Grok 4.5

by xAI

Grok 4.5 is xAI's July 2026 frontier release, aimed more squarely at software engineering and multi-step agentic work than the original Grok 4. Trained on data spanning coding, science, engineering, and mathematics, it offers a 500K token context window and reasoning that can be switched on or off per request, and xAI introduced it as its smartest model yet for coding, agentic tasks, and knowledge work. Its strengths center on sustained coding sessions and tool-driven execution, with function calling, structured outputs, and vision input rounding out the agentic toolkit. It fits code assistants, autonomous engineering workflows, and research agents that alternate between careful reasoning and fast tool calls within one long-running context.

Key info

Input
Output
Features
Context window
500K
Max output
—

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Intelligence Index38.8
Coding Index72.4
Reasoning & knowledge
GPQA Diamond
93%
Humanity's Last Exam
43%
Long-context reasoning
79%
Coding
SciCode
55%

Available routes

No routes currently available — Grok 4.5 isn't routed through the Opper gateway right now. It may return.

Contact us about this model →

Available models from xAI

Start building with 700+ models

One API key for every major provider, up and running in minutes.

Get startedView Documentation