---
id: "openai/gpt-audio"
also: ["openai/gpt-audio"]
card_usd_per_m: "2.5 in, 10.0 out, at openai"
cheapest_list_usd_per_m: "2.5 in, 10.0 out, at openai on openrouter"
cheapest_effective_usd_per_m: "9.7539 in, 45.0962 out, at openai on openrouter"
context: 128000
max_output: 16384
input: ["text", "audio"]
output: ["text", "audio"]
released: "2026-01-19"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 1
---
# OpenAI: GPT Audio

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...