---
id: "nousresearch/hermes-4-70b"
also: ["nousresearch/hermes-4-70b", "NousResearch/Hermes-4-70B", "requesty/nousresearch/hermes-4-70b"]
cheapest_list_usd_per_m: "0.13 in, 0.4 out, at nebius/fp8 on openrouter"
cheapest_effective_usd_per_m: "0.1298 in, 0.3981 out, at nebius/fp8 on openrouter"
context: 131072
max_output: 117964
input: ["text"]
output: ["text"]
released: "2025-08-26"
params: ["frequency_penalty", "include_reasoning", "max_tokens", "presence_penalty", "reasoning", "repetition_penalty", "response_format", "temperature", "tools", "top_k", "top_p"]
endpoints: 2
gateways: "openrouter (1), requesty (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Nous: Hermes 4 70B

Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...