AI Providers
This page covers setting up inference providers for Hermes Agent — from cloud APIs like OpenRouter and Anthropic, to self hosted endpoints like Ollama and vLLM,
This page covers setting up inference providers for Hermes Agent — from cloud APIs like OpenRouter and Anthropic, to self-hosted endpoints like Ollama and vLLM, to advanced routing and fallback configurations. You need at least one provider configured to use Hermes. You need at least one way to connect to an LLM. …
What this page covers
- Inference Providers
- Nous Portal
- Two Commands for Model Management
- Anthropic (Native)
- GitHub Copilot
- First-Class API-Key Providers
- xAI (Grok) — Responses API + Prompt Caching
- NovitaAI
- Ollama Cloud — Managed Ollama Models, OAuth + API Key
- AWS Bedrock
- Qwen Portal (OAuth)
- Alibaba Cloud (Coding Plan)
- MiniMax (OAuth)
- NVIDIA NIM
- GMI Cloud
- StepFun
- Hugging Face Inference Providers
- Google Gemini via OAuth (google-gemini-cli)
- Custom & Self-Hosted LLM Providers
- General Setup
- Switching Models with /model
- Ollama — Local Models, Zero Config
- vLLM — High-Performance GPU Inference
- SGLang — Fast Serving with RadixAttention
- llama.cpp / llama-server — CPU & Metal Inference
- LM Studio — Desktop App with Local Models
- WSL2 Networking (Windows Users)
- Troubleshooting Local Models
- LiteLLM Proxy — Multi-Provider Gateway
- ClawRouter — Cost-Optimized Routing
- Other Compatible Providers
- Context Length Detection
- Named Custom Providers
- Cookbook: Together AI, Groq, Perplexity
- Choosing the Right Setup
- Optional API Keys
- Self-Hosting Firecrawl
- OpenRouter Provider Routing
- OpenRouter Pareto Code Router
- Fallback Providers
- See Also
Section outline mirrored from the official Hermes Agent documentation. Follow any heading to read the complete text on the source site.
More in Integrations
Integrations
Hermes Agent connects to external systems for AI inference, tool servers, IDE workflows, programmatic access, and more. These integrations extend what Hermes ca
Nous Portal
Nous Portal is Nous Research's unified subscription gateway and the recommended way to run Hermes Agent . One OAuth login replaces the juggling act of separate