Nous Research
Hermes 4 (Thinking)
General-purpose chat model for instruction following, writing, and analysis
Model facts
- Context window
- 128K tokens
- Maximum output
- 8K tokens
- Cheapest paid input
- $0.201 per 1M tokens
- Cheapest paid output
- $0.4 per 1M tokens
- Open weights
- yes
- Providers
- 1
Capabilities and modalities
open weights, text.
Observed price history
- 2026-08-24: $0.201 input / $0.4 output per 1M tokens
API providers
- NanoGPT — model id NousResearch/Hermes-4-70B:thinking; $0.201 input / $0.4 output per 1M tokens; provider documentation