---
title: "Draft Hermes Agent integration"
description: "Unverified draft settings for using Hermes Agent with minirouter."
canonical_url: "https://minirouter.sh/integrations/hermes"
markdown_url: "https://minirouter.sh/integrations/hermes.md"
last_updated: "2026-08-04"
---

# Hermes Agent + minirouter

Verification status: UNVERIFIED DRAFT
Confirm the current client fields and run the verification request before relying on this configuration.

Draft custom-endpoint configuration for Hermes Agent, including running it on the Hermes models themselves.

Base URL: https://api.minirouter.sh/v1
Get a key: https://minirouter.sh/key

## Settings

~/.hermes/config.yaml, with the key in ~/.hermes/.env

1. Setup wizard → provider: Custom OpenAI-compatible endpoint
2. Base URL: https://api.minirouter.sh/v1
   The wizard asks for the OpenAI-compatible root. Paste it complete, including /v1.
3. API key: mr-live-… (your key)
   Stored in ~/.hermes/.env, not inline in the config file.
4. model.provider: custom
5. model.name: nousresearch/hermes-4-70b

## Draft configuration

~/.hermes/config.yaml — unverified draft

```
model:
  provider: custom
  base_url: https://api.minirouter.sh/v1
  name: nousresearch/hermes-4-70b

# ~/.hermes/.env
# OPENAI_API_KEY=mr-live-YOUR-KEY-HERE
```

## Recommended models

Only use a model after confirming it appears in the live model catalog at https://minirouter.sh/api/v1/models.

- nousresearch/hermes-4-70b: The model the agent is named for, served here as open weights.
- meta/llama-3.3-70b: General-purpose candidate for the turn loop.
- mistral/ministral-14b: Small, cheap candidate for routine turns.
- zai/glm-5: Tool-calling candidate for multi-step chores.

## Troubleshooting

### Provider loads but every model call 404s

Paste https://api.minirouter.sh/v1 complete, including the /v1. These clients treat the base URL as the OpenAI-compatible root and append /chat/completions themselves, so trimming the /v1 leaves them calling a path that does not exist.

Error reference: https://minirouter.sh/docs/errors#invalid_request

### Switching back from a custom endpoint keeps failing

A stale base URL left behind by the previous provider is the usual cause. Confirm base_url in ~/.hermes/config.yaml matches the provider you actually selected.

### Credits gone overnight with nothing to show

An agent in a retry loop spends at machine speed. Set dailyLimitNano on the key the agent uses — one key per agent, so a runaway is contained to that key rather than the whole balance.

Error reference: https://minirouter.sh/docs/errors#insufficient_credits

### 401 on every request

Wrong or rotated key. Keys start with mr-live-; after a rotation the old key keeps working for 24 hours, then dies.

Error reference: https://minirouter.sh/docs/errors#invalid_api_key

### Response stops mid-sentence with a credits message

Balance hit $0 mid-stream. The stream ends with a terminal error naming the exact charge for tokens delivered — never a silent close.

Error reference: https://minirouter.sh/docs/errors#insufficient_credits