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

Contexto
131k tokens
Máx. completion
—
Tools
No
JSON
Sí
Lanzamiento
2025-08-26

Llámalo desde Geek Hub

El mismo SDK de OpenAI. Cambia el base URL y el id del modelo.

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"}]
  }'
Consigue tu API key

Preguntas frecuentes

¿Qué es 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 corre en el API de Geek Hub (compatible con OpenAI). Id: nousresearch/hermes-4-405b.
¿Hermes 4 405B es gratis?
No. El input cuesta $1.0901 / 1M tokens y el output $3.2702 / 1M tokens en Geek Hub (markup incluido).
¿Cuál es el contexto de Hermes 4 405B?
Hermes 4 405B tiene una ventana de 131k tokens.
¿Hermes 4 405B soporta tool calling y structured outputs?
Hermes 4 405B no publica tool calling en este endpoint. También soporta structured outputs con un JSON schema en response_format.
¿Cuándo se lanzó Hermes 4 405B?
Hermes 4 405B se lanzó el 26 de agosto de 2025.

Más modelos de Nous Research