Grok 4.5

LLM Provider / Model · Coding and agentic work on the previous xAI flagship

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
Knowledge cutoff	Feb 2026
Modality	Multimodal (vision)
Model ID	grok-4.5
Provider	xAI
Benchmark	Previous xAI flagship, superseded by Grok 4.6
Released	Jul 2026
Hosting	Closed/API
Capabilities	Vision, Tool use, Reasoning, Streaming, Structured output, Prompt caching

Vision, Tool use, Reasoning, Streaming, Structured output, Prompt caching

Coding and agentic work on the previous xAI flagship

Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but Grok 4.5 is not in the supported model list.
Kiro's spec mode is tuned for Claude models — Grok 4.5 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 4.5 is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is Grok 4.5.
Claude Code only works with Claude models — your LLM is Grok 4.5.
Devin uses Cognition's proprietary model internally — your selected Grok 4.5 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Grok 4.5 will be ignored.
Jules runs Gemini models internally — your selected Grok 4.5 will be ignored.
The Claude Code SDK is tuned for Claude models — Grok 4.5 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 4.5 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Grok 4.5 will be ignored.

Build a full stack around Grok 4.5 — Flowpicker shows compatibility warnings before you commit.