Nous Research
Hermes 4 405B
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.
Model facts
- Context window
- 131K tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $0.996 per 1M tokens
- Cheapest paid output
- $2.99 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Observed price history
- 2026-08-24: $0.996 input / $2.99 output per 1M tokens
API providers
- Cortecs — model id hermes-4-405b; $0.996 input / $2.99 output per 1M tokens; provider documentation
- Nebius Token Factory — model id NousResearch/Hermes-4-405B; $1 input / $3 output per 1M tokens; provider documentation
- OpenRouter — model id nousresearch/hermes-4-405b; $1 input / $3 output per 1M tokens; provider documentation