Hermes 4 70B

Nebius • hermes-4-70b

Model Information

Slug	hermes-4-70b
LLM.txt	View
Release Date	August 26, 2025

Organization

Name	Nebius

Model Description

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 respond directly or generate explicit <think>...</think> reasoning traces before answering. Users can control the reasoning behaviour with the `reasoning` `enabled` boolean. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#enable-reasoning-with-default-config)

This 70B variant is trained with the expanded post-training corpus (~60B tokens) emphasizing verified reasoning data, leading to improvements in mathematics, coding, STEM, logic, and structured outputs while maintaining general assistant performance. It supports JSON mode, schema adherence, function calling, and tool use, and is designed for greater steerability with reduced refusal rates.

Available at 10 Providers

Provider	Type	Model Name	Original Model	Input ($/1M)	Output ($/1M)	Actions
WaveSpeed AI	Chat Code	hermes-4-70b	`nousresearch/hermes-4-70b`	$0.12	$0.42	Visit
OpenRouter	Chat Code	Hermes 4 70B	`nousresearch/hermes-4-70b`	$0.13	$0.40	Model
Nebius Token Factory		Hermes-4-70B	`NousResearch/Hermes-4-70B`	$0.13	$0.40	Model
Kilo Code	Code	Nous: Hermes 4 70B	`nousresearch/hermes-4-70b`	$0.13	$0.40	Visit
Nano-GPT		Hermes 4 (Thinking)	`NousResearch/Hermes-4-70B:thinking`	-	-	Visit
Nano-GPT		Hermes 4 Medium	`nousresearch/hermes-4-70b`	-	-	Visit
Yupp	Chat	Hermes 4 70B (OpenRouter)	`nousresearch/hermes-4-70b`	-	-	Visit
LangDB		hermes-4-70b	`hermes-4-70b`	-	-	Model
Airforce API		hermes-4-70b	`hermes-4-70b`	-	-	Visit
Writingmate	Chat Code	Nous: Hermes 4 70B	`nousresearch/hermes-4-70b`	-	-	Model

Back to Models View Organization