Skip to main content
Docs
Model Hub

Model Hub

Discover, compare, and test 2,000+ AI models from 9 major providers in the Elyxir Model Hub.

The Model Hub is your central directory for discovering and comparing AI models from major providers. Browse 2,000+ models from OpenAI, Anthropic, Google, Meta, and more.

Overview

The Model Hub provides:

  • Model Discovery: Search and filter by capability, provider, and type
  • Model Details: View specifications, pricing, and capabilities
  • Comparison: Side-by-side model comparisons
  • Quick Access: One-click access to test models in chat

Accessing the Model Hub

  1. Sign in to studio.elyxir.ai
  2. Click Model Hub in the main navigation
  3. Browse or search for models

Model Categories

Models are organized by capability:

CategoryDescriptionExamples
ChatConversational AIGPT-4o, Claude 3.5
CodeProgramming assistanceCodex, CodeLlama
VisionImage understandingGPT-4V, Claude 3
EmbeddingsText vectorizationtext-embedding-3, Cohere Embed
AudioSpeech and audioWhisper, ElevenLabs

Model Information

Each model card displays:

  • Provider: OpenAI, Anthropic, Google, etc.
  • Capabilities: Chat, code, vision, etc.
  • Context Window: Maximum input/output tokens
  • Pricing: Cost per 1K tokens (input/output)
  • Speed: Latency characteristics

Model Details Page

Click any model to view detailed information:

  • Full specification
  • Pricing breakdown
  • Use case recommendations
  • Example prompts
  • Performance benchmarks

Search and Filters

Use the search bar to find models by:

  • Model name (e.g., "GPT-4", "Claude")
  • Provider (e.g., "OpenAI", "Anthropic")
  • Capability (e.g., "vision", "code")

Filters

Filter models by:

FilterOptions
ProviderOpenAI, Anthropic, Google, Meta, etc.
CapabilityChat, Code, Vision, Embeddings, Audio
Context Size4K, 8K, 32K, 128K, etc.
Pricing TierFree, Standard, Premium

Testing Models

Test any model directly from the Model Hub:

  1. Click on a model card
  2. Click Try in Chat
  3. Start a conversation with the selected model

OpenAI

  • GPT-4o: Latest multimodal model, fast and capable
  • GPT-4o-mini: Cost-effective for simpler tasks
  • GPT-4: High reasoning capability
  • text-embedding-3-large: Best-in-class embeddings

Anthropic

  • Claude 3.5 Sonnet: Excellent for coding and analysis
  • Claude 3 Opus: Highest capability model
  • Claude 3 Haiku: Fast and affordable

Google

  • Gemini Pro: Balanced performance
  • Gemini Flash: Fast and cost-effective

Meta

  • Llama 3.2: Latest open-weight model
  • Llama 3.1 405B: Largest open model
Model Hub | elyxir