Grok 4 Fast Non Reasoning Pricing & Specs | AI Models

Grok 4 Fast Non Reasoning is a text model from xAI with a context window of 2.0M tokens and max output of 2.0M tokens. Pricing starts at 0.20 per million input tokens and 0.50 per million output tokens.

Capabilities

✗ Vision✓ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✓ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output

Specifications

Model Key	`xai/grok-4-fast-non-reasoning`
Provider	xAI
Provider ID	xai
Mode	Text
Canonical Name	grok-4-fast
Context Window	2.0M tokens
Max Output	2.0M tokens

Pricing

Type	Per 1K Tokens	Per 1M Tokens
Input Tokens	0.000200	0.200
Output Tokens	0.000500	0.500
Cache Read (Input)	0.000050	0.050

Benchmarks

Intelligence Index	23.1#77
Coding Index	19.0#79
Math Index	41.3#58
MMLU-Pro	0.7#95
GPQA	0.6#98
HLE	0.1#105
LiveCodeBench	0.4#77
IFBench	0.4#95
Time to First Token	0.29s#82
SciCode	0.3#87
AIME 2025	0.4#58
LCR	0.2#105
TerminalBench Hard	0.1#70
TAU2	0.6#45

All Variants

All available versions, regions, and API endpoints for Grok 4 Fast Non Reasoning.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
xai/grok-4-fast-non-reasoning	xAI	Text	0.200	0.500	2.0M	2.0M	no	yes
xai/grok-4-fast-reasoning	xAI	Text	0.200	0.500	2.0M	2.0M	no	yes

← Back to All Models