From ad34da72a4f6f6eb695a71b91d6473e69b36eaaa Mon Sep 17 00:00:00 2001
From: Inferencebot <inference-bot@inference.coop>
Date: Fri, 16 Oct 2026 10:10:45 -0600
Subject: [PATCH] Add Regolo provider: apertus-70b, qwen3.5-122b (thinking
 off), qwen-image + Apertus fallback chain

---
 config.yaml | 42 ++++++++++++++++++++++++++++++++++++++++++
 start.sh    |  5 +++++
 2 files changed, 47 insertions(+)

diff --git a/config.yaml b/config.yaml
index 2fc409b..69188a7 100644
--- a/config.yaml
+++ b/config.yaml
@@ -130,6 +130,44 @@ model_list:
       input_cost_per_token: 0.00000082
       output_cost_per_token: 0.00000292
 
+  # --- Regolo (EU, zero data retention, 100% renewables) ---
+  # Seeweb S.r.l. (Italy). Added 2026-10-16 following member suggestion (#22).
+  # apertus-70b: same open-weights model as PublicAI's apertus-v1.5-70b, ~45% cheaper
+  #   input. Wired as fallback pair with PublicAI (see router_settings.fallbacks).
+  # qwen3.5-122b: large vision+reasoning MoE (262K ctx). REQUIRES
+  #   chat_template_kwargs: {enable_thinking: false} — otherwise the reasoning
+  #   phase consumes the entire token budget and content comes back empty.
+  # Qwen-Image: image generation via /v1/images/generations, billed per pixel.
+  - model_name: regolo/apertus-70b
+    litellm_params:
+      model: openai/apertus-70b
+      api_base: https://api.regolo.ai/v1
+      api_key: os.environ/REGOLO_API_KEY
+    model_info:
+      mode: chat
+      input_cost_per_token: 4.6e-7
+      output_cost_per_token: 2.44e-6
+
+  - model_name: regolo/qwen3.5-122b
+    litellm_params:
+      model: openai/qwen3.5-122b
+      api_base: https://api.regolo.ai/v1
+      api_key: os.environ/REGOLO_API_KEY
+      chat_template_kwargs: {"enable_thinking": false}
+    model_info:
+      mode: chat
+      input_cost_per_token: 1.16e-6
+      output_cost_per_token: 4.87e-6
+
+  - model_name: regolo/qwen-image
+    litellm_params:
+      model: openai/Qwen-Image
+      api_base: https://api.regolo.ai/v1
+      api_key: os.environ/REGOLO_API_KEY
+    model_info:
+      mode: image_generation
+      input_cost_per_pixel: 1.5e-8
+
   # --- Audio models (Tinfoil, in-TEE) ---
   # Used for chat dictation (STT) and voice mode (TTS). These are NOT chat
   # models: the member portal's /v1/models filters them out of the chat model
@@ -193,6 +231,10 @@ router_settings:
         - tinfoil/deepseek-v4-1-flash
     - tinfoil/deepseek-v4-1-flash:
         - tinfoil/gpt-oss-120b
+    - publicai/apertus-v1.5-70b:
+        - regolo/apertus-70b
+    - regolo/apertus-70b:
+        - publicai/apertus-v1.5-70b
 
 general_settings:
   master_key: os.environ/LITELLM_MASTER_KEY
diff --git a/start.sh b/start.sh
index e792afd..cf64ed3 100644
--- a/start.sh
+++ b/start.sh
@@ -37,6 +37,11 @@ if [ ! -f "$MASTER_KEY_FILE" ]; then
     python3 -c "import secrets; print('sk-' + secrets.token_urlsafe(32))" > "$MASTER_KEY_FILE"
 fi
 export LITELLM_MASTER_KEY=$(cat "$MASTER_KEY_FILE")
+# Regolo API key (member-suggested provider, 2026-10-16): stored in /app/data by the operator
+# via the Cloudron file manager — kept out of app env config and git.
+if [ -f "/app/data/regolo_key.txt" ]; then
+  export REGOLO_API_KEY=$(cat /app/data/regolo_key.txt | tr -d '[:space:]')
+fi
 
 # Generate a salt key if not already in /app/data
 SALT_KEY_FILE="/app/data/.salt_key"