Grok 1 Voice Think Fast is xAI's language model. A real-time voice LLM supporting bidirectional audio and text streaming via WebSocket, designed for voice assistants, phone agents, and interactive voice applications.
Specifications
Canonical IDxai-grok-1-voice-think-fast
TypeLanguage
StatusActive
CreatorxAIxAI
Input ModalitiesText
Output ModalitiesText
Release Date · 3 months ago

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
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·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Grok 4.5500K$2.00$6.00Available
Grok 4.31.0M$1.25$2.50Available
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$2.50Available
Grok 4.20 Reasoning2.0M$1.25$2.50Available
Grok 4.1 Reasoning2.0M$0.200$0.500Deprecated
Grok 4.1 Fast2.0M$0.200$0.500Deprecated
Grok 4.1 Fast Non-Reasoning2.0M$0.200$0.500Deprecated
Grok 1 Voice Think FastCurrent

Model IDs

xai-grok-1-voice-think-fast
xai/grok-voice-think-fast-1.0