GPT-4 Vision is a multimodal, vision-language AI model developed by OpenAI, part of the GPT family. It was released on 2023-09-25. Its tracked lifecycle status is active. It supports a context window of 128,000 tokens.
Specifications
- 組織
- OpenAI
- Model family
- GPT
- Generation
- 4
- 状態
- active
- Released
- 2023-09-25
- Model type
- Multimodal, Vision-Language
- Input modalities
- text, image
- Output modalities
- text
- Context window
- 128,000 tokens
- ライセンス
- Proprietary
- 重み
- closed weights
- 公式 API
- Yes
- 自己ホスト可能
- いいえ
- Last verified
- 2026-08-01
機能
- Tool use
- Function calling
- Structured output
Related models in the GPT family
Interactive filtering and search on this page need JavaScript; every fact above is part of the page itself.