Grok 4.7 appears in Amazon Bedrock with 500K-token context and four effort profiles

Grok 4.7 appears in AWS Bedrock’s model catalog with a 500K-token window and multiple inference profiles, enabling enterprises to run Grok without leaving the AWS control plane.

In this brief: 2 sections 1 min read

- Model available through Responses, Chat Completions and Converse APIs on Bedrock.
- Inference profiles named us.xai.grok-4.7 and global.xai.grok-4.7 referenced.
- Bedrock positioned the model for coding, long-running agents and knowledge work.
- 500K-token context window and text+image input.
- Four reasoning-effort levels: low, medium, high, xhigh.
- Cited Artificial Analysis figures showing Intelligence and Coding Agent index increases and average output per task rising to ~81K tokens.

Read full analysis on aiweekly.co

Useful?