The original Grok 4 model that launched the Grok 4 generation, now legacy. A multimodal reasoning model with a 256K-token context window and text+image input, kept available in the xAI API for backward compatibility.
profile normalized against the 47-model field
Context window· 256K of 1.05M24%
Max output· 16K of 272K6%
Output speed· 75 tok/s23%
Affordability—
Capability breadth· 7 of 1164%
Capability switches · 7 of 11
Reasoning mode
Tool / function use
Streaming
JSON mode
Structured outputs
Prompt caching
Fine-tuning
Web search
Code execution
Vision input
Audio input
Specifications
Every value carries a primary source and a verification date.
Capacity
Context window
256K
Max output
16K
Performance
Output speed
75 tok/s tok/s
Capabilities
Input modalities
Text, image
Output modalities
Text
Reasoning mode
Yes
Tool / function use
Yes
Streaming
Yes
JSON mode
Yes
Structured outputs
Yes
Web search
Yes
Vision input
Yes (image input)
API
API model ID
grok-4
General
Release date
July 9, 2025
Benchmarks
Sourced evaluation scores, each verified against its primary source.