diff --git a/agent/.env.example b/agent/.env.example
index db5d5854..41f6ef26 100644
--- a/agent/.env.example
+++ b/agent/.env.example
@@ -9,7 +9,6 @@ GROQ_API_KEY=
 MISTRAL_API_KEY=
 NOUS_API_KEY=
 NVIDIA_API_KEY=
-NVIDIA_NIM_API_KEY=
 OPENCODE_ZEN_API_KEY=
 OPENROUTER_API_KEY=
 PARALLEL_API_KEY=
diff --git a/agent/litellm/config.yaml b/agent/litellm/config.yaml
index 69462f00..4b0f2c8b 100644
--- a/agent/litellm/config.yaml
+++ b/agent/litellm/config.yaml
@@ -1,12 +1,67 @@
 general_settings:
   store_model_in_db: true
+  enable_health_check_routing: true
+  background_health_checks: true
+  health_check_interval: 60
+  health_check_ignore_transient_errors: true
+  cancel_on_disconnect: true
 
 litellm_settings:
-  drop_params: true
-  request_timeout: 60
   json_logs: true
+  request_timeout: 60
+  drop_params: true
+
+router_settings:
+  cooldown_time: 60
+  allowed_fails: 3
+  ttft_timeout: 30
+  enable_pre_call_checks: true
+  optional_pre_call_checks: [prompt_caching]
+  enable_anthropic_prompt_caching: true
+  default_litellm_params:
+    cache_control_injection_points:
+      - location: message
+        role: system
+  default_fallbacks: [complex, medium, simple]
+  fallbacks:
+    - reasoning: complex
+    - complex: medium
+    - medium: simple
 
 model_list:
+  - model_name: auto
+    litellm_params:
+      model: auto_router/complexity_router
+      complexity_router_config:
+        tiers:
+          SIMPLE: simple
+          MEDIUM: medium
+          COMPLEX: complex
+          REASONING: reasoning
+      adaptive: true
+      session_affinity: true
+      complexity_router_default_model: complex
+
+  - model_name: simple
+    litellm_params:
+      model: openai/deepseek-v4-flash-free
+      litellm_credential_name: opencode_zen
+
+  - model_name: medium
+    litellm_params:
+      model: openai/deepseek-v4-flash-free
+      litellm_credential_name: opencode_zen
+
+  - model_name: complex
+    litellm_params:
+      model: openai/tencent/hy3:free
+      litellm_credential_name: nous
+
+  - model_name: reasoning
+    litellm_params:
+      model: openai/tencent/hy3:free
+      litellm_credential_name: nous
+
   - model_name: cerebras/gemma-4-31b
     litellm_params:
       model: cerebras/gemma-4-31b
@@ -42,19 +97,6 @@ model_list:
     litellm_params:
       model: openrouter/openrouter/free
 
-  - model_name: smart-router
-    litellm_params:
-      model: auto_router/complexity_router
-      complexity_router_config:
-        tiers:
-          SIMPLE: opencode-zen/deepseek-v4-flash-free
-          MEDIUM: opencode-zen/deepseek-v4-flash-free
-          COMPLEX: nous/hy3:free
-          REASONING: nous/hy3:free
-      adaptive: true
-      session_affinity: true
-      complexity_router_default_model: nous/hy3:free
-
 credential_list:
   - credential_name: nous
     credential_values: