GPT Audio

The gpt-audio model is our first generally available audio model. It accepts audio inputs and outputs, and can be used in the Chat Completions REST API.

Input price
$2.25list $2.50-10%
Output price
$9.00list $10.00-10%
Context
128K
Max output
16K
Modalities
InputTextAudioOutputTextAudio
—
—
Released
2025-10-07
Knowledge cutoff
—
Try in ChatCompare

Providers

This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].

Included providers1
  • SuccessTTFT
  • OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

Input
$2.25list $2.50-10%
per 1M tokens
Output
$9.00list $10.00-10%
per 1M tokens
Cache read
$0.225list $0.25-10%
per 1M tokens
Audio input
$28.80list $32.00-10%
per 1M tokens
Audio output
$57.60list $64.00-10%
per 1M tokens

Make a request

Set your provider preferences, then copy the request. It reads your API key from OHMYGPT_API_KEY.

Provider preferences don’t apply to this model. Need a custom setup? Contact [email protected].

curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer $OHMYGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-audio",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Similar models

Other models with the same output types at a similar price.

  • Better value: more capable, lower price
  • Pareto frontier
  • Similar models

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

GPT AudioThis model
—
Input
$2.25
Output
$9.00
GPT-5.4
157
Input
$2.25–$4.50
Output
$13.50–$20.25
Claude Sonnet 5.5
167
Input
$2.20
Output
$11.00
DeepSeek R1 Distill Llama 70B
—
Input
$2.20
Output
$2.20
Pixtral Large 25.02
—
Input
$2.20
Output
$6.60