nousresearch/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...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Nebiusfp8 | $0.130 | $0.400 | 131K | 100% |
Hermes 4 70B costs $0.130 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 71st cheapest of 298 paid models.
Hermes 4 70B scores 16.0 on the Artificial Analysis Intelligence Index, ranking 138th of 179 benchmarked models, with a GPQA Diamond score of 70%.
Hermes 4 70B generates around 67 tokens per second with 252ms time-to-first-token (p50), the 113th fastest tracked model.
Hermes 4 70B supports a 131K-token context window. It accepts text input.