Hermes 3 70B Instruct

Nousresearch

nousresearch/hermes-3-llama-3.1-70bOpen Weights

Open Llama instruction model for multilingual chat, reasoning, and coding

Benchmark Pricing$0.41 / 1M in$0.41 / 1M out$0.20 cache read

Context: 131,072 tokens•Max Output: 16,384 tokens•Knowledge: 2023-12-31•Released: 2024-08-18

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output16,38416.4K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingNot Supported

Structured OutputsPrompt Based

MODEL CONTEXT PROTOCOL (MCP) READINESS

⚠ Hermes 3 70B Instruct does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Hermes 3 70B Instruct 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-3-llama-3.1-70b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

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