# STT Async V4 API Pricing

As of October 10, 2026, STT Async V4 costs $0 per minute of audio on Soniox. It has an 8,000-token context window and returns up to 8,000 tokens per response.

- Page: https://models.litellm.ai/models/stt-async-v4
- LiteLLM model name: `soniox/stt-async-v4`
- Context window: 8,000 tokens
- Max output: 8,000 tokens
- Added to LiteLLM: June 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 |
|---|---|---|---|---|---|---|---|
| Soniox | `soniox/stt-async-v4` | – | – | – | – | $0.00002778 | 8K |

## Cost examples

Transcribing 1,000 minutes of audio:

- Soniox: $0

## Features

Supported: Audio input.

## Use it with LiteLLM

```python
from litellm import transcription

response = transcription(
    model="soniox/stt-async-v4",
    file=open("audio.mp3", "rb"),
)
```

## FAQ

### How much does STT Async V4 cost?

STT Async V4 costs $0 per minute of audio on Soniox.

### What is the context window of STT Async V4?

STT Async V4 has an 8,000-token context window and returns up to 8,000 tokens per response.

### Which providers offer STT Async V4?

STT Async V4 is available from Soniox through LiteLLM, using the model name soniox/stt-async-v4.

### How do I call STT Async V4 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="soniox/stt-async-v4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/audio/transcriptions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does STT Async V4 support?

STT Async V4 supports audio input.

### When did LiteLLM add STT Async V4?

STT Async V4 was added to LiteLLM's model price file in June 2026.

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