BETA
Nous: Hermes 4 70B is a community fine-tune. Behaviour and benchmarks track the upstream base model the fine-tune was trained from. Available via nousresearch. 131K-token context. Efficient pricing. Inherits weights from an upstream open-weights base; benchmarks track the base model unless the fine-tuner publishes their own.
Nous: Hermes 4 70B is a efficient AI model from nousresearch. It costs $0.130 per million input tokens and $0.400 per million output tokens (blended $0.211/M), with a 131K-token context window.
Nous: Hermes 4 70B costs $0.130 per million input tokens and $0.400 per million output tokens, for a blended reference rate of $0.211 per million tokens.
Nous: Hermes 4 70B supports up to 131K tokens of context (131,072 tokens).
Nous: Hermes 4 70B is well suited to Persona/tuning beyond the base model, Persona/style adherence beyond the base model and Specific domain (RP, instruction, etc.) tuning.
Nous: Hermes 4 70B is developed and served by nousresearch.