GPT-4o Transcribe

GA

Speech-to-text. Input audio+text, output text. ~$0.006/min. Token prices shown are text-token equivalents; audio input billed differently. Still listed as current on models index.

GPT-4o Transcribe by OpenAI costs $2.50 per 1M input tokens and $10 per 1M output tokens ($4.38/1M blended), with a 16K (16.000-token) context window. It is generally available (GA), with a knowledge cutoff of 1 Jun 2024.

Last verified: 13 Aug 2026 · sourced from official provider documentation

Provider
OpenAI
Status
GA
Input price
$2.50 / 1M tokens
Output price
$10 / 1M tokens
Cached input
Blended price
$4.38 / 1M tokens
Context window
16.000 tokens (16K)
Max output
2000 tokens
Modality
audio, text
Open weights
No — API only
Knowledge cutoff
2024-06-01
Released
API string
gpt-4o-transcribe

Source: OpenAI official documentation ↗

FAQ

GPT-4o Transcribe — questions & answers

How much does GPT-4o Transcribe cost?

GPT-4o Transcribe is priced at $2.50 per 1M input tokens and $10 per 1M output tokens ($4.38/1M blended at a 3:1 input-to-output ratio).

What is the context window of GPT-4o Transcribe?

GPT-4o Transcribe has a 16.000-token context window (16K), with up to 2000 output tokens per request.

Is GPT-4o Transcribe deprecated?

No — GPT-4o Transcribe is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does GPT-4o Transcribe support image or vision input?

Our catalog lists GPT-4o Transcribe's modalities as audio, text; image/vision input is not among them.

Can I self-host GPT-4o Transcribe?

No — GPT-4o Transcribe is proprietary. Its weights are not publicly released, so it is available only through OpenAI's API (or hosted partners), not for self-hosting.

What is the API model string for GPT-4o Transcribe?

The API model identifier for GPT-4o Transcribe is "gpt-4o-transcribe" when calling OpenAI's API.

What is GPT-4o Transcribe's knowledge cutoff?

GPT-4o Transcribe's training knowledge cutoff is 1 Jun 2024.