xAI's Grok 4.7 lands on Amazon Bedrock
Amazon Bedrock has added xAI's Grok 4.7 with a 500K-token context window and reasoning effort levels from low to xhigh (default high). Per Artificial Analysis, the Intelligence Index rose from 44 to 46, but output tokens per task roughly doubled from ~38K to ~81K.
- Grok 4.7 offers a 500K-token context window via us. and global. inference profiles.
- Intelligence Index: 46 vs 44 for Grok 4.6; Coding Agent Index 56 vs 47.
- Output tokens per task rose from ~38K to ~81K.
- Supports Responses, Chat Completions, InvokeModel and Converse, plus prompt caching and Guardrails.
Read next
AI