modelgrep
O

OpenAI: GPT Audio

openai/gpt-audio

ToolsJSONAudio
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
44
193rd fastest
Latency
547ms
first token
Input price
$2.50
253rd cheapest
Context
128K
16K max out

How it compares

Faster than37%
of all ranked models
Cheaper than15%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
OpenAI$2.50$10.00

Specifications

Context window128K
Max output16K
Knowledge cutoff
Input modalitiestext, audio
Output modalitiestext, audio
Prompt caching
Cache read price
ModeratedYes

GPT Audio FAQ

How much does GPT Audio cost?

GPT Audio costs $2.50 per million input tokens and $10.00 per million output tokens via OpenRouter, making it 253rd cheapest of 298 paid models.

How fast is GPT Audio?

GPT Audio generates around 44 tokens per second with 547ms time-to-first-token (p50), the 193rd fastest tracked model.

What is GPT Audio's context window?

GPT Audio supports a 128K-token context window and can output up to 16K tokens. It accepts text, audio input.

Compare head-to-head