Meterary
Start free

xAI

Grok Voice (Realtime) API Pricing

Priced per minute, not per token: $0.05/min ($3.00/hr). Realtime text input billed separately at $0.004 per message.

Verified against xAI’s pricing page on 2026-07-02.

View source ↗

Facts

Specs

  • FamilyGrok Voice
  • API ID—
  • ModalityAudio
  • Context window—
  • Max output—
  • Release dateNot published

Pricing (per 1M tokens)

  • Input—
  • Output—
  • Cached input—
  • Cache write—
  • Batch discount—

Capabilities

realtime, speech-to-speech

Notes

Priced per minute, not per token: $0.05/min ($3.00/hr). Realtime text input billed separately at $0.004 per message.

Worked cost examples

Not priced per token

Grok Voice (Realtime)is billed per unit (image, second, or similar), not per token — the standard chatbot/RAG/batch workloads don’t apply. See the notes in the facts panel above for its per-unit rate.

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

Grok Voice (Realtime) pricing FAQ

How is Grok Voice (Realtime) priced?
Grok Voice (Realtime) is billed per unit rather than per token. Priced per minute, not per token: $0.05/min ($3.00/hr). Realtime text input billed separately at $0.004 per message.
Does Grok Voice (Realtime) have cache pricing?
No cache discount is documented for Grok Voice (Realtime) on the provider's pricing page.

Keep exploring

Estimate my usage