OpenAI: GPT-4o Transcribe

openai/gpt-4o-transcribe

128KContext Window

4KMax Output

Normal

GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.

Capabilities

Audio GenerationSpeech Recognition

Technical Specs

Input Modality

Text

Output Modality

Text

Arch

—

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

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-transcribe",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

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