Changelog / updated
AI Model Selector — Multi-Provider Support
Live Preview — ai-model-selector-01
GPT-4
State-of-the-art LLM from OpenAI, versatile in chat and coding tasks.
ChatCodeReasoning
The Problem
Most AI applications now support multiple providers — OpenAI, Anthropic, Google, Mistral, and more. Our original model selector only displayed a flat list of model names, which became unwieldy as the number of available models grew.
What’s New
Grouped Provider Sections
Models are now organized by provider in the dropdown:
- OpenAI — GPT-4o, GPT-4o Mini, o1, o3-mini
- Anthropic — Claude 3.5 Sonnet, Claude 3.5 Haiku
- Google — Gemini 2.0 Flash, Gemini 1.5 Pro
- Open Source — Llama 3.1 70B, Mixtral 8x7B
Provider Icons
Each section header now displays the provider’s logo, making it visually scannable at a glance.
Keyboard Navigation
You can now type to filter models in real-time. The dropdown uses Shadcn’s Command component under the hood, so it supports fuzzy matching out of the box.
Performance Metadata
Each model option now shows:
- Context window size (e.g. 128K tokens)
- Relative speed indicator (fast / moderate / slow)
- Pricing tier badge