GPT-4o mini Transcribe
Summary
GPT-4o mini Transcribe is a proprietary language model from OpenAI, released on 20 Mar 2025. It accepts audio and generates text, with a 16K-token context window and up to 2K output tokens per response. As of 21 Oct 2026, the lowest listed API price is $1.25 per million input tokens and $5 per million output tokens (Vercel AI Gateway), across 1 provider we track.
Speech-to-text model powered by GPT-4o Mini for fast, accurate transcription
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 20 Mar 2025 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Context window | 16K (16,000 tokens) [models.dev] |
| Max output | 2K tokens [models.dev] |
| Knowledge cutoff | 1 Jun 2024 [models.dev] |
| Input | Audio [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
GPT-4o mini Transcribe API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Vercel AI Gateway openai/gpt-4o-mini-transcribe | $1.25 | $5 | – | 16K | models.dev, 21 Oct 2026 |
Frequently asked questions
What is the context window of GPT-4o mini Transcribe?
GPT-4o mini Transcribe has a context window of 16,000 tokens (16K) and can generate up to 2,000 tokens in a single response, according to models.dev.
How much does the GPT-4o mini Transcribe API cost?
GPT-4o mini Transcribe is listed from $1.25 per million input tokens and $5 per million output tokens (Vercel AI Gateway). Prices last verified 21 Oct 2026.
Is GPT-4o mini Transcribe open source?
No. GPT-4o mini Transcribe is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.
When was GPT-4o mini Transcribe released?
OpenAI released GPT-4o mini Transcribe on 20 Mar 2025, according to models.dev.
Change history
- Max output changed from 16K to 2K
- Added to the directory
- Now listed on Vercel AI Gateway