OpenAI: GPT-4 Turbo
Detailed specifications for implementing OpenAI: GPT-4 Turbo in your RAG applications.
Model Overview
Released:April 9, 2024
Introducing the advanced GPT-4 Turbo model, now enhanced with cutting-edge vision capabilities. This powerful update allows vision-based requests to leverage JSON mode and function calling, delivering greater flexibility and precision. Trained on data up to December 2023, GPT-4 Turbo combines the latest advancements in AI with unparalleled performance, making it an indispensable tool for innovative applications.
Architecture
- Modality
- text+image->text
- Tokenizer
- GPT
Pricing
| Operation | Rate |
|---|---|
| Prompt | 0.00001 |
| Completion | 0.00003 |
| Image | 0.01445 |
| Request | 0 |
Provider Details
- Context Length
- 128,000 tokens
- Max Completion
- 4,096 tokens
- Moderation
- Enabled
Ready to implement OpenAI: GPT-4 Turbo?
Start building powerful RAG applications with our flexible pricing plans and developer-friendly API.