⚡ BREAKING
ModelsBusiness & Market 🇺🇸 26.07.2026 23:03

OpenAI GPT-5.6 Sol, Terra, and Luna Models Now Available on Amazon Bedrock

OpenAIOpenAI Amazon Web ServicesAmazon Web Services
OpenAI's GPT-5.6 family (Sol, Terra, Luna) is now generally available on Amazon Bedrock, accessible via the OpenAI Responses API on the bedrock-mantle endpoint. The models target different workloads: Sol for deep reasoning and autonomous coding, Terra for balanced production use, and Luna for high-volume low-latency inference. They feature a 272K-token context window, text and image input, and configurable reasoning effort levels.
OpenAI has made its GPT-5.6 model family—Sol, Terra, and Luna—generally available on Amazon Bedrock. The models are accessed through the OpenAI Responses API on the bedrock-mantle endpoint, and pricing matches OpenAI first-party rates, counting toward AWS commitments. Sol is designed for autonomous coding, security research, and deep multi-step reasoning; Terra balances performance and cost for everyday production workloads; Luna is optimized for high-volume, latency-sensitive tasks like classification and summarization. All models support text and image input, a 272K-token context window, and reasoning effort levels from none to max. They run under AWS IAM policies inside a user's VPC, with data not used for training and only retained for abuse detection if flagged. Caching is available in implicit and explicit modes, with a 90% discount on cached input tokens. Users can also try models in a new project-based Bedrock console. The models are available in US East (N. Virginia) for Sol, and also in US East (Ohio) and US West (Oregon) for Terra and Luna.
Сокращения
API = Application Programming Interface — интерфейс программирования приложений
AWS = Amazon Web Services — Amazon Web Services
IAM = Identity and Access Management — управление идентификацией и доступом
VPC = Virtual Private Cloud — виртуальное частное облако
SDK = Software Development Kit — набор средств разработки
RAG = Retrieval Augmented Generation — генерация с дополнением по поиску
Source: AWS ML blog — original
Our earlier posts on this topic ↓
Fresh news