AWS Bedrock brings OpenAI GPT-5.6 cross-Region inference to Australia with full setup guide
AWS ML Blog · rss · 2026-09-03
Australian teams can now invoke OpenAI's GPT-5.6 family (Sol, Terra, Luna) via Amazon Bedrock global cross-Region inference, with Sydney and Melbourne as source Regions routing to supported commercial Regions automatically.
All three models take text and image inputs, support up to 1M token context: Sol targets heavy reasoning/coding/agentic workloads, Terra balances performance and cost, and Luna offers fast, cheap inference.
The post walks through:
- Verifying active global.openai.gpt-5.6- inference profiles via AWS CLI or console
- Calling the Responses API and Chat Completions API through the /openai/v1 path with the OpenAI SDK, authenticating via SigV4 or short-term inference API keys generated by aws-bedrock-token-generator (no static keys needed)
- Using the Converse API via AWS SDKs, including streaming
- Prompt caching on GPT-5.6, with implicit caching enabled by default, to cut inference costs
More from Infra
- SGLang Summit sponsors grow from 11 to 36 in one week; Lip-Bu Tan, Lilian Weng to speak — BanghuaZ · 2026-10-18
- Yacine jokes his datacenter KPI is gigawatt-hours: get paged if not burning enough power — yacineMTB · 2026-10-18
- 1.68x inference speedup drops, directly accelerating GRPO post-training — yacineMTB · 2026-10-18
- OpenRouter is only a fraction of the total addressable market, poster argues — sloppenheimer · 2026-10-18
- Developer builds change alerts for LLM prices and retirements across Bedrock, Azure and Vertex — jsandhu0780 · 2026-10-18
- 12.3M tokens in 27 minutes for $0.14: agent session with 99.6% cache hit — teortaxesTex · 2026-10-18