NEWS · MODELS · #1176
xAI’s Grok 4.7 becomes available on Amazon Bedrock
xAI has made Grok 4.7 available via Amazon Bedrock (served through the bedrock-runtime endpoint with cross-Region inference profiles). The model offers a 500K-token context window, four configurable reasoning-effort levels (low/medium/high/xhigh), improved long-horizon self-verification for coding and knowledge work, new safeguards, and support for Responses, Chat Completions, InvokeModel and Converse APIs.
KEY POINTS
- xAI has made Grok 4.7 available via Amazon Bedrock (served through the bedrock-runtime endpoint with cross-Region inference profiles).
- The model offers a 500K-token context window, four configurable reasoning-effort levels (low/medium/high/xhigh), improved long-horizon self-verification for coding and knowledge work, new safeguards, and support for Responses, Chat Completions, InvokeModel and Converse APIs.
- This matters because Grok 4.7’s very long context window, configurable reasoning effort, and stronger self‑verification are aimed at more reliable long‑horizon agentic and coding workflows and are now accessible in a major cloud model catalog.
WHY IT MATTERS
This matters because Grok 4.7’s very long context window, configurable reasoning effort, and stronger self‑verification are aimed at more reliable long‑horizon agentic and coding workflows and are now accessible in a major cloud model catalog.