# Whisper Large v3

> Whisper Large v3 is an open-weight language model from OpenAI, released on 1 Sept 2023. It accepts audio and generates text, with a 448-token context window and up to 4K output tokens per response.

Source page: https://www.aimodel.directory/models/whisper-large-v3
Last verified: 4 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 1 Sept 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Weights:** Open weights (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Context window:** 448 (448 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Knowledge cutoff:** Sept 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Input:** Audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)
- **Tool calling:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/nvidia/models/openai/whisper-large-v3.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| NVIDIA NIM | Free | Free | – | – |
| Groq | – | – | – | – |

## FAQ

### What is the context window of Whisper Large v3?

Whisper Large v3 has a context window of 448 tokens (448) and can generate up to 4,096 tokens in a single response, according to models.dev.

### Is Whisper Large v3 open source?

Whisper Large v3 is an open-weight model. Check the license terms before commercial use.

### When was Whisper Large v3 released?

OpenAI released Whisper Large v3 on 1 Sept 2023, according to models.dev.

### Which providers offer Whisper Large v3?

We track Whisper Large v3 on 2 providers: NVIDIA NIM, Groq.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Whisper Large v3", https://www.aimodel.directory/models/whisper-large-v3