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. Best for reasoning-heavy tasks that need more deliberate model control.
Best forBest for reasoning-heavy tasks that need more deliberate model control.
Temperature0 to 2
Reasoning effortlow, medium, high, xhigh
VerbosityNot supported
Thinking levelsNot supported
Structured outputsSupported
Tool choiceSupported
Computer useNot supported
Deep researchNot supported
Memory supportSupported
Max output tokensNot published
Frequently asked questions
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.
