Nous Research
Hermes 4 70B
Hermes 4 70B is a hybrid reasoning model from Nous Research, built on Meta-Llama-3.1-70B. It introduces the same hybrid mode as the larger 405B release, allowing the model to either...
Model facts
- Context window
- 131K tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $0.129 per 1M tokens
- Cheapest paid output
- $0.399 per 1M tokens
- Open weights
- yes
- Providers
- 2
Capabilities and modalities
reasoning, tool calling, structured output, temperature control, open weights, text.
Local hardware estimate
At 4K context: Q4_K_M 44.2 GiB, Q8_0 77.0 GiB, F16 138.6 GiB working memory.
- Parameters
- 70.6 billion
- Architecture
- llama
- Model license
- llama3
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Observed price history
- 2026-08-24: $0.129 input / $0.399 output per 1M tokens
API providers
- Cortecs — model id hermes-4-70b; $0.129 input / $0.399 output per 1M tokens; provider documentation
- OpenRouter — model id nousresearch/hermes-4-70b; $0.13 input / $0.4 output per 1M tokens; provider documentation