Grok 4.6

LLM Provider / Model · Long-running agents, coding and ambitious interactive/visual work

At a glance

Input price	$2
Output price	$6
Cache price	$0.20
Price tier	Mid
Context window	500K
Max output	128K
Context tier	500K+
Speed tier	Standard
Latency	medium
Modality	Multimodal (vision)
Model ID	grok-4.6
Provider	xAI
Benchmark	Matches GPT-5.6 Sol on the Artificial Analysis Intelligence Index
Released	Aug 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Reasoning, Streaming, Structured output, Prompt caching, Agentic long-running tasks

Vision, Tool use, Reasoning, Streaming, Structured output, Prompt caching, Agentic long-running tasks

Long-running agents, coding and ambitious interactive/visual work

Trae's built-in model menu may not include Grok 4.6 — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Grok 4.6 is not in the supported model list.
Kiro's spec mode is tuned for Claude models — Grok 4.6 may work but spec-driven flows are best with Claude.
OpenAI Codex (VS Code) is tied to OpenAI's hosted GPT-5 and Codex models — Grok 4.6 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Grok 4.6.
Claude Code only works with Claude models — your LLM is Grok 4.6.
Devin uses Cognition's proprietary model internally — your selected Grok 4.6 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Grok 4.6 will be ignored.
Jules runs Gemini models internally — your selected Grok 4.6 will be ignored.
The Claude Code SDK is tuned for Claude models — Grok 4.6 may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected Grok 4.6 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Grok 4.6 will be ignored.

Build a full stack around Grok 4.6 — Flowpicker shows compatibility warnings before you commit.