From 9d95527e93d98f3ad207af58fa6aa927fa6bd246 Mon Sep 17 00:00:00 2001
From: Inferencebot <inference-bot@inference.coop>
Date: Fri, 16 Oct 2026 10:46:04 -0600
Subject: [PATCH] Remove PublicAI provider (billing never operational; Regolo
 replaces it for Apertus)

---
 config.yaml | 33 ++-------------------------------
 1 file changed, 2 insertions(+), 31 deletions(-)

diff --git a/config.yaml b/config.yaml
index 69188a7..51cdfab 100644
--- a/config.yaml
+++ b/config.yaml
@@ -105,35 +105,10 @@ model_list:
   # options. Pricing per Tinfoil catalog: whisper $0.05/1M in; voxtral-tts
   # listed $0/$0 (verify on invoice — may be beta-free).
 
-
-  # --- PublicAI (publicly developed / sovereign models) ---
-  # OpenAI-compatible gateway for public open models. Apertus is the Swiss AI
-  # Initiative's fully-open model (Apache-2.0: weights, code, and training data).
-  # Pricing from PublicAI /v1/models (per 1M): 8b $0.10/$0.20, 70b $0.82/$2.92.
-  # Member-facing name drops the upstream `swiss-ai/` owner prefix for brevity;
-  # the litellm_params.model keeps the full PublicAI id.
-  - model_name: publicai/apertus-v1.5-8b
-    litellm_params:
-      model: openai/swiss-ai/apertus-v1.5-8b
-      api_base: https://api.publicai.co/v1
-      api_key: os.environ/PUBLICAI_API_KEY
-    model_info:
-      input_cost_per_token: 0.00000010
-      output_cost_per_token: 0.00000020
-
-  - model_name: publicai/apertus-v1.5-70b
-    litellm_params:
-      model: openai/swiss-ai/apertus-v1.5-70b
-      api_base: https://api.publicai.co/v1
-      api_key: os.environ/PUBLICAI_API_KEY
-    model_info:
-      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).
+  # apertus-70b: replaced PublicAI (removed 2026-10-16) as our Apertus provider —
+  #   same open-weights model, ~45% cheaper input, EU ZDR + renewables.
   # 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.
@@ -231,10 +206,6 @@ 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