# GPT-4o Transcribe (OpenAI) — API pricing and providers

> Speech-to-text. Model id `openai/gpt-4o-transcribe`. Audio model by OpenAI.

- Page: https://infro.io/models/openai/gpt-4o-transcribe
- Vendor: OpenAI (https://infro.io/models/openai)
- Modality: Audio
- Endpoint through INFRO: `POST /v1/audio/speech` at https://api.infro.io/v1
- List rate: $0.36 per audio hour
- Rates checked: 2026-10-05

Rates are OpenAI's published list price: what the customer's own provider account bills, not an INFRO charge. INFRO is a BYOK control plane; it charges a software subscription and adds 0% to model spend.

**Retirement:** OpenAI shuts GPT-4o Transcribe down on 26 Feb 2027. OpenAI recommends GPT-Transcribe. Source: https://developers.openai.com/api/docs/deprecations

## Providers that serve it

| Provider | Model id sent |
| --- | --- |
| OpenAI | `gpt-4o-transcribe` |
| Azure OpenAI | `gpt-4o-transcribe` |
| OpenRouter | `openai/gpt-4o-transcribe` |
| LaoZhang API | `gpt-4o-transcribe` |

## Questions

### How much does the GPT-4o Transcribe API cost?

OpenAI's published list rate for GPT-4o Transcribe is $0.36 per audio hour (checked 2026-10-05). The provider account you connect bills you at the rate on that account, so a negotiated rate replaces the list rate. INFRO adds 0% to model spend.

### Which providers serve GPT-4o Transcribe?

In INFRO's provider registry, GPT-4o Transcribe can be served by OpenAI, Azure OpenAI, OpenRouter and LaoZhang API. You connect your own account with any of them, and INFRO routes and fails over between the ones you connect.

### What is the GPT-4o Transcribe model ID?

Request it from INFRO as "openai/gpt-4o-transcribe". INFRO sends each provider its own id: OpenAI "gpt-4o-transcribe", Azure OpenAI "gpt-4o-transcribe", OpenRouter "openai/gpt-4o-transcribe", LaoZhang API "gpt-4o-transcribe".

### How do I call GPT-4o Transcribe through an OpenAI-compatible API?

Point an OpenAI SDK, or any HTTP client, at https://api.infro.io/v1 with an INFRO gateway key and send model "openai/gpt-4o-transcribe" to POST /v1/audio/speech. INFRO runs the request on a provider account you connected and returns the provider's response with an estimated cost.

### Is GPT-4o Transcribe being retired?

OpenAI shuts GPT-4o Transcribe down on 26 Feb 2027. OpenAI recommends GPT-Transcribe.

### Does INFRO mark up GPT-4o Transcribe usage?

No. OpenAI or the provider you connect bills model usage to your own account. INFRO charges a software subscription for routing, failover, observability, budgets and policy, and takes 0% of model spend.