From 0e605de7d5bc8160b5140ba5b8454b6493e243be Mon Sep 17 00:00:00 2001
From: inference-bot <inference-bot@hermes>
Date: Mon, 14 Sep 2026 17:04:51 -0600
Subject: [PATCH] Expand API access docs: curl, OpenAI SDK, pi.dev, and generic
 OpenAI-compatible configs

---
 README.md | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 59 insertions(+), 6 deletions(-)

diff --git a/README.md b/README.md
index d60386c..824ad9e 100644
--- a/README.md
+++ b/README.md
@@ -72,20 +72,73 @@ The gateway currently exposes three models (all served through Tinfoil's TEE-pro
 
 Members can use the co-op's models programmatically through an OpenAI-compatible API:
 
-- **Endpoint:** `https://gateway.inference.coop/v1`
-- **Auth:** a bearer API key (created in the [Member Dashboard](https://dashboard.inference.coop))
-- **Format:** standard OpenAI chat completions (`POST /v1/chat/completions`)
+- **Endpoint (base URL):** `https://gateway.inference.coop/v1`
+- **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:** `deepseek-v4-1-flash` (default), `gpt-oss-120b`, `glm-5-3-flash`
 
-Example:
+API usage draws from the **same monthly balance as chat** — there is no separate quota. The gateway is publicly reachable (member keys authenticate it), but its admin UI and API documentation are disabled; admin access is via the internal dashboard or the gateway's admin endpoints.
+
+#### Plain `curl`
 
 ```bash
 curl https://gateway.inference.coop/v1/chat/completions \
-  -H "Authorization: Bearer sk-..." \
+  -H "Authorization: Bearer sk-your-key" \
   -H "Content-Type: application/json" \
   -d '{"model": "deepseek-v4-1-flash", "messages": [{"role": "user", "content": "Hello"}]}'
 ```
 
-API usage draws from the **same monthly balance as chat** — there is no separate quota. The gateway is publicly reachable (member keys authenticate it), but its admin UI and API documentation are disabled; admin access is via the internal dashboard or the gateway's admin endpoints.
+#### OpenAI SDK (Python, Node, etc.)
+
+Point the SDK at our base URL and use the member key:
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="https://gateway.inference.coop/v1",
+    api_key="sk-your-key",
+)
+resp = client.chat.completions.create(
+    model="deepseek-v4-1-flash",
+    messages=[{"role": "user", "content": "Hello"}],
+)
+```
+
+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.
+
+#### pi.dev (coding agent)
+
+pi.dev's `api` field selects the protocol. Use `openai-completions` (our gateway is an OpenAI-compatible chat-completions server), set `baseUrl` to the full `/v1` path, and `apiKey` to your member key:
+
+```json
+{
+  "providers": {
+    "inference-coop": {
+      "baseUrl": "https://gateway.inference.coop/v1",
+      "api": "openai-completions",
+      "apiKey": "sk-your-key",
+      "models": [
+        { "id": "deepseek-v4-1-flash" },
+        { "id": "gpt-oss-120b" },
+        { "id": "glm-5-3-flash" }
+      ]
+    }
+  }
+}
+```
+
+Note: pi.dev appends `/chat/completions` to `baseUrl` itself, so include the trailing `/v1` and do **not** add `/chat/completions`.
+
+#### Other OpenAI-compatible tools (Ollama-style, LibreChat, etc.)
+
+The general pattern is the same across tools that speak the OpenAI API:
+
+- **Base URL / endpoint:** `https://gateway.inference.coop/v1`
+- **API type / protocol:** "OpenAI compatible" or `openai-completions` (not "Ollama", "Anthropic", or "Responses")
+- **API key:** your member key (the `sk-…` string)
+
+If a tool's docs show an Ollama example with `baseUrl: http://localhost:11434/v1` and `api: "openai-completions"`, substitute our base URL and your member key for `apiKey` — the `api` value stays the same.
 
 ### Privacy