Prior-generation Grok 3 model, now legacy. A general-purpose multimodal model with a 131K-token context window and text+image input, retained in the xAI API at low legacy pricing for cost-sensitive and compatibility use cases.
profile normalized against the 47-model field
Context window· 131K of 1.05M12%
Max output· 8K of 272K3%
Output speed· 70 tok/s22%
Affordability—
Capability breadth· 6 of 1155%
Capability switches · 6 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
131K
Max output
8K
Performance
Output speed
70 tok/s tok/s
Capabilities
Input modalities
Text, image
Output modalities
Text
Reasoning mode
No
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-3
General
Release date
February 17, 2025
Benchmarks
Sourced evaluation scores, each verified against its primary source.