Add DeepSeek Instant/Expert/Vision modes + modelType + image support in /v1

Add Meta AI fast (think_fast) and thinking (think_hard) modes + model variants

Add fast/thinking mode variants for all Qwen models + meta module

Update Exocore Gateway

Add GPT and Grok via Puter driver + V1 routes and HTML docs

Add V1 API section with all model examples

Add Claude tab/section to HTML docs

Update Gemini API to support new AI models and improve functionality

Upload 20 files