Grok 4.7 is now available on Amazon Bedrock

xAI's Grok 4.7 is now available in the Amazon Bedrock model catalog. According to xAI, it is the company's most capable model for coding and knowledge work, designed to work longer on difficult tasks and verify its own output more carefully before continuing. The model accepts text and image input and returns text, with a 500K token context window and configurable reasoning effort at four levels: low, medium, high, and xhigh. The default is high.

xAI says Grok 4.7 uses a new and larger base model, trained with a longer reinforcement learning run over a harder mix of tasks weighted toward problems that take many hours to complete. xAI credits the training with better self-verification and more effective use of the context window on long tasks, and says the model natively understands the Grok Bot harness. xAI reports gains on published evaluations including CursorBench, DeepSWE, Terminal-Bench, AA Briefcase, EEBench, the Harvey Legal Agent Benchmark, and HealthBench Professional.

Independent evaluator Artificial Analysis reports Grok 4.7 improves across its suite, with the largest gains on long-horizon agentic knowledge work and coding agents run in xAI's own harness. Its Intelligence Index rose to 46 from 44, Coding Agent Index to 56 from 47, and AA-Omniscience Index to 32 from 30. Artificial Analysis measured Grok 4.7 at xhigh effort and reports output tokens per Intelligence Index task at roughly 81k, up from about 38k.

xAI says Grok 4.7 was built with an entirely new safeguard stack and is the strongest model it has tested on refusals and jailbreak resistance. xAI has begun giving selected cyber security partners invite-only access to the model's red-team capabilities for defense research.

On Bedrock, the model is served on the bedrock-runtime endpoint through two cross-Region inference profiles, us.xai.grok-4.7 and global.xai.grok-4.7, rather than a bare model ID. It supports the Responses API, Chat Completions API, InvokeModel, and Converse API. The OpenAI SDK works against the /openai/v1 path with a bearer token, which can be an Amazon Bedrock API key or a short-term token minted from IAM credentials; AWS SDKs use Converse with SigV4 signing. Bedrock features include implicit prompt caching, Guardrails, structured outputs, and invocation logging to CloudWatch. Service tiers are Standard, Priority, and Flex.