GPT-Realtime-2.1 mini
by OpenAI
Today's price · per 1M tokens
Input
$0.600
per 1M tokens
Output
$2.40
per 1M tokens
Blended
$1.05
blended $/1M — 3:1 weighted input:output
Cached input
$0.060
10% of input — prompt caching
How this price is scoped: OpenAI prices this model per 1M tokens on three separate modalities: text at $0.60 input / $0.06 cached input / $2.40 output, audio at $10.00 / $0.30 / $20.00, and image input at $0.80 / $0.08. The tracked figures are the TEXT rates, matching how the other realtime rows are tracked.
Price receipt
We read OpenAI's own pricing page on Aug 17, 2026 and found gpt-realtime-2.1-mini listed with a price on the same row — that read is where the number above comes from, recorded as a new model. We keep the page text we read; its content hash is fb730533d2.
Overview
Distilled, lower-cost realtime voice model for WebRTC, WebSocket and SIP voice agents, and OpenAI's named replacement for GPT-Realtime mini. Text tokens $0.60/$2.40 per 1M; audio tokens $10/$20 per 1M.
Capabilities
struck through = not supportedSpecifications
- Provider
- OpenAI
- Context window
- 128K tokens
- Modality
- audio, text, image
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Jul 6, 2026
- Status
- Current
- Last updated
- Aug 17, 2026
- Tags
Availability verified: Aug 17, 2026 — listed on OpenAI's own page