GPT-4o Audio

OpenAI chataudiottstool_use

API ID: openai/gpt-4o-audio-preview

Input Price
$2.50
/1M tokens
Output Price
$10.00
/1M tokens

About GPT-4o Audio

The gpt-4o-audio-preview model adds support for audio inputs as prompts. This enhancement allows the model to detect nuances within audio recordings and add depth to generated user experiences. Audio outputs are currently not supported. Audio tokens are priced at $40 per million input audio tokens.

๐Ÿ’ฐ
Price Ranking
#1139 lowest price among 1240 Chat models

Model Specifications

Context Length
128k
Max Output
16k
Release Date
2025-08-15
Capabilities
chat audio tts tool_use
Input Modalities
audiotext
Output Modalities
textaudio

Best For

  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)

๐Ÿ’ฐ Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$4.13
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$127.50
/month
1000 tickets/day, ~800 tokens each

OpenAI Model Lineup

Compare all models from OpenAI to find the best fit

Model Input Output Context Capabilities
GPT-4o Audio Current Free Free 128k chat audio tts tool_use
GPT-3.5 Turbo 16k (older v1106) Free Free 16k chat
GPT-3.5 Turbo 16k (older v1106) Free Free 16k chat
GPT-4 32k Free Free 33k chat
GPT-4 32k Free Free 33k chat
GPT-4 32k (older v0314) Free Free 33k chat

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Other Inflection 3 Pi
Input: $2.50
Output: $10.00
Context: 8k
Other Inflection 3 Productivity
Input: $2.50
Output: $10.00
Context: 8k
Cohere Command A
Input: $2.50
Output: $10.00
Context: 256k
Cohere Command R+ (08-2024)
Input: $2.50
Output: $10.00
Context: 128k

๐Ÿš€ Quick Start

Get started with GPT-4o Audio API

OpenAI Python SDK
from openai import OpenAI
client = OpenAI()

response = client.chat.completions.create(
    model="openai/gpt-4o-audio-preview",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)