gpt-audio-2025-08-28 (gpt-audio-2025-08-28) is a speech model from openai with a 128K-token context window; capabilities tools; input audio, text; output audio, text.
128KContext
16.4KMax output
$2.5$ / 1M in
Pricing
Input
$2.5 / 1M tokens
Output
$10 / 1M tokens
Currency
USD
Note
Indicative US list price — verify with the vendor.
Indicative US list price — a reference only, verify with the vendor. Source: litellm. Last verified 2026-07-22.