gpt-4o-mini-tts Cost Calculator - OpenAI

Calculate the cost of using gpt-4o-mini-tts from OpenAI for your AI applications

gpt-4o-mini-tts Cost Calculator

Mode: Audio speech

Input Tokens

Output Tokens

Audio Duration (seconds)

Cost Breakdown

Input Cost$0.002500

Output Cost$0.010000

Audio Cost$0.015000

Total Cost$0.027500

Pricing Details

Input: $0.00000250 per token

Output: $0.00001000 per token

Output Video/Audio: $0.00025000 per second

[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

Book a Demo

or, Get started here

About gpt-4o-mini-tts

gpt-4o-mini-tts is a powerful audio speech AI model offered by OpenAI. This comprehensive guide provides detailed pricing information, technical specifications, and capabilities to help you understand the costs and features of using gpt-4o-mini-tts in your applications.

Pricing Information

Input Cost$2.50 per 1M tokens

Output Cost$10.00 per 1M tokens

Audio/Video Output Cost$0.0003 per second

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

When should you use gpt-4o-mini-tts?

gpt-4o-mini-tts is best suited for the following scenarios:

Text-to-speech (TTS) voice assistants and narration
IVR systems and customer support voice responses
Generating spoken audio from short scripts or prompts

When should you avoid gpt-4o-mini-tts?

General-purpose chatbots or long-form text generation
Document RAG pipelines (use an embedding or chat model instead)
Complex reasoning or tool-heavy agent workflows

How does gpt-4o-mini-tts compare to similar models?

This is a specialized text-to-speech model. When comparing similar options, focus on voice quality, latency, supported languages/voices, and how pricing is split between prompt tokens and audio duration (seconds). It is typically a better fit for voice UX than general chat models.

Understanding gpt-4o-mini-tts pricing

gpt-4o-mini-tts is a text-to-speech (TTS) model provided by OpenAI.
Input tokens are priced at $2.50 per 1M tokens.
Output tokens are priced at $10.00 per 1M tokens.
Audio/video output is priced at $0.0003 per second.
For this model, input tokens are less expensive than output tokens, so optimizing your prompts can help manage costs.
Because this is an audio-focused model, your total cost can be driven by output duration (seconds) in addition to any token-based costs.
OpenAI offers gpt-4o-mini-tts for text-to-speech (TTS) workloads — voice assistants, narration, and audio response generation.

How to Use This Calculator

Step 1: Enter the number of input tokens you expect to use. Input tokens include your prompt, system messages, and any context you provide to the model.

Step 2: Specify the number of output tokens you anticipate. Output tokens are the text generated by the model in response to your input.

Step 3: Review the cost breakdown to see the total estimated cost for your usage. The calculator automatically updates as you adjust the token counts.

← Back to All Models View All OpenAI Models