GPT-4o Transcribe
OpenAI's current transcription model and the practical replacement for the older Whisper endpoint, which remains available at the same price but is no longer the recommended path. Priced at twice the mini variant, which is worth it on difficult audio and wasted on clean recordings.
Pricing checked against provider documentation on . How we verify
gpt-4o-transcribe Price
$0.006
/ audio min
Context
—
not token-based
Max output
—
varies
Pricing caveat: Legacy whisper-1 costs the same. Live transcript streaming through the realtime endpoint is far pricier at roughly $0.017/min. Uploads are capped at 25 MB.
Where GPT-4o Transcribe fits
- Noisy or accented audio
- Technical and domain vocabulary
- Transcripts used without human review
- Existing OpenAI-based pipelines
Specifications
- API model ID
- gpt-4o-transcribe
- Provider
- OpenAI
- Model family
- GPT-4o Transcribe
- Released
- March 2025
- Knowledge cutoff
- —
- Context window
- —
- Max output
- —
- Native reasoning
- No
- Relative latency
- medium
- Input modalities
- audio
- Output modalities
- text
- Open weights
- No
- Cached input
- —
- Batch discount
- —
Frequently asked
How much does GPT-4o Transcribe cost?
GPT-4o Transcribe is billed at $0.006 / audio min.
What is GPT-4o Transcribe's context window?
Context limits for GPT-4o Transcribe depend on the input format rather than a token count.
Is GPT-4o Transcribe a reasoning model?
No. GPT-4o Transcribe answers directly without a native thinking phase, which keeps latency and cost predictable.
What is GPT-4o Transcribe best for?
Higher-accuracy managed transcription. OpenAI's current transcription model and the practical replacement for the older Whisper endpoint, which remains available at the same price but is no longer the recommended path. Priced at twice the mini variant, which is worth it on difficult audio and wasted on clean recordings.