Document multi-provider model choices (Tinfoil private + GreenPT green)

api-access.md

@@ -9,14 +9,43 @@ client works.
 - **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:**
+- **Models:** see the table below.
-  - `deepseek-v4-1-flash` — default, best for agentic tasks (1M context, tool calling)
-  - `gpt-oss-120b` — lightweight fallback
-  - `glm-5-3-flash` — fast, efficient MoE model
 
 API usage draws from the **same monthly allowance as chat** — there's no separate
 quota.
 
+## Models
+
+Models are named `provider/model-name`, so you can choose not just *which* model
+but *where* it runs. Providers carry a value you can route by:
+
+| Model | Provider | Value |
+|---|---|---|
+| `deepseek-v4-1-flash` | Tinfoil | **private** (TEE) |
+| `gpt-oss-120b` | Tinfoil | **private** (TEE) |
+| `glm-5-3-flash` | Tinfoil | **private** (TEE) |
+| `greenpt/green-r` | GreenPT | **green** (renewable) |
+| `greenpt/green-l` | GreenPT | **green** (renewable) |
+
+- **Tinfoil** — *private*. Models run inside hardware enclaves (TEEs) with
+  end-to-end encryption, so neither we nor the provider can read your prompts
+  or responses. Best privacy.
+- **GreenPT** — *green*. Models served on 100% renewable energy in the EU.
+  Cleaner energy, standard (non-enclave) hosting.
+
+> **Note:** the three Tinfoil models currently use their bare names (no
+> `tinfoil/` prefix). They'll be renamed to `tinfoil/deepseek-v4-1-flash` and so
+> on in an upcoming change — we'll email members before that happens. GreenPT
+> models already use the `greenpt/` prefix.
+
+**Which to pick:**
+
+- `deepseek-v4-1-flash` — default; best for agentic tasks (1M context, tool calling).
+- `gpt-oss-120b` — lightweight fallback.
+- `glm-5-3-flash` — fast, efficient MoE model.
+- `greenpt/green-r` — reasoning, renewable energy.
+- `greenpt/green-l` — lightweight, renewable energy.
+
 ## Get a key
 
 Log in to the [Member Dashboard](https://dashboard.inference.coop) and create an
@@ -60,7 +89,7 @@ endpoint configuration:
 - **API type / protocol:** "OpenAI compatible" (or `openai-completions` where a
   protocol string must be named) — not "Ollama", "Anthropic", or "Responses"
 - **API key:** your member key (the `sk-…` string)
-- **Model:** one of `deepseek-v4-1-flash`, `gpt-oss-120b`, `glm-5-3-flash`
+- **Model:** one from the table above, e.g. `deepseek-v4-1-flash` or `greenpt/green-r`
 
 A typical provider entry looks like:
 
@@ -74,7 +103,9 @@ A typical provider entry looks like:
       "models": [
         { "id": "deepseek-v4-1-flash" },
         { "id": "gpt-oss-120b" },
-        { "id": "glm-5-3-flash" }
+        { "id": "glm-5-3-flash" },
+        { "id": "greenpt/green-r" },
+        { "id": "greenpt/green-l" }
       ]
     }
   }

getting-started.md

@@ -37,6 +37,9 @@ account. Click it and create your login.
 The chat lives at **[chat.inference.coop](https://chat.inference.coop)**. Log in
 with the account you created in step 1.
 
+- **Choose your model.** You can pick not just *which* model but *where* it runs:
+  **private** (Tinfoil, runs in encrypted enclaves) or **green** (GreenPT, 100%
+  renewable energy). See [API access](api-access.md#models) for the full list.
 - **Web search** is enabled by default (self-hosted, no external dependency).
 - **File uploads** work out of the box — ask the chat about a document you attach.
 - Your usage draws from your monthly allowance; you can see it on the

infrastructure.md

@@ -98,24 +98,38 @@ edit, and ask for review.
 
 Questions about the Git itself? Write to info@inference.coop.
 
-## Models and privacy
+## Models and providers
 
-Inference runs through [Tinfoil](https://tinfoil.sh/inference), which provides
+The co-op serves models from multiple providers, named `provider/model-name` so
-**architectural** privacy: models run inside hardware enclaves (TEEs), and
+members can choose both *which* model and *where* it runs. Each provider carries
-request/response bodies are encrypted end-to-end (EHBP), so even Tinfoil's own
+a value you can route by:
-infrastructure can't read them. This is verifiable via remote attestation — not
-just a policy promise. A local Tinfoil proxy sidecar handles the encryption on
-our side of the gateway.
 
-Three models are exposed:
+| Provider | Value | How it works |
+|---|---|---|
+| **Tinfoil** | *private* | Models run inside hardware enclaves (TEEs); request/response bodies are encrypted end-to-end (EHBP), so even Tinfoil's infrastructure can't read them. Verifiable via remote attestation. |
+| **GreenPT** | *green* | Models served on 100% renewable energy in the EU. Standard (non-enclave) hosting — cleaner energy, but privacy is a policy commitment, not architectural. |
+| **PublicAI** | *public* | (coming soon — publicly developed models.) |
 
-- **DeepSeek V4.1 Flash** — default, agentic tasks.
+Five models are currently exposed:
-- **GPT-OSS 120B** — lightweight fallback.
-- **GLM-5.3 Flash** — fast, efficient.
 
-The honest caveat: your **chat history** is stored on our server so you can
+- **DeepSeek V4.1 Flash** (`deepseek-v4-1-flash`) — default, agentic tasks. *(Tinfoil)*
-revisit it, and that stored history is not encrypted in a way that prevents us
+- **GPT-OSS 120B** (`gpt-oss-120b`) — lightweight fallback. *(Tinfoil)*
-from technically reading it. We commit not to. The full distinction — what's
+- **GLM-5.3 Flash** (`glm-5-3-flash`) — fast, efficient. *(Tinfoil)*
+- **Green-R** (`greenpt/green-r`) — reasoning, renewable energy. *(GreenPT)*
+- **Green-L** (`greenpt/green-l`) — lightweight, renewable energy. *(GreenPT)*
+
+The three Tinfoil models currently use their bare names (no `tinfoil/` prefix);
+they'll be renamed to `tinfoil/…` in an upcoming, announced change.
+
+A local Tinfoil proxy sidecar handles the enclave encryption on our side of the
+gateway.
+
+The honest caveat: only **Tinfoil** offers architectural privacy. The other
+providers are chosen for their value (renewable energy, public models) but do
+not run in enclaves — prompts and responses pass through them in the ordinary
+way. Your **chat history** is also stored on our server so you can revisit it,
+and that stored history is not encrypted in a way that prevents us from
+technically reading it — we commit not to. The full distinction — what's
 architecturally private versus what's a policy commitment — is in the
 [Privacy Policy](privacy-policy.md).