From 057507d67c10e75c1a74a44a060348b363fbc17c Mon Sep 17 00:00:00 2001
From: inference-bot <bot@inference.coop>
Date: Fri, 25 Sep 2026 15:56:08 -0600
Subject: [PATCH] Add PublicAI Apertus models (publicai/apertus-v1.5-8b, -70b)

---
 config.yaml | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/config.yaml b/config.yaml
index 9280c5f..2bb405a 100644
--- a/config.yaml
+++ b/config.yaml
@@ -85,6 +85,30 @@ model_list:
       output_cost_per_token: 0.00000044
       cache_read_input_token_cost: 0.000000022
 
+  # --- 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
+
 # Fallback: if DeepSeek is down, use GPT-OSS
 # NOTE: DeepSeek V4.1 Flash is a reasoning model — generations routinely run
 # longer than 30s. A 30s timeout caused LiteLLM to abandon in-flight DeepSeek