OpenAI · Transcription
Transcription Fast API price
OpenAI’s Transcription Fast through one prepaid, OpenAI-compatible key: $1.25 per 1M audio tokens, the provider’s list price with nothing added per request.
Transcription Fast price
- Price
- $1.25per 1M audio tokens
- about $0.003 a minute
OpenAI’s list price, in US dollars. Tokens.Pay adds a 5% fee (minimum $0.79) when you add credit, never per request.
What Transcription Fast is good at
Upload an audio file, get the transcript back. The cheap tier.
In short: low-cost speech to text.
Transcription model, called at /v1/audio/transcriptions. Listed under speech to text.
Transcription Fast endpoint and id
- Provider
- OpenAI
- Type
- Transcription
- Endpoint
/v1/audio/transcriptions- Model id
gpt-4o-mini-transcribe
What Transcription Fast costs per request
The list price, multiplied out.
| Minutes of audio | Cost |
|---|---|
| 1 | $0.003000 |
| 60 | $0.1800 |
| 600 | $1.80 |
At $1.25 per 1M audio tokens (about $0.003 a minute), OpenAI’s list price.
Transcription Fast cost calculator
Set how much you need. The provider bills per unit; this is the arithmetic.
Call Transcription Fast with the OpenAI SDK
Base URL https://api.airuntime.dev/v1, your key as the bearer token, and model set to gpt-4o-mini-transcribe.
curl
curl https://api.airuntime.dev/v1/audio/transcriptions \
-H "Authorization: Bearer $TOKENS_PAY_KEY" \
-F model="gpt-4o-mini-transcribe" \
-F file="@meeting.mp3"Python
from openai import OpenAI
import os
client = OpenAI(base_url="https://api.airuntime.dev/v1", api_key=os.environ["TOKENS_PAY_KEY"])
with open("meeting.mp3", "rb") as audio:
text = client.audio.transcriptions.create(model="gpt-4o-mini-transcribe", file=audio)
print(text.text)Node
import fs from "node:fs";
import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.airuntime.dev/v1", apiKey: process.env.TOKENS_PAY_KEY });
const text = await client.audio.transcriptions.create({ model: "gpt-4o-mini-transcribe", file: fs.createReadStream("meeting.mp3") });
console.log(text.text);Who processes Transcription Fast requests
Your code calls AI Runtime directly. It forwards the request to the provider and keeps only the bill.
Processing and storage
- Model provider
- OpenAI · data terms
- Gateway
- AI Runtime, AWS us-east-1
Not stored by Tokens.Pay or AI Runtime. Prompts and outputs exist in memory only while the request runs; we keep the billing record. The provider processes the request under its own terms. Zero data retention, exactly
Compare Transcription Fast with similar models
| Model | Provider | Price |
|---|---|---|
| Transcription Fast (this page) | OpenAI | $1.25 per 1M audio tokens |
| Transcription Accurate | OpenAI | $2.50 per 1M audio tokens |
| Fish Transcribe 1 Pro | Fish Audio | $0.006 per minute |
Transcription Fast API questions
How much does the Transcription Fast API cost?
$1.25 per 1M audio tokens, OpenAI’s list price. Tokens.Pay adds nothing per request; a 5% fee (minimum $0.79) applies when you add credit.
What is the model id for Transcription Fast?
Send model "gpt-4o-mini-transcribe" to https://api.airuntime.dev/v1/audio/transcriptions with your Tokens.Pay key as the bearer token. Any OpenAI-compatible SDK works.
Does Tokens.Pay store my Transcription Fast prompts?
No. AI Runtime, the gateway your key calls, keeps prompts and outputs in memory only while the request runs and stores just the billing record. The request is processed by OpenAI, under the provider’s own API data terms.
Add credit, then call Transcription Fast.
From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.
Add credit