Nous: Hermes 4 405B
NOUSRESEARCH Developer Architecture Profile
Intelligence (ELO)1485Chatbot Arena Verified
Max Context Limit131,072Max Out: 117,964 tokens
Prompt CachingStandardNo Cache Discount
Standard API / 1M$4.00🧠 Deep Reasoner
Model Capabilities & Contract SLAs
- Reasoning
- Coding & Logic
- Fictional
- 🧠 Extended Test-Time Reasoning
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...
Granular Pricing Matrix
Input Tokens (Standard Prompt)$1.00 / 1M
Output Tokens (Completion)$3.00 / 1M
Pricing data via OpenRouter. Sync: 10/2/2026
Evaluate Competitors
VS Engine MatchupNous: Hermes 4 405B vs OpenAI: GPT-5.6 Terra (batch)VS Engine MatchupNous: Hermes 4 405B vs Anthropic: Claude Opus 4.7VS Engine MatchupNous: Hermes 4 405B vs OpenAI: GPT-5.4 NanoVS Engine MatchupNous: Hermes 4 405B vs OpenAI: o3 (batch)VS Engine MatchupNous: Hermes 4 405B vs Anthropic: Claude Opus 4.8VS Engine MatchupNous: Hermes 4 405B vs Google: Nano Banana Pro (Gemini 3 Pro Image Preview)