nousresearch/hermes-4-405bOpen WeightsReasoning model for deliberate analysis, multi-step problem solving, and tool use
Benchmark Pricing$1.00 / 1M in$2.99 / 1M out
Context: 131,072 tokens•Max Output: 117,964 tokens•Knowledge: 2024-08-31•Released: 2025-08-26
TECHNICAL SPECIFICATIONS
Context Window131,072131.1K tokens
Max Output117,964118K tokens
LicenseOpen SourceSelf-hostable
Input Modalities
Text
Function / Tool CallingSupported (MCP Ready)
Structured OutputsGuaranteed Schema
MODEL CONTEXT PROTOCOL (MCP) READINESS
✓ Hermes 4 405B 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 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 4 405B 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-4-405b",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
Cortecshermes-4-405b
$1.00 / $2.99
NanoGPTNousResearch/hermes-4-405b
$0.30 / $1.20$0.15 cache
Kilo Gatewaynousresearch/hermes-4-405b
$1.00 / $3.00
OpenRouternousresearch/hermes-4-405b
$1.00 / $3.00
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
MODEL RESOURCES
More Models by Nousresearch
Alternative and family models from the same lab
Hermes 3 405B Instruct
nousresearch/hermes-3-llama-3.1-405b•Nousresearch
Open Llama instruction model for multilingual chat, reasoning, and coding
16.4K out max
In: $1.38 • Out: $1.38
NousresearchHermes 3 70B Instruct
nousresearch/hermes-3-llama-3.1-70b•Nousresearch
Open Llama instruction model for multilingual chat, reasoning, and coding
16.4K out max
In: $0.41 • Out: $0.41
NousresearchHermes 2 Pro Llama 3 8B
nousresearch/hermes-2-pro-llama-3-8b•Nousresearch
Llama 3 fine-tune optimized for function calling, structured JSON responses, and dialogue
8.2K out max
In: $0.14 • Out: $0.14
Nousresearch