The Orchestrator › Models › OpenAI
OpenAI: GPT-4o Transcribe
GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.
Specifications
| Provider | OpenAI |
| Model ID | openai/gpt-4o-transcribe |
| Context window | — |
| Modalities | audio → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2024-03-13 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | openai/gpt-4o-transcribe | $2.50 | $10.00 | — |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.50 | $10.00 | — |
Capabilities
Audio inputNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
—