Grok 4.7 is now available on Amazon Bedrock
Machine Learning Blog
This article announces the availability of xAI's Grok 4.7 on Amazon Bedrock, a frontier model designed for coding, long-running agents, and knowledge work.
- Grok 4.7 features a 500K token context window with four configurable reasoning effort levels: low, medium, high, and xhigh
- Model excels at self-verification and long-horizon tasks, with improvements across coding, legal work, clinical reasoning, and professional knowledge work
- Available through cross-Region inference profiles (us.xai.grok-4.7 for US residency, global.xai.grok-4.7 for global routing) with three service tiers: standard, priority, and flex
- Supports Responses, Chat Completions, and Converse APIs with OpenAI-compatible endpoints and image input capabilities
- Integrates with Bedrock features including implicit prompt caching, Guardrails, structured outputs, and invocation logging
- Reasoning effort level is a primary cost and latency control; higher levels provide more self-checking for multi-step tasks
Grok 4.7 on Amazon Bedrock enables developers to build sophisticated agentic AI solutions with strong performance on complex, long-running tasks requiring verification and reasoning.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.