OpenAI: GPT Audio

openai/gpt-audio · OpenAINot yet established

Declared family: GPT
Evidence confidence: Unknown
Declared tokenizer tag: GPT
Entered catalogue: 19 January 2026
Last tested: Not yet measured
Measurement: Awaiting measurement

Evidence stack

Signals of different kinds, weighed together

Signal	Result	Reference
Tokenizer signature	Not measured	–
API surface	No other entry shares this exact contract	api_01186cbc
Context and output	128,000 context · 16,384 max output	declared
Reasoning contract	None declared	declared
Serving providers observed	None recorded yet	–

Declared record

What the catalogue claims about this model

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...

Modalities: text+audio->text+audio
Declared tokenizer: GPT
Prompt price: $2.50 / M tokens
Completion price: $10.0 / M tokens

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_logprobstop_p

defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}

Catalogue entry

History

Every observation, kept as taken

19 January 2026Enters the OpenRouter catalogue declared as GPT.

Cite this page as the evidence record for OpenAI: GPT Audio: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.