# GPT Realtime Translate API Pricing

GPT Realtime Translate is available through LiteLLM. It has a 16,000-token context window and returns up to 2,000 tokens per response.

- Page: https://models.litellm.ai/models/gpt-realtime-translate
- Lab: OpenAI
- Context window: 16,000 tokens
- Max output: 2,000 tokens
- Added to LiteLLM: August 10, 2026
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| OpenAI | `gpt-realtime-translate` | – | – | – | – | – | 16K |
| Azure OpenAI | `azure/gpt-realtime-translate` | – | – | – | – | – | 32K |

## Features

Supported: Audio input, Audio output.

## FAQ

### What is the context window of GPT Realtime Translate?

GPT Realtime Translate has a 16,000-token context window and returns up to 2,000 tokens per response.

### Which providers offer GPT Realtime Translate?

GPT Realtime Translate is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.

### What features does GPT Realtime Translate support?

GPT Realtime Translate supports audio input and audio output.

### When did LiteLLM add GPT Realtime Translate?

GPT Realtime Translate was added to LiteLLM's model price file on August 10, 2026.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json