The Index / Cortecs / Hermes 4 405B Hermes 4 405B by Cortecs · family hermes · listed Aug 2025T W
Hermes 4 405B is a frontier hybrid-mode reasoning model built on Llama 3.1, optimized for advanced logic, math, coding, and structured output generation.
Current rates USD per 1M tokens Input $0.996
Output $2.99
Cache read —
Cache write —
Against the market Input price vs. maker flagships ($/1M tokens) DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017: $0.15 per 1M tokens $0.15 Qwen3.8 Omni Flash Qwen3.8 Omni Flash: $0.15 per 1M tokens $0.15 DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017: $0.30 per 1M tokens $0.30 Hermes 4 405B Hermes 4 405B: $0.996 per 1M tokens $0.996 Grok 4.7 Grok 4.7: $2.00 per 1M tokens $2.00 Gemini 4 Neon Gemini 4 Neon: $3.00 per 1M tokens $3.00 Claude Fable 5.2 Claude Fable 5.2: $8.00 per 1M tokens $8.00 GPT-6.2 Astra GPT-6.2 Astra: $8.00 per 1M tokens $8.00 Output price vs. maker flagships ($/1M tokens) Qwen3.8 Omni Flash Qwen3.8 Omni Flash: $0.47 per 1M tokens $0.47 DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017: $0.60 per 1M tokens $0.60 DeepSeek V4.1 Flash 1017 DeepSeek V4.1 Flash 1017: $1.20 per 1M tokens $1.20 Hermes 4 405B Hermes 4 405B: $2.99 per 1M tokens $2.99 Grok 4.7 Grok 4.7: $6.00 per 1M tokens $6.00 Gemini 4 Neon Gemini 4 Neon: $15.00 per 1M tokens $15.00 Claude Fable 5.2 Claude Fable 5.2: $40.00 per 1M tokens $40.00 GPT-6.2 Astra GPT-6.2 Astra: $40.00 per 1M tokens $40.00 On the record
Model id hermes-4-405b
Context window 128K tokens
Max output 128K tokens
Input modalities text
Output modalities text
Reasoning no
Tool calls yes
Open weights yes
Knowledge cutoff Aug 2024
Released 2025-08-26
Last updated 2025-08-26 ← All Cortecs listings