Grok 4.6

Grok 4.6 is a xAI model available in Agent Serve. Grok 4.6 is a xAI model tracked in Agent Serve. It supports a 500k token context window. Pricing starts at $2/1M input tokens and $6/1M output tokens. Key capabilities include Temperature 0-2, Tool choice, Structured outputs.

Grok 4.6 starts at $2/1M input tokens, $0.5/1M cached input tokens, and $6/1M output tokens. Above 200k input tokens, the full request is priced at $4/1M input tokens, $1/1M cached input tokens, and $12/1M output tokens.

Grok 4.6 supports a context window of 500k tokens in Agent Serve. In an agent, this determines how much conversation history, tool outputs, and retrieved documents the model can hold in a single call.

Grok 4.6 supports the following capabilities in Agent Serve: Temperature 0-2, Tool choice, Structured outputs, Reasoning low, medium, high, xhigh.

Best for reasoning-heavy tasks that need more deliberate model control. When used in an Agent Serve workflow, it can be selected in any Agent block from the model picker.