AI TOOLS RADAR
Explorar
Todos los modelos / NOUSRESEARCH
nousresearch logo
nousresearch

Nous: Hermes 3 70B Instruct

Hermes 3 is a generalist language model with many improvements over [Hermes 2](/models/nousresearch/nous-hermes-2-mistral-7b-dpo), including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board. $0.70 per million input tokens, $0.70 per million output tokens. 131,072 token context window, maximum output of 16,384 tokens. Includes independent benchmarks from Artificial Analysis.

Ver fuente en OpenRouter Hugging Face
Resumen

Especificaciones del modelo

Contexto
131.072 tokens
Salida máxima
16.384 tokens
Arquitectura
text->text
Tokenizador
Llama3
Corte de conocimiento
2023-12-31
Moderado
No
OPENROUTER

Precios completos

Tarifas sincronizadas desde OpenRouter, por millón de tokens.

Entrada
$0.7
/M tokens
Salida
$0.7
/M tokens
API

Inicio rápido

Usa este modelo mediante la API compatible con OpenAI de OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"nousresearch/hermes-3-llama-3.1-70b","messages":[{"role":"user","content":"Hello!"}]}'
Capacidades y modalidades

Entrada → Salida

Entrada
text
Salida
text
API

Parámetros API compatibles

frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetop_ktop_p
Proveedores disponibles

1 Proveedor

Proveedores en vivo en OpenRouter

Disponibilidad, latencia, rendimiento y enrutamiento cambian continuamente. Consulta la fuente para datos actuales.

OpenRouter

DeepInfra

fp8
Contexto
131K
Salida máxima
16K
Entrada
$0.700
Salida
$0.700
Lectura de caché
No indicado
Escritura de caché
No indicado
nousresearch

modelos

Todos los modelos
nousresearch logonousresearch

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...

Contexto
131K
Entrada
text
Salida
text
Entrada: $0.130Salida: $0.400por millón de tokens
Ver detalles del modelo →
nousresearch logonousresearch

Nous: 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...

Contexto
131K
Entrada
text
Salida
text
Entrada: $1.00Salida: $3.00por millón de tokens
Ver detalles del modelo →
nousresearch logonousresearch

Nous: Hermes 3 405B Instruct

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Contexto
131K
Entrada
text
Salida
text
Entrada: $1.00Salida: $1.00por millón de tokens
Ver detalles del modelo →