Hermes 2 Pro Llama 3 8B

NousresearchMCP Tool Call

nousresearch/hermes-2-pro-llama-3-8bOpen Weights

Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue

Benchmark Pricing$0.14 / 1M in$0.14 / 1M out

Context: 8,192 tokens•Max Output: 8,192 tokens•Released: 2024-04-30

TECHNICAL SPECIFICATIONS

Context Window8,1928.2K tokens

Max Output8,1928.2K tokens

LicenseLlama 3 Community LicenseSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Hermes 2 Pro Llama 3 8B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 8,192 tokens, this model can handle compact tool sets. Consider keeping MCP server tool manifests minimal to preserve headroom.

API CALL INVOCATION EXAMPLE

// Example: Calling Hermes 2 Pro Llama 3 8B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NOUSRESEARCH_API_KEY,
});

const response = await client.chat.completions.create({
  model: "nousresearch/hermes-2-pro-llama-3-8b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);