Nous Research
Hermes 4 Large (Thinking)
Flagship model for demanding analysis, coding, and production agent workflows
Model facts
- Context window
- 128K tokens
- Maximum output
- 8K tokens
- Cheapest paid input
- $0.3 per 1M tokens
- Cheapest paid output
- $1.2 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
structured output, open weights, text.
Observed price history
- 2026-08-24: $0.3 input / $1.2 output per 1M tokens
API providers
- NanoGPT — model id NousResearch/hermes-4-405b:thinking; $0.3 input / $1.2 output per 1M tokens; provider documentation