Grok Voice 2.0

Deprecated

xai/grok-voice-2.0

xAI real-time voice model supporting text and audio input and output over WebSocket.

Compare

Context window: -
Input: Audio · Text
Output: Audio · Text
Released: 2026-07-29

Capabilities: Reasoning, Tool call

Pricing

Audio input

$4.80

USD / 1 audio hour

USD 0.08 per minute or 4.80 per hour. server_vad bills session duration including silence; push-to-talk bills only audio sent and received.

Request

$0.004

USD / 1 request

Per billable text input message: one conversation.item.create event; function_call_output items and audio-content items excluded; response.create not billed as a text input.

Performance

No evaluation results available.

Providers

No providers found

ModelRegistry · Catalog updated 2026-10-14