docs: Metis is not yet metered; document the decisions endpoint in API access

models.md claimed decisions count toward the member allowance. Verified today that a
/v1/systemone call registers no spend against the calling key, so the claim was wrong.
States the gap plainly instead. api-access.md now names the decisions route, the fact
that it is not an OpenAI chat endpoint, and the metering caveat.

api-access.md

@@ -10,6 +10,10 @@ client works.
 - **Auth:** a bearer API key (create one in the [Member Dashboard](https://dashboard.inference.coop))
 - **Format:** OpenAI chat completions — `POST https://gateway.inference.coop/v1/chat/completions`
 - **Models:** see the [model list](models.md).
+- **Not only chat:** the gateway also serves a decision endpoint,
+  `POST https://gateway.inference.coop/v1/systemone` — see
+  [Decisions](models.md#decisions). It takes a different request shape, so
+  it is not reachable through an OpenAI SDK's `chat.completions` call.
 
 API usage draws from the **same monthly allowance as chat** — there's no separate
 quota.
@@ -66,6 +70,24 @@ resp = client.chat.completions.create(
 Any OpenAI-compatible client works the same way: set the base URL to
 `https://gateway.inference.coop/v1` and the API key to your member key.
 
+## Decisions (Metis)
+
+Alongside the chat models, the gateway exposes GreenPT's **Metis** decision model
+at `POST https://gateway.inference.coop/v1/systemone`. It is the same key and the
+same base URL — only the path and the request body differ. For what it is, the
+three question types, and a full `curl` example, see
+[Decisions in the model list](models.md#decisions).
+
+Two practical notes:
+
+- **It is not an OpenAI chat endpoint.** You send a `state` plus typed `questions`
+  and receive probabilities; there is nothing for an OpenAI SDK's
+  `chat.completions` to parse. Post the body directly (`curl`, `requests`,
+  `httpx`, or an SDK's generic POST).
+- **Its usage is not yet metered** (see the note in the model list): calls
+  currently register no spend against your key. Use it as though it counted
+  toward your allowance, because that is what it is meant to do.
+
 ## Coding agents and other OpenAI-compatible clients
 
 Any tool that speaks the OpenAI API works. Where a tool asks for provider or

models.md

@@ -227,10 +227,12 @@ curl https://gateway.inference.coop/v1/systemone \
 ```
 
 Metis is hosted by **GreenPT** — the same policy-based privacy, EU hosting, and
-100% renewable energy as the 🌱 chat models. Metering on this route is
+100% renewable energy as the 🌱 chat models. **Metering on this route is not yet active.** Verified 2026-11-03: a call to
-**approximate**: the gateway bills a small flat amount per call rather than the
+`/v1/systemone` returns a correct answer but registers no spend against the
-exact token count, so treat its spend figure as an estimate (it still counts
+key that made it, so decisions currently do not count toward your monthly
-toward your allowance).
+allowance. That is a gap on our side, not a policy — the intent is that
+decisions draw on the same allowance as everything else. Until it is fixed,
+please use the route in the spirit of the allowance it is meant to share.
 
 ## Limitations on privacy