🚀 OpenAI GPT-4.1 Models, Reasoning (o1/o3/o4) & Vision Integration
What's New:
- Added OpenAI's latest GPT-4.1 series: 4.1, 4.1 mini, and 4.1 nano models
- Integrated all OpenAI reasoning models: o1, o3, o4 series (including o1 Pro)
- Image URL support for vision-enabled models in both prompts and workflows
- Enhanced token tracking: cache tokens, reasoning tokens, and audio tokens
- Dynamic and static image URL input options with variable support
- Automatic caching for inputs over 1,000 tokens (OpenAI feature)
Benefits:
- Access to OpenAI's most advanced reasoning capabilities for complex problem-solving
- Faster, more cost-effective options with 4.1 mini and nano variants
- Combine visual analysis with text prompts in a single request
- Real-time cost visibility with detailed token breakdown including reasoning costs
- Flexible image processing for website analysis, object identification, and branding insights
- Seamless integration across existing prompt and workflow infrastructure
- Build multimodal AI solutions that process both text and visual content efficiently