Hub/Models/openai/gpt-audio
openaitext + audio → text + audio

OpenAI: GPT Audio

Canonical ID: openai/gpt-audio

Compare ModelOpen on OpenRouter →

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...

Artificial Analysis Benchmarks

Verified
No standardized Artificial Analysis benchmark scores recorded for this variant yet.

Token Pricing & Economics

Prompt Input (1M Tokens)
$2.50
Input
Completion Output (1M Tokens)
$10.00
Output
Prompt KV-Cache Read (1M Tokens)
$0.00
Cached
Context Window Capacity
125k tokens
Context

Supported Parameters & Features

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p