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 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.

ChatNous Research131k tokens$1.0901 / $3.2702 · 1M

nousresearch/hermes-4-405b

Context
131k tokens
Completion cap
—
Tools
No
JSON
Yes
Released
2025-08-26

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nousresearch/hermes-4-405b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is 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 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. Hermes 4 405B runs on the Geek Hub API (OpenAI-compatible). Model id: nousresearch/hermes-4-405b.
Is Hermes 4 405B free?
No. Input is $1.0901 per 1M tokens and output is $3.2702 per 1M tokens on Geek Hub (markup included).
What is the context length of Hermes 4 405B?
Hermes 4 405B has a 131k tokens context window.
Does Hermes 4 405B support tool calling and structured outputs?
Hermes 4 405B does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Hermes 4 405B released?
Hermes 4 405B was released on 2025-08-26.

More models from Nous Research