Nous: Hermes 4 70B
NOUSRESEARCH Developer Architecture Profile
Intelligence (ELO)1449Chatbot Arena Verified
Max Context131,072Tokens
API Cost / 1M$0.53Blended Prompt + Completion
Model Capabilities
- Coding & Logic
- Fictional
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...
Granular Pricing Matrix
Input Tokens (Prompt)$0.13 / 1M
Output Tokens (Completion)$0.40 / 1M
Pricing data via OpenRouter. Sync: 6/14/2026
Evaluate Competitors
VS Engine MatchupNous: Hermes 4 70B vs xAI: Grok 4.20 Multi-AgentVS Engine MatchupNous: Hermes 4 70B vs Meta: Llama 3.1 70B InstructVS Engine MatchupNous: Hermes 4 70B vs Anthropic Claude Sonnet LatestVS Engine MatchupNous: Hermes 4 70B vs Qwen: Qwen3.5-9BVS Engine MatchupNous: Hermes 4 70B vs Qwen: Qwen3.5 397B A17BVS Engine MatchupNous: Hermes 4 70B vs Google: Gemini 2.5 Pro