Llama Guard#
Providers / Google Vertex AI / Llama Guard
📋 Overview#
- ID:
llama-guard@llama-guard-4-12b - Provider: Google Vertex AI
- Authors: Meta
- Open Weights: false
- Context Window: 128k tokens
- Max Output: 4k tokens
🔬 Technical Specifications#
Sampling Controls: 
🎯 Capabilities#
Feature Overview#
Input/Output Modalities#
| Direction | Text | Image | Audio | Video | |
|---|---|---|---|---|---|
| Input | ✅ | ❌ | ❌ | ❌ | ❌ |
| Output | ✅ | ❌ | ❌ | ❌ | ❌ |
Core Features#
| Tool Calling | Tool Definitions | Tool Choice | Web Search | File Attachments |
|---|---|---|---|---|
| ✅ | ✅ | ❌ | ❌ | ❌ |
Response Delivery#
| Streaming | Structured Output | JSON Mode | Function Call | Text Format |
|---|---|---|---|---|
| ✅ | ❌ | ❌ | ✅ | ✅ |
Advanced Reasoning#
| Basic Reasoning | Reasoning Effort | Reasoning Tokens | Include Reasoning | Verbosity Control |
|---|---|---|---|---|
| ✅ | ❌ | ❌ | ❌ | ❌ |
🎛️ Generation Controls#
Sampling & Decoding#
| Temperature | Top-P |
|---|---|
| 0.0-2.0 | 0.0-1.0 |
Length & Termination#
| Max Tokens |
|---|
| 1-4k |
💰 Pricing#
Pricing shown for Google Vertex AI
Contact provider for pricing information.
📋 Metadata#
Created: 0001-01-01 00:00:00 UTC
Last Updated: 2025-10-19 18:13:08 UTC
Navigation#
Last Updated: 2025-10-21 23:55:56 UTC | Generated by ModelWiki