GPT-4o
OpenAIยทopenai/gpt-4o
Omni-modal flagship model accepting any combination of text, audio, image, and video inputs with native real-time multimodal processing.
Closed APIClosedTool CallingStructured OutputsNatural Language ProcessingArtificial Intelligence
Context
128,000
Output Limit
16,384
Linked Papers
88
Citations
3.4K
Release Date
May 13, 2024
Model Specifications
- Lab / Vendor
- OpenAI
- Model Family
- OpenAI
- Modality
- text, image, audio, video, pdf
- Architecture
- End-to-End Multimodal Transformer
- Parameters
- Dense MoE 200B+
- Context Window
- 128,000
- Max Output
- 16,384
- Input / Output Price
- $2.5 / $10 per 1M
- License
- Commercial
Research & Evaluation Papers
Academic evaluations, empirical benchmarks, and publications for GPT-4o.
Sort