---
id: "nousresearch/hermes-4-405b"
also: ["nousresearch/hermes-4-405b", "NousResearch/Hermes-4-405B", "requesty/nousresearch/hermes-4-405b"]
cheapest_list_usd_per_m: "1.0 in, 3.0 out, at nebius/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.4139 in, 3.0 out, at nebius/fp8 on openrouter"
context: 131072
max_output: 117964
input: ["text"]
output: ["text"]
released: "2025-08-26"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["frequency_penalty", "include_reasoning", "logit_bias", "logprobs", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "seed", "stop", "structured_outputs", "temperature", "tools", "top_k", "top_logprobs", "top_p"]
endpoints: 2
gateways: "openrouter (1), requesty (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Nous: Hermes 4 405B

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberate internally with...