OpenAI: GPT-4o Transcribe

GPT-4o Transcribe is OpenAI's high-quality speech-to-text model built on GPT-4o audio capabilities. It's priced per token (input and output), making it suitable for workflows that benefit from token-level billing transparency.

• Context window: 128,000 tokens
• Input: audio
• Output: transcription
• Pricing: $2.5/M input tokens, $10/M output tokens

View on OpenRouter. Model data sourced from OpenRouter.