GPT-4o Transcribe

Advanced speech recognition model based on GPT-4o, supporting audio token pricing.

Input price: $2.25list $2.50-10%
Output price: $9.00list $10.00-10%
Context: 128K
Max output: —
Modalities: InputAudioOutputText
Capability: —
30-day uptime: —
Released: 2025-03-14
Knowledge cutoff: —

Speech to text

Providers

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].

DedicatedInput$2.25-10%Output$9.00-10%Cache read—Context128KThis model is served by a dedicated set of providers. We pick the provider for each request, and you pay the same price whichever one serves it.

Included providers1

SuccessTTFT
OpenAIUnited States——

Pricing

Prices for this model. Each request is billed at these prices, whichever provider serves it.

Input: $2.25list $2.50-10%; per 1M tokens
Output: $9.00list $10.00-10%; per 1M tokens
Audio input: $5.40list $6.00-10%; per 1M tokens

Similar models

Other models with the same output types at a similar price.

GPT-4o TranscribeThis model

Capability: —
Input: $2.25
Output: $9.00

GPT-4o Mini Transcribe

Capability: —
Input: $1.125
Output: $4.50