Hermes 4 405B

About 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 <think>...</think> traces or respond directly, offering flexibility between speed and depth. 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) The model is instruction-tuned with an expanded post-training corpus (~60B tokens) emphasizing reasoning traces, improving performance in math, code, STEM, and logical reasoning, while retaining broad assistant utility. It also supports structured outputs, including JSON mode, schema adherence, function calling, and tool use. Hermes 4 is trained for steerability, lower refusal rates, and alignment toward neutral, user-directed behavior.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Nous Research Model Lineup

Compare all models from Nous Research to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Relace Search

Relace

Input: $1.00

Output: $3.00

Context: 256k

Nova Pro 1.0

Amazon

Input: $0.80

Output: $3.20

Context: 300k

MiMo-V2.5-Pro

Xiaomi

Input: $1.00

Output: $3.00

Context: 1.1M

Qwen VL Max

Alibaba Qwen

Input: $0.80

Output: $3.20

Context: 131k

💡 Cheaper Alternatives

Same Brand (Nous Research)

Cross Brand

🚀 Quick Start

Get started with Hermes 4 405B API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="nousresearch/hermes-4-405b",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision