Model Discovery
Learn how to find and filter models in the Alvin Model Hub.
The Model Hub makes it easy to find the right AI model for your use case. With hundreds of models from eleven providers, effective discovery tools are essential.
Search
Basic Search
Type in the search bar to find models:
- By name: "gpt-4", "claude", "llama"
- By provider: "openai", "anthropic"
- By capability: "vision", "embeddings"
Search Tips
- Use partial names: "gpt" finds all GPT models
- Search is case-insensitive
- Multiple terms narrow results
Filters
By Provider
Filter to show models from specific providers:
- OpenAI
- Anthropic
- Meta
- Cohere
- Perplexity
- xAI
- ElevenLabs
- Ollama (self-hosted)
By Capability
Filter by what the model can do:
| Capability | Description |
|---|---|
| Chat | Conversational responses |
| Code | Programming and code generation |
| Vision | Image understanding and analysis |
| Embeddings | Text vectorization for search/RAG |
| Audio | Speech-to-text, text-to-speech |
| Multimodal | Multiple input/output types |
By Context Window
Filter by maximum context size:
- 4K tokens: Basic conversations
- 8K tokens: Short documents
- 32K tokens: Long documents
- 128K+ tokens: Very long context
By Price
Filter by relative cost band, from the cheapest high-volume models through to the frontier tier. Exact rates are shown on each model card.
Sorting
Sort the model list by:
| Sort Option | Description |
|---|---|
| Popular | Most used models |
| Newest | Recently added |
| Name | Alphabetical |
| Price (Low) | Cheapest first |
| Price (High) | Most expensive first |
| Context Size | Largest context first |
Model Cards
Each model card shows at a glance:
┌─────────────────────────────────┐
│ Provider Logo │
│ Model Name │
│ ─────────────────────────────── │
│ Capabilities: 💬 👁️ 💻 │
│ Context: 128K tokens │
│ Price: $0.005 / 1K tokens │
│ [Try] [More] │
└─────────────────────────────────┘
Finding the Right Model
Filter to the capability you need — chat, code, vision, embeddings, image, video or audio — then narrow by context size and cost band. Each model card carries its rate, context window and capability flags, and you can compare candidates side by side.
Which model is strongest for a given task changes as providers ship, so the Model Hub reflects the current catalog rather than a fixed recommendation. If you'd rather not track that, Alvin routing picks per request across the whole catalog.
Saved Filters
Save frequently used filter combinations:
- Apply your filters
- Click Save Filter
- Name your filter
- Access from the Saved dropdown
Related
- Model Hub Overview - Hub introduction
- Providers - Provider details
- Comparison - Compare models