---
id: "nousresearch/hermes-3-llama-3.1-405b"
also: ["nousresearch/hermes-3-llama-3.1-405b", "NousResearch/Hermes-3-Llama-3.1-405B"]
cheapest_list_usd_per_m: "1.0 in, 1.0 out, at deepinfra/fp8 on openrouter"
cheapest_effective_usd_per_m: "1.0 in, 1.0 out, at deepinfra/fp8 on openrouter"
context: 131072
max_output: 16384
input: ["text"]
output: ["text"]
released: "2024-08-16"
params: ["frequency_penalty", "logit_bias", "max_tokens", "min_p", "presence_penalty", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "top_k", "top_p"]
endpoints: 1
gateways: "openrouter (1)"
no_training: 1
trains: 0
retains_prompts: 0
intelligence: 7.4000
---
# Nous: Hermes 3 405B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...