GPU/Deploy AI Models/Hermes 3
Function Calling

Hermes 3 405B

Llama 3.1 405B Fine-tuned

The ultimate model for AI agents and tool use. Fine-tuned Llama 3.1 405B with best-in-class function calling accuracy, 128K context, and optimization for complex agentic workflows.

Model Specifications

Parameters405 Billion
ArchitectureLlama 3.1
Context Length128K tokens
Base ModelMeta Llama 3.1 405B
Fine-tuningHermes Dataset
LicenseLlama License

Built-in Tool Support

Example tools that Hermes 3 can use out of the box.

web_search

Search the web for information

code_interpreter

Execute Python code

database_query

Query SQL databases

api_call

Make HTTP requests to APIs

Why Choose Hermes 3

Function Calling

Best-in-class function calling accuracy for tool use.

405B Parameters

Largest open model for maximum capability.

128K Context

Industry-leading context for complex agent tasks.

Agentic Optimized

Fine-tuned specifically for agentic workflows.

Pricing Options

Serverless API

Pay per token with auto-scaling

₹100 input /1M tokens
₹200 output /1M tokens
  • Auto-scaling
  • No minimum
  • 99.9% uptime
  • Rate limits apply
Recommended

Dedicated Instance

Reserved GPU for consistent performance

₹600/hour
  • 8x H100 GPUs
  • No rate limits
  • Fine-tuning support
  • Private deployment

Use Cases

AI Agents

Build autonomous agents with reliable function calling.

Tool Integration

Connect AI to external APIs and databases.

Complex Workflows

Orchestrate multi-step automated processes.

Code Execution

Generate and execute code with tool use.

Ready to Deploy Hermes 3?

Build powerful AI agents with the best function calling model.