Models

Browse and explore available AI models.

Running Models Only

The Models page (titled "Running Models" in the UI) displays only models that have active deployments. If a model is not currently deployed, it will not appear in the list. Contact your platform administrator to request deployment of additional models.

Model Catalog

The Models page displays all models accessible to your tenant. The catalog offers a grid view (default) and a list view — use the toggle to switch between them.

Field	Description
Model	Model identifier
Type	Chat, Completion, Embedding
Context	Maximum context window
Pricing	Input and output cost per 1M tokens

Model Details

Click any model to view:

Overview

• Model ID: Full identifier for API calls
• Description: Model capabilities and use cases
• Family: Model family (e.g., Llama, Mistral)

Specifications

Spec	Description
Context Length	Maximum input + output tokens
Input Pricing	Cost per 1M input tokens
Output Pricing	Cost per 1M output tokens
Capabilities	Chat, completion, function calling, etc.

Status

Only deployed models are listed — every model you see on this page is available for inference. If a model is missing from the list, it is not currently deployed.

note

Contact your platform administrator to request deployment of additional models.

Model Types

Chat Models

Designed for conversational interactions:

• Accept message arrays
• Support system prompts
• Maintain conversation context

Examples: Llama-3.1, Mistral, Qwen

Completion Models

Text completion without conversation structure:

• Accept text prompts
• Generate continuations
• No message roles

Embedding Models

Generate vector representations:

• Convert text to vectors
• Used for semantic search
• Fixed dimension output

Examples: BGE, E5

Using Models

In API

Use the model ID directly:

response = client.chat.completions.create(
    model="meta-llama/Llama-3.1-8B-Instruct",  # Model ID
    messages=[...]
)

In Playground

1. Open Playground
2. Select model from dropdown
3. Start chatting

Model Selection Guide

Use Case	Recommended
General chat	Llama-3.1-8B-Instruct
Complex reasoning	Llama-3.1-70B-Instruct
Code generation	Code Llama models
Semantic search	BGE-large
Cost optimization	Smaller models (8B)

Pricing

Each model has its own per-token rate, displayed in USD per 1M tokens for both input and output. Output tokens are typically priced higher than input tokens.

View exact pricing in the model detail page.

Requesting Models

Need a model that's not listed?

1. Confirm it doesn't appear in the Running Models list
2. Contact your platform administrator
3. Request deployment

Factors affecting availability:

• GPU resource requirements
• License restrictions
• Platform configuration