GPT TranscribePricing
$0.017 per minute (same as OpenAI's official rate, no markup), charged by the audio duration transcribed in real time. Usage is settled to the second, rounded up to the next whole second.
Input Modalities
- Text
Output Modalities
- Text
Providers
Performance for gpt-transcribe
Uptime is the percentage of requests that succeeded over the past 72 hours. AIHubMix continuously monitors every provider and automatically retries with the next-best provider when one returns an error or responds too slowly; Latency is total round-trip time (lower is better); Throughput is how fast the model writes (tokens per second, higher is better).
Frequently asked questions
More models from OpenAI
See all OpenAI models →- Input: $ 2 /M
- Output: $ 10 /M
- Web Search: $0.01/request
GPT-6.1 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows. GPT-6.1 Sol's performance in complex programming, computer operations, and professional work tasks is close to Astra, but at a lower cost. You can compare the two on your own tasks to weigh quality against cost.
- Input: $ 0.1 /M
- Output: $ 0.5 /M
- Web Search: $0.01/request
GPT-6 Luna is OpenAI's latest and most efficient model, designed for focused, high-throughput tasks.
- Input: $ 2 /M
- Output: $ 10 /M
- Web Search: $0.01/request
GPT-6 Sol is OpenAI's latest model in the GPT-6 series, specifically designed for complex programming and agent workflows.
- Input: $ 10 /M
- Output: $ 50 /M
- Web Search: $0.01/request
GPT-6 Astra is OpenAI's newest and most intelligent model, with industry-leading performance in computer operations, web browsing, software engineering, scientific research, and professional work. It excels at executing multi-step workflows across code, browsers, and various professional software. Astra can achieve better results with significantly fewer output tokens, making its estimated API cost per task lower.
OpenAI's latest realtime speech-to-text model, built for low-latency use — it streams incremental transcripts as audio arrives, ideal for live captions, dictation, and voice interfaces. Supports automatic transcription across 57 languages, with keyword/context hints and a tunable latency-vs-accuracy tradeoff.
GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool use and configurable reasoning effort, improving on GPT-Realtime-2 in alphanumeric recognition, silence and noise handling, and interruption behavior.
