Rename Tinfoil models to tinfoil/* provider prefix

config.yaml

@@ -6,9 +6,9 @@
 # via environment variable TINFOIL_API_KEY.
 #
 # Pricing (model_info) is per-token, derived from Tinfoil's per-1M rates:
-#   deepseek-v4-1-flash: $0.65 in / $1.45 out / $0.13 cached per 1M
+#   tinfoil/deepseek-v4-1-flash: $0.65 in / $1.45 out / $0.13 cached per 1M
-#   gpt-oss-120b:        $0.15 in / $0.60 out per 1M
+#   tinfoil/gpt-oss-120b:        $0.15 in / $0.60 out per 1M
-#   glm-5-3-flash:       $0.40 in / $1.25 out / $0.10 cached per 1M
+#   tinfoil/glm-5-3-flash:       $0.40 in / $1.25 out / $0.10 cached per 1M
 # Without these, LiteLLM can't price these custom models, so spend shows $0.00
 # and the team budget cap is not enforced.
 #
@@ -19,7 +19,7 @@
 
 model_list:
   # DeepSeek V4.1 Flash — default model (replaces V4 Flash, deprecated 2026-09-15)
-  - model_name: deepseek-v4-1-flash
+  - model_name: tinfoil/deepseek-v4-1-flash
     litellm_params:
       model: openai/deepseek-v4-1-flash
       api_base: http://127.0.0.1:3301/v1
@@ -30,7 +30,7 @@ model_list:
       cache_read_input_token_cost: 0.00000013
 
   # GPT-OSS 120B — lightweight fallback
-  - model_name: gpt-oss-120b
+  - model_name: tinfoil/gpt-oss-120b
     litellm_params:
       model: openai/gpt-oss-120b
       api_base: http://127.0.0.1:3301/v1
@@ -40,7 +40,7 @@ model_list:
       output_cost_per_token: 0.00000060
 
   # GLM-5.3 Flash — fast, efficient MoE model
-  - model_name: glm-5-3-flash
+  - model_name: tinfoil/glm-5-3-flash
     litellm_params:
       model: openai/glm-5-3-flash
       api_base: http://127.0.0.1:3301/v1
@@ -88,8 +88,8 @@ router_settings:
   retry_policy:
     TimeoutErrorRetries: 0
   fallbacks:
-    - deepseek-v4-1-flash:
+    - tinfoil/deepseek-v4-1-flash:
-        - gpt-oss-120b
+        - tinfoil/gpt-oss-120b
 
 general_settings:
   master_key: os.environ/LITELLM_MASTER_KEY