OpenAIChat

OpenAI: GPT-4o Audio

openai/gpt-4o-audio-preview

128KContext Window

16KMax Output

Supported Protocols:seedmax_tokensresponse_formatstructured_outputstemperaturetop_pstopfrequency_penaltypresence_penaltylogit_biaslogprobstop_logprobstoolstool_choice

Normal

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 and $80 per million output audio tokens.

Capabilities

🔧 Function CallingText GenerationCode GenerationAnalysis & ReasoningReasoning

Technical Specs

Input Modality

Audio、Text

Output Modality

Text、Audio

Arch

—

Default Temperature

0.7

Default Top_P

Pricing

Pay per use, no monthly fees

Billing Type	Unit	Price
Text Input	—	$2.5000/M tokens
Text Output	—	$10.0000/M tokens
Image Input	—	< $0.001/张
Audio Input	—	$40.0000/分钟
Audio Output	—	< $0.001/分钟

Quick Start

from openai import OpenAI

client = OpenAI(
    base_url="https://api.uniontoken.ai/v1",
    api_key="YOUR_UNIONTOKEN_API_KEY",
)

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

print(response.choices[0].message.content)