Use Hermes Agent with WebikAI

Hermes Agent supports a custom OpenAI-compatible endpoint, so a persistent agent can run on WebikAI routes with a client-labeled key, a spend cap, and a receipt on every call.

Setup

Create an account, confirm your email, complete the four-question onboarding, and copy your wk_live_… key (shown once).
Add a supported provider credential for BYOK, fund the managed wallet, or do both for hybrid.
Pick the custom endpoint in Hermes' model menu:

bash

hermes model
# choose: Custom endpoint
#   Base URL: https://gateway.webik.ai/v1
#   API key:  wk_live_...
#   Model:    auto/chat

The base URL must end at /v1 — Hermes appends /chat/completions itself. Hermes saves the selection for every subsequent run; re-run hermes model to change it. Config-file users: set provider: custom with the same base_url in the model: section (see the Hermes provider docs).

Models to start with

Alias	Routes to
auto/chat	Balanced general-purpose chat
auto/code	WebikAI lane ranked by coding evidence under your rules
auto/cheap	Aggressively minimize cost
auto/vision	Multimodal — image or document input
z-ai/glm-5.2	Pin an exact model (OpenRouter-style slug)

Honest limit

Hermes runs scheduled automations and subagents, so it can spend while you sleep. Spend caps hold estimates — final provider-reported usage can exceed one — so give an always-on agent its own key with a monthly cap sized for unattended operation.

Route receipts and spend controls

Every successful routed response carries the five x-webik-* receipt headers, and per-key or client spend caps can stop a request before it is forwarded. Label the key by client to separate usage in reports.

Full reference: docs · live scores: benchmarks · start free