Models/OpenAI/GPT Audio

GPT Audio

Name: GPT Audio API access
Brand: OpenAI

OpenAI · Proprietary · Released Jan 19, 2026 · openai/gpt-audio

Compare Estimate cost

128K contextToolsStructured outputAudio input

Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
OpenAI1ST PARTY	$2.50	$10.00	—	128K	—	✕	✕	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 44 hours ago

About

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

Specifications

Context window128,000

Max output16,384

Modalities intext, audio

Modalities outtext, audio

LicenseProprietary

ReleasedJan 19, 2026

TokenizerGPT

Deprecation2027-01-20

GPT-5.6 Luna Pro$0.10 / $0.60 GPT-5.6 Luna$0.10 / $0.60 GPT-5.6 Terra Pro$1.00 / $6.00 GPT-5.6 Terra$1.00 / $6.00

Embed badge

[![GPT Audio](https://modelindex.ai/badge/openai/gpt-audio)](https://modelindex.ai/models/openai/gpt-audio)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

LiteLLM dataset4 minutes ago

AGGREGATOR

ModelIndex benchmarks44 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.