xAI’s Grok 4.3 is now generally available on Amazon Bedrock, offering teams building agents and AI workflows a model that reasons reliably over long inputs. Grok 4.3 is a model with configurable reasoning effort, accepts text and image input, and has a 1 million token context window. It runs on Mantle, the next-generation inference engine in Amazon Bedrock. According to xAI, Grok 4.3 ranked #1 on the Artificial Analysis Omniscience benchmark with the lowest hallucination rate among the frontier models it compared, #1 on the Artificial Analysis Tau2 Telecom benchmark for tool calling, and #1 on the Vals AI Case Law and Corporate Finance benchmarks for document understanding. xAI places the model on the intelligence-versus-cost Pareto frontier, described as 2 to 10 times more intelligence per dollar than other frontier models. Users can configure effort level (none, low, medium, and high) per request. Grok 4.3 runs on Mantle, which uses OpenAI-compatible APIs, and can be invoked with the OpenAI SDK or through direct HTTPS requests to the Chat Completions API or the Respon.