Nous: Hermes 4 405B

Fiabilité 20%

nousresearch/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...

🧠 Intelligence & Données
Knowledge Cutoff: 2024-08-31
Tokenizer: Other
Moderation: ✅ Non
📅 Cycle de vie
Ajouté le: 26/08/2025
Spécifications
  • Provider & Modalité nousresearch text->text
  • Fenêtre de contexte 131,072 tokens
  • Max Output Tokens 0
  • Support des Outils (Tools) Non supporté
🔍 Modèles similaires
Modèle Provider Input Output Contexte
Inception: Mercury 2
inception/mercury-2
inception $0.2500 $0.7500 128,000
OpenAI: GPT-5.3 Chat
openai/gpt-5.3-chat
openai $1.7500 $14.0000 128,000
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/gemini-3.1-flash-i...
google $0.5000 $3.0000 65,536
AionLabs: Aion-2.0
aion-labs/aion-2.0
aion-labs $0.8000 $1.6000 131,072
MiniMax: MiniMax M2.5 (free)
minimax/minimax-m2.5:free
minimax $0.0000 $0.0000 196,608