Grok 5

LLM Provider / Model · Real-time web/X context, long-context analysis, and agentic browsing

At a glance

Input price	$5
Output price	$25
Cache price	$0.50
Price tier	Premium
Context window	1M+
Max output	64K
Context tier	500K+
Speed tier	Medium
Latency	medium
Knowledge cutoff	Dec 2025
Modality	Multimodal (vision)
Model ID	grok-5
Provider	xAI
HumanEval	94%
MMLU	89%
SWE-Bench	72%
Benchmark	GPQA, AIME, ARC-AGI competitive
Released	Jan 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Web search, Streaming, Function calling, Real-time X data

Vision, Tool use, Web search, Streaming, Function calling, Real-time X data

Real-time web/X context, long-context analysis, and agentic browsing

Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Grok 5 is not in the supported model list.
Kiro's spec mode is tuned for Claude models — Grok 5 may work but spec-driven flows are best with Claude.
OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Grok 5 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Grok 5.
Claude Code only works with Claude models — your LLM is Grok 5.
Devin uses Cognition's proprietary model internally — your selected Grok 5 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Grok 5 will be ignored.
Jules runs Gemini models internally — your selected Grok 5 will be ignored.
The Claude Code SDK is tuned for Claude models — Grok 5 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 5 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Grok 5 will be ignored.

Build a full stack around Grok 5 — Flowpicker shows compatibility warnings before you commit.