NEWS · MODELS · #1912
SpaceXAI's Grok 4.7 added to Amazon Bedrock
SpaceXAI announced Grok 4.7 is available on Amazon Bedrock with features aimed at long-horizon agent workloads: a 500K-token context window, tool calling, configurable reasoning-effort levels (low/medium/high/xhigh), and support for Chat Completions/Responses and the Bedrock Converse API. In SpaceXAI's tests of a tool-calling agent on three search-style tasks, the agent answered 67 of 72 runs correctly (18/18 at xhigh; 15/18 at low), illustrating a tunable trade-off between correctness and token use; Bedrock access uses cross-Region inference profiles and requires specific IAM permissions.
KEY POINTS
- SpaceXAI announced Grok 4.7 is available on Amazon Bedrock with features aimed at long-horizon agent workloads: a 500K-token context window, tool calling, configurable reasoning-effort levels (low/medium/high/xhigh), and support for Chat Completions/Responses and the Bedrock Converse API.
- In SpaceXAI's tests of a tool-calling agent on three search-style tasks, the agent answered 67 of 72 runs correctly (18/18 at xhigh; 15/18 at low), illustrating a tunable trade-off between correctness and token use; Bedrock access uses cross-Region inference profiles and requires specific IAM permissions.
- Makes a long-context, tool-aware Grok model (with tunable deliberation) available to Bedrock customers, relevant for running and tuning multi-step agent workloads and measuring cost/accuracy trade-offs.
WHY IT MATTERS
Makes a long-context, tool-aware Grok model (with tunable deliberation) available to Bedrock customers, relevant for running and tuning multi-step agent workloads and measuring cost/accuracy trade-offs.