LLM ReferenceLLM Reference

Hermes 2

Nous ResearchOpen Source
12 models2023Up to 200K ctxFrom $0.05/1M input

About

The Hermes 2 family of large language models, crafted by Nous Research, represents a suite of advanced models derived from diverse base architectures and refined for exceptional capabilities. Known for their superior performance across a wide spectrum of both general tasks and conversations, these models shine particularly in function calling and generating structured JSON outputs 23. Hermes 2 incorporates ChatML, facilitating structured multi-turn dialogues and specialized prompts tailored for dependable function calling and JSON output. Comprising models built on Llama 3 and Mistral architectures, they offer varying parameter configurations that cater to diverse performance needs 2. These models are evaluated highly in accuracy for function calling and JSON generation, making them apt for applications where reliable and interpretable machine-generated responses are crucial 4.

Specifications(12 models)

Hermes 2 model specifications comparison
ModelReleasedContextParametersFn Calling
Hermes 2 Pro Llama 3 8B2023-128BNo
Hermes 2 Theta Llama 3 8B2023-128BNo
Hermes 2 Pro Mistral 7B2023-1232K7BYes
Nous Hermes 2 Mixtral 8x7B2023-128x7BNo
Nous Hermes 2 Mistral 7B2023-1232K7BNo
Nous Hermes 2 Yi 34B2023-12200K34BNo
Nous Hermes 2 SOLAR 10.7B2023-1210.7BNo
Hermes 2 Theta Llama 3 70B2023-1270BNo
Hermes 2 Pro Llama 3 70B2023-128K70BNo
Nous Hermes 2 Llama 2 70B2023-124K70BNo
Nous Hermes 2 Llama 2 13B2023-124K13BNo
Nous Hermes 2 Llama 2 7B2023-124K7BNo

Available From(7 providers)

Pricing

Hermes 2 model pricing by provider
ModelProviderInput / 1MOutput / 1MType
Hermes 2 Theta Llama 3 8BReplicate API$0.05$0.25Serverless
Nous Hermes 2 SOLAR 10.7BReplicate API$0.1$0.5Serverless
Hermes 2 Pro Llama 3 8BOpenRouter$0.14$0.14Serverless
Nous Hermes 2 Mixtral 8x7BOctoAI API$0.15$0.15Serverless
Hermes 2 Pro Llama 3 8BOctoAI API$0.15$0.15Serverless
Hermes 2 Pro Mistral 7BFireworks AI$0.2$0.2Provisioned
Nous Hermes 2 Mistral 7BTogether AI$0.2$0.2Serverless
Nous Hermes 2 Yi 34BReplicate API$0.2$1Serverless
Hermes 2 Pro Llama 3 8BMicrosoft Foundry$0.37$1.1Provisioned
Nous Hermes 2 Mixtral 8x7BFireworks AI$0.5$0.5Provisioned
Nous Hermes 2 Mixtral 8x7BTogether AI$0.6$0.6Serverless
Nous Hermes 2 Yi 34BTogether AI$0.8$0.8Serverless
Nous Hermes 2 Yi 34BFireworks AI$0.9$0.9Provisioned

Frequently Asked Questions

What is Hermes 2?
The Hermes 2 family of large language models, crafted by Nous Research, represents a suite of advanced models derived from diverse base architectures and refined for exceptional capabilities. Known for their superior performance across a wide spectrum of both general tasks and conversations, these models shine particularly in function calling and generating structured JSON outputs 23. Hermes 2 incorporates ChatML, facilitating structured multi-turn dialogues and specialized prompts tailored for dependable function calling and JSON output. Comprising models built on Llama 3 and Mistral architectures, they offer varying parameter configurations that cater to diverse performance needs 2. These models are evaluated highly in accuracy for function calling and JSON generation, making them apt for applications where reliable and interpretable machine-generated responses are crucial 4.
How many models are in the Hermes 2 family?
The Hermes 2 family contains 12 models.
What is the latest Hermes 2 model?
The latest model is Hermes 2 Pro Llama 3 8B, released in 2023-12.
How much does Hermes 2 cost?
Hermes 2 models range from $0.05/1M to $0.9/1M input tokens depending on the model and provider.

Models(12)