalanced · 2026-09-30