Hermes Agent API setup: custom endpoint and Base URL

Hermes Agent supports custom OpenAI-compatible endpoints. Exit the current chat and run the setup wizard below in your terminal. The in-chat /model command switches configured models; it does not add a new endpoint or key.

Hermes on Link: check task budgets and groups together

Use a dedicated Link key for Hermes, verify that the chosen provider resolves to https://www.aifast.link/v1, and identify whether it uses Chat Completions or Responses. A configuration template is not runtime proof; confirm the route with a short real task.

Long tasks, tool loops and scheduled jobs can consume the daily allowance continuously. Plans cover specified groups only. Set limits on turns, retries and spending, and check the wallet-fallback preference after allowance exhaustion.

Review Link funding and monthly-plan rules

Check before you start

Prepare the following information:

Base URL: https://www.aifast.link/v1
API Key: YOUR_LINK_API_KEY
Model: YOUR_MODEL_ID

First use curl to verify the Key and model list:

export AIFAST_LINK_API_KEY="YOUR_LINK_API_KEY"

curl https://www.aifast.link/v1/models \
  -H "Authorization: Bearer $AIFAST_LINK_API_KEY"

Configuration steps

Run:

hermes model

Select the custom endpoint in the wizard and fill in the following:

1. API base URL: https://www.aifast.link/v1
2. API key: AIFast independent Key
3. Model name: real model ID
4. API mode: Select the corresponding mode when the target model uses Chat Completions

Choose the API mode supported by your target model. The current setup wizard saves this choice. Configuration structure can vary by version; the example below shows core fields only and should not replace the full generated file.

Hermes will save the current model and endpoints to ~/.hermes/config.yaml. After the configuration is completed, check whether the core fields in the file are consistent:

model:
  default: YOUR_MODEL_ID
  provider: custom
  base_url: https://www.aifast.link/v1

Do not commit configuration files containing real API keys to Git. For a named custom provider, prefer key_env to reference environment variables.

Avoid conflicting endpoint settings

Save the custom endpoint through the wizard and check the active provider and Base URL. Do not assume legacy OPENAI_BASE_URL or LLM_MODEL variables override the current configuration.

Minimal verification

After starting Hermes, send the short task first:

Reply with only: connection ok

Then check:

1. The active provider is the custom provider you just configured, not the previous one.
2. The chosen model ID must appear in the /v1/models list returned for your key.
3. The request address is not duplicated /v1.
4. After the normal conversation is successful, test tool calls and long tasks.

FAQ

Still requesting old provider after configuration

Check ~/.hermes/config.yaml in model.provider and model.base_url, and clean up old environment variables that conflict with the current settings. Restart Hermes and verify again.

/model custom Unable to automatically select model

Automatic selection requires the endpoint to return exactly one model. Link may expose several models, so explicitly enter a model ID available to your account.

Text generation succeeds but Agent tool fails

Custom endpoints must correctly handle the request and response fields required for tool calls. Confirm the link with a normal conversation first, and then test the tool call individually; do not attribute all failures to model capabilities.

Next step

Set API Key, usage limit and log retention policy individually for Hermes. Test tool calls, long contexts, 429 backoffs, and model switches before going live, and make sure profile permissions are not open to other local users.