Skip to main content
QwenCloud home page
Docs
Connect AI Tools

Hermes Agent

Terminal AI coding assistant by Nous Research

When using qwen4-max-preview, keep provider: custom; do not set it to anthropic, or the model name will be rewritten and return 400.

Install Hermes Agent

  1. Run this command to install Hermes Agent. The script automatically installs dependencies like Python and Git.
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
Windows does not support native installation. Install WSL2 first, then run the above command in WSL2.
  1. After installation, reload the terminal environment.
source ~/.bashrc    # If using zsh, change to source ~/.zshrc
  1. Verify the installation. A version number confirms success.
hermes --version

Add a model

Choose your client and complete the configuration.
  • CLI
  • Desktop
1

Get an API key

2

Configure the model

Run hermes model, select the provider for your billing plan, enter the API key, and select a model.
  • Token Plan
  • Pay-as-you-go
  1. Select Qwen > Alibaba Cloud (Token Plan).
  2. Enter the Token Plan API key and keep the default Base URL.
  3. Select a model. For supported models, see the Individual plan supported models and Team Edition supported models.
The provider list may include models that your plan does not support. The plan's supported model list is authoritative.
3

Verify

Run the following command to verify:
hermes chat -q "hello"

Configure with a configuration file

The provider list in hermes model includes QwenCloud from v2026.8.31. If it is not in the list, use the following steps.
1

Open or create the configuration file

  • macOS / Linux / WSL2: ~/.hermes/config.yaml
  • Windows: %LOCALAPPDATA%\hermes\config.yaml
2

Add the configuration

Replace YOUR_API_KEY with the API key for that plan, and add the configuration to the model section.
  • Token Plan
  • Pay-as-you-go
OpenAI-compatible
model:
  default: auto
  provider: custom
  base_url: https://token-plan.maas.qwencloudapi.com/compatible-mode/v1
  api_key: YOUR_API_KEY
Anthropic-compatible
model:
  default: auto
  provider: custom
  base_url: https://token-plan.maas.qwencloudapi.com/apps/anthropic
  api_mode: anthropic_messages
  api_key: YOUR_API_KEY
3

Verify

After saving, run hermes chat -q "Hello" to verify.

Error codes

If you encounter an error during configuration, see the FAQ for your billing plan:

FAQ

The model list in hermes model may include models that your plan does not support. Select a model from the plan's supported model list, or select Enter custom model name and enter a model ID.