Whisper Large v3
Summary
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.
Speech transcription model for accurate audio-to-text and captioning workflows
Last verified 4 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | OpenAI |
|---|---|
| Release date | 1 Sept 2023 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [models.dev] |
| Context window | 448 (448 tokens) [models.dev] |
| Max output | 4K tokens [models.dev] |
| Knowledge cutoff | Sept 2023 [models.dev] |
| Input | Audio [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
Whisper Large v3 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| NVIDIA NIM openai/whisper-large-v3 | Free | Free | – | – | models.dev, 4 Oct 2026 |
| Groq whisper-large-v3 | – | – | – | – | models.dev, 4 Oct 2026 |
Frequently asked questions
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.
Change history
No changes detected since we started tracking this model. We re-check every source daily.