Models
You can access 0 models via the Nous API, powered by OpenRouter:
Showing 10 recommended models for use in Hermes Agent. Search to browse all 0 supported models.
| Model | Token Price |
|---|---|
| minimax/minimax-m2.7 | Price unavailable |
| moonshotai/kimi-k2.5 | Price unavailable |
| z-ai/glm-5 | Price unavailable |
| google/gemini-3-flash-preview | Price unavailable |
| mistralai/mistral-small-2603 | Price unavailable |
| openai/gpt-5.4 | Price unavailable |
| openai/gpt-5.4-mini | Price unavailable |
| anthropic/claude-opus-4.7 | Price unavailable |
| anthropic/claude-sonnet-4.6 | Price unavailable |
| nvidia/nemotron-3-ultra:free | $0.00/1M |
| Supported model data is currently unavailable. | |
Hermes 4
Hermes 4 models are not recommended for use in Hermes Agent. Use an agentic model from the list above.
Hermes 4 is a frontier, hybrid-mode reasoning model. It extends Hermes 3 with stronger math and science reasoning, better instruction following and schema-adherent outputs, and more nuanced roleplay and writing.
Hybrid thinking models require the following system prompt to activate reasoning mode:
You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.
Hermes-4-70B
Model CardAvailable to all API users
Was: $0.70/1M tokens
$0.80/1M prompt tokens
$0.60/1M completion tokens
Free on Nous Chat!
128k tokens ctx
Thinking:
hybrid
This incarnation of Hermes 4 balances scale and size. It handles complex reasoning tasks, while staying fast and cost effective. A versatile choice for many use cases.
This model is based on Llama-3.1-70B.
Hermes-4-405B
Model Card
Unsupported Models
Hermes-4.3-36B
Model CardCurrently unavailable via the API
You can use this model locally, but if you're using our hosted API we recommend migrating to Hermes-4-70B.
N/A
128k tokens ctx
Thinking:
hybrid
Hermes 4.3 is optimised for local deployment. You can dowload it from Hugging Face for local use.