App profile
Hermes Agent
By Nous Research
An open-source agent from Nous Research. Connect a custom model service for multi-step tasks in your terminal.
GPT · Chat Completions
Live client test passed
Real conversation and a local read-only file tool passed, including random content, completion and billing checks. This covers the listed version and model only. OpenCode also has a separately recorded canceled stream whose hold released naturally.
API status · verifiedThe protocol used by this client succeeded in its corresponding GPT client test.
- Provider mode
- OpenAI-compatible
- Key service
- GPT
- Client base URL
https://api.openoxai.com/v1- Request endpoint
POST https://api.openoxai.com/v1/chat/completions- Model ID
gpt-6.1-sol
- 1
Prepare a GPT service key
Select the GPT service in Keys and confirm gpt-6.1-sol is allowed for that key.
- 2
Configure the custom provider
Select OpenAI-compatible and enter the URL and model below. Merge the configuration while preserving other providers.
- 3
Check the first request
Send a simple message and check its model, completion and cost in Usage. Tool support and charges depend on the selected model.
model:
provider: custom
default: gpt-6.1-sol
base_url: https://api.openoxai.com/v1
api_mode: chat_completions
api_key: YOUR_OPENOX_API_KEYReplace the placeholder with your own key. CLI environment variables use macOS, Linux or WSL shell syntax. Preserve existing settings.
Use the Hermes config.yaml. Claude mode requires the anthropic Python dependency; this installation was missing it during preflight.