GPT-4o Transcribe
Advanced speech recognition model based on GPT-4o, supporting audio token pricing.
- Audio input
- $6.60per 1M tokens
- Context
- 128K
- 30-day uptime
- —
- Released
- 2025-03-14
Speech to textInputAudioOutputText
This model is being retired
Requests stop working on 2027-02-26.
Switch to openai/gpt-transcribeProviders
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
Included providers1
- SuccessTTFT
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
- Input
- $2.75
- per 1M tokens
- Output
- $11.00
- per 1M tokens
- Audio input
- $6.60
- per 1M tokens
Estimated cost of common use (500 output tokens each)
- One chat message
- $0.0138
- 3K input tokens
- Agent first turn
- $0.281
- 100K tokens of context, none cached
- Each later agent turn
- $0.286
- same context plus 2K new tokens
- 20-turn agent task
- $5.71
- first turn plus 19 more
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.