Grok 4 Fast is xAI's language model with a 131K context window and up to 30K output tokens, available from 2 providers, starting at $0.2 / 1M input and $0.5 / 1M output. A cost-efficient multimodal LLM from xAI with a 2M token context window, available in both reasoning and non-reasoning flavors.
Specifications
Canonical IDxai-grok-4-fast
TypeLanguage
StatusDeprecated
CreatorxAIxAI
Providers
Context Window131K tokens
Max Output30K tokens
Input ModalitiesImageText
Output ModalitiesText
Reasoning Effortsdefault
Release Date · 1 year ago
Knowledge Cutoff · 1 year ago
Deprecation Date
Benchmarks
Intelligence Index
#298
Math Index
#179
MMLU-Pro
#205
GPQA
#338
HLE
#440
LiveCodeBench
#189
IFBench
#289
Time to First Token
#334
SciCode
#299
AIME 2025
#179
LCR
#342
TerminalBench Hard
#207
TAU2
#170
Output TPS
#564

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Azure AI Foundry logo
Azure AI Foundry
xai:grok4fast
$0.2$0.5
Oracle Cloud (OCI) logo
Oracle Cloud (OCI)
oci/xai.grok-4-fast
$5.00$25.00

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Grok 4.7524K$2.00$6.00Available
Grok 4.6524K$2.00$6.00Available
Grok 4.5500K$2.00$6.00Available
Grok 4.31.0M$1.25$2.50Available
Grok 4.3 Batch1.0M$1.00$2.00Available
Grok 4.202.0M$1.25$2.50Available
Grok 4.20 Multi-Agent2.0M$1.25$2.50Available
Grok 4.20 Multi-Agent Beta2.0M$1.25$2.50Available
Grok 4.20 Non-Reasoning2.0M$1.25$2.50Deprecating
Grok 4.20 Multi-Agent2.0M$1.00$2.00Available
Grok 4 Fast131K$0.200$0.500Current

Model IDs

grok-4-fast
oci/xai.grok-4-fast
x-ai/grok-4-fast
xai-grok-4-fast