Guides / Hermes Agent

Use Hermes Agent with llmapi.cheap

Run Hermes Agent on Gemini 3.8 Flash, Claude Sonnet 4.6, Claude Opus 4.6 or GPT-OSS with a single llmapi.cheap key. Plans start at $2 a month, and there is a free one-hour trial.

Protocol: OpenAI Chat · Config: ~/.hermes/config.yaml

Fastest: one command

The setup command finds Hermes Agent on your machine, writes its configuration with your key and sets Gemini 3.8 Flash (high) as the default model. It needs no Node.js. Sign up first: your key is created automatically, and the dashboard shows this command with the key already filled in.

macOS / Linux

curl -fsSL https://llmapi.cheap/install.sh | sh

Windows (PowerShell)

irm https://llmapi.cheap/install.ps1 | iex

Manual setup

Let Hermes write its own config (on Windows it lives in %LOCALAPPDATA%\hermes):

hermes config set LLMAPI_API_KEY YOUR_API_KEY
hermes config set model.provider custom
hermes config set model.base_url https://llmapi.cheap/v1
hermes config set model.key_env LLMAPI_API_KEY
hermes config set model.default gemini-3.8-flash-high

Endpoints

Use the base URL that matches the protocol your tool speaks.

OpenAI
https://llmapi.cheap/v1
Anthropic
https://llmapi.cheap
Gemini
https://llmapi.cheap/v1beta
Models
https://llmapi.cheap/v1/models

Model IDs

Any of these work wherever Hermes Agent asks for a model name. Gemini 3.8 Flash (high) is the default the setup command picks.

Model IDModel
gemini-3.8-flash-highGemini 3.8 Flash, high reasoning (default)
gemini-3.8-flashGemini 3.8 Flash, medium reasoning
gemini-3.8-flash-lowGemini 3.8 Flash, low reasoning
gemini-3.1-pro-highGemini 3.1 Pro, high reasoning
gemini-3.1-pro-lowGemini 3.1 Pro, low reasoning
gemini-3-flashGemini 3 Flash
claude-sonnet-4-6Claude Sonnet 4.6
claude-opus-4-6Claude Opus 4.6
gpt-oss-120bGPT-OSS 120B

Troubleshooting

  • 401 / invalid key: check the key starts with sk-llm- and has no extra spaces. Create a new one under Dashboard → API keys if needed.
  • Model not allowed: the free trial covers the Gemini models; Claude and GPT-OSS come with any paid plan.
  • 404 on requests: OpenAI-style tools need https://llmapi.cheap/v1; Anthropic-style tools need https://llmapi.cheap without /v1.