OpenAI GPT-5.6 Sol, Terra and Luna go live on Amazon Bedrock
AWS ML Blog · rss · 2026-07-24
AWS says OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock through the OpenAI Responses API.
- Sol targets autonomous coding, security research, scientific analysis, and deep multi-step reasoning.
- Terra is positioned for general production workloads that balance performance and cost.
- Luna is tuned for high-volume, latency-sensitive tasks such as classification, summarization, and routing.
All three models support text and image input, a 272K-token context window, and configurable reasoning effort levels from none to max. AWS also highlights Bedrock integration details such as the bedrock-mantle endpoint, OpenAI SDK compatibility, prompt caching, tool calling, IAM/VPC/CloudTrail controls, in-Region inference, and data-retention settings. Pricing matches OpenAI first-party rates and usage counts toward existing AWS commitments.
More from Infra
- Engram's random reads don't suit SSDs; CPU-memory over NVLink could serve all 72 GPUs — bookwormengr · 2026-09-11
- 80% of the DIY LLM inference hype posters have already quit — it's brutally hard systems work — abhijithneil · 2026-09-11
- Hugging Face's Ultra Scale Playbook: a free book on training LLMs on GPU clusters — mdancho84 · 2026-09-11
- Is inference latency becoming the biggest bottleneck for production AI agents? — Euphoric_Sea632 · 2026-09-11
- LLM Serving Metrics Thread: Why TPOT and Uptime Make or Break User Experience — abhijithneil · 2026-09-11
- PlanetScale launches sharded Postgres: 768 servers acting as one, 1PB scale — dhruv2038 · 2026-09-11