Add greenpt/deepseek-v4.1-flash as default (renewable, not Experimental); fallback → tinfoil deepseek

config.yaml

@@ -5,7 +5,8 @@
 # with EHBP (HPKE) before forwarding to the Tinfoil enclave. Provider key set
 # via environment variable TINFOIL_API_KEY.
 #
-# Pricing (model_info) is per-token, derived from Tinfoil's per-1M rates:
+# Pricing (model_info) is per-token, derived from provider per-1M rates:
+#   greenpt/deepseek-v4.1-flash: $0.22 in / $1.10 out / $0.011 cached per 1M
 #   tinfoil/deepseek-v4-1-flash: $0.65 in / $1.45 out / $0.13 cached per 1M
 #   tinfoil/gpt-oss-120b:        $0.15 in / $0.60 out per 1M
 #   tinfoil/glm-5-3-flash:       $0.40 in / $1.25 out / $0.10 cached per 1M
@@ -18,7 +19,22 @@
 # models.md is the member-facing mirror.
 
 model_list:
-  # DeepSeek V4.1 Flash — default model (replaces V4 Flash, deprecated 2026-09-15)
+  # DeepSeek V4.1 Flash on GreenPT — DEFAULT model. Same model family as Tinfoil's
+  # deepseek-v4-1-flash, but on renewable energy and NOT marked Experimental by the
+  # provider (Tinfoil's deepseek + glm-flash carry an "Experimental: may be deprecated
+  # with minimal notice" flag). Policy-based privacy (GreenPT) vs TEE (Tinfoil).
+  # €0.22 in / €1.10 out / €0.011 cached per 1M.
+  - model_name: greenpt/deepseek-v4.1-flash
+    litellm_params:
+      model: openai/deepseek-v4.1-flash
+      api_base: https://api.greenpt.ai/v1
+      api_key: os.environ/GREENPT_API_KEY
+    model_info:
+      input_cost_per_token: 0.00000022
+      output_cost_per_token: 0.00000110
+      cache_read_input_token_cost: 0.000000011
+
+  # DeepSeek V4.1 Flash on Tinfoil (TEE) — private counterpart to the default.
   - model_name: tinfoil/deepseek-v4-1-flash
     litellm_params:
       model: openai/deepseek-v4-1-flash
@@ -152,6 +168,8 @@ router_settings:
   retry_policy:
     TimeoutErrorRetries: 0
   fallbacks:
+    - greenpt/deepseek-v4.1-flash:
+        - tinfoil/deepseek-v4-1-flash
     - tinfoil/deepseek-v4-1-flash:
         - tinfoil/gpt-oss-120b