OpenAI: GPT-4o Transcribe

GPT-4o Transcribe is OpenAI's speech-to-text model built on GPT-4o audio capabilities, released 2026-04. It provides high-quality transcription with token-based pricing.

Modalities
inAudiooutText
Price / 1M−70%
$0.75 / $3.00$2.50 / $10.00
Context
128K
Knowledge cutoff

Capabilities

Structured output

Channels

Same weights on every channel. Requests route to the cheapest healthy one; the channel used is printed on each billing line.

Provider
Discount
Input /M
Output /M
Cache Read /M
Cache Create 5m /M
Cache Create 1h /M
Codexcheap
−70%
$0.75
$3.00
Defaultstable
−30%
$1.75
$7.00

Quick Start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="openai/gpt-4o-transcribe",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire GPT-4o Transcribe into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free