num_workers 4

Dockerfile

@@ -15,7 +15,7 @@
 
 from ghcr.io/berriai/litellm:main-latest
 
-# SERVER_ROOT_PATH=/hf/v1 
+# SERVER_ROOT_PATH=/hf/v1
 # ENV LITELLM_LOG=DEBUG
 ENV STORE_MODEL_IN_DB=true
 ENV TZ=Asia/Shanghai OPENAI_API_KEY=any SERVER_ROOT_PATH=/v1 CONFIG_FILE_PATH=/app/config.yaml
@@ -23,10 +23,10 @@ ENV TZ=Asia/Shanghai OPENAI_API_KEY=any SERVER_ROOT_PATH=/v1 CONFIG_FILE_PATH=/a
 COPY ./litellm_config.yaml /app/config.yaml
 EXPOSE 7860
 
-ENTRYPOINT ["litellm"] 
+ENTRYPOINT ["litellm"]
 
 # "--num_workers", "8"
 # env CONFIG_FILE_PATH=/app/config.yaml
 # CMD [ "--config", "/app/config.yaml", "--port", "7860", "--num_workers", "2" ]
 
-CMD [ "--port", "7860", "--num_workers", "8" ]
+CMD [ "--port", "7860", "--num_workers", "4" ]

litellm_config-bk.yaml

@@ -0,0 +1,112 @@
+model_list:
+  # - model_name: "anthropic/*"
+    # litellm_params:
+      # model: "openrouter/qwen/qwen3-coder" # Qwen/Qwen3-Coder-480B-A35B-Instruct
+      # max_tokens: 65536
+      # repetition_penalty: 1.05
+      # temperature: 0.7
+      # top_k: 20
+      # top_p: 0.8
+
+  # OK curl, ccr not OK, ccapi use litellm-v0 OK, anthropic-curl OK
+  - model_name: v0-a
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY1
+    model_info:
+      max_tokens: 200_000
+      id: v0/v0-1.5-md
+      additionalProp1:
+        info: v0-bug-team
+  - model_name: v0-b
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY2
+  - model_name: v0-c
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY3
+  - model_name: v0
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY1
+    model_info:
+      max_tokens: 200_000
+      id: v0/v0-1.5-md
+      additionalProp1:
+        info: v0-bug-team
+  - model_name: v0
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY2
+  - model_name: v0
+    litellm_params:
+      model: v0/v0-1.5-md
+      api_base: https://api.v0.dev/v1
+      api_key: os.environ/V0_API_KEY3
+
+  # https://elysiver.h-e.top/v1 sk-JE5JTfpHyV2Ri648gr1dJY9BhIhOPtD3iOd0F1vuYoXHCIhH kimi-k2.5
+  - model_name: kimi-k2.5-elysiver
+    litellm_params:
+      model: openai/kimi-k2.5
+      api_base: https://elysiver.h-e.top/v1
+      api_key: os.environ/ELY_API_KEY
+  - model_name: kimi-k2.5
+    litellm_params:
+      model: openai/kimi-k2.5
+      api_base: https://elysiver.h-e.top/v1
+      api_key: os.environ/ELY_API_KEY
+  - model_name: gemini-2.5-flash-lite-elysiver
+    litellm_params:
+      model: openai/gemini-2.5-flash-lite
+      api_base: https://elysiver.h-e.top/v1
+      api_key: os.environ/ELY_API_KEY
+  - model_name: gemini-2.5-flash-lite
+    litellm_params:
+      model: openai/gemini-2.5-flash-lite
+      api_base: https://elysiver.h-e.top/v1
+      api_key: os.environ/ELY_API_KEY
+
+  - model_name: claude-sonnet-4
+    litellm_params:
+      model: openrouter/claude-sonnet-4
+      api_base: https://aidrouter.qzz.io/v1
+      api_key: os.environ/AIDROUTER_API_KEY
+  - model_name: claude-opus-4-6
+    litellm_params:
+      model: openrouter/claude-opus-4-6
+      api_base: https://aidrouter.qzz.io/v1
+      api_key: os.environ/AIDROUTER_API_KEY
+  - model_name: gemini-3-flash-preview
+    litellm_params:
+      model: openrouter/gemini-3-flash-preview
+      api_base: https://aidrouter.qzz.io/v1
+      api_key: os.environ/AIDROUTER_API_KEY
+
+general_settings:
+  # master_key: "sk-1234" # Disabled for easy testing
+  # master_key: ${LITELLM_MASTER_KEY}
+  master_key: os.environ/LITELLM_MASTER_KEY
+
+# litellm --config parent_config.yaml --detailed_debug/--debug
+# os.environ["LITELLM_LOG"] = "INFO" os.environ["LITELLM_LOG"] = "DEBUG"
+# https://docs.litellm.ai/docs/proxy/config_settings
+litellm_settings:
+  # set_verbose: true  # deprecated, use `os.environ['LITELLM_LOG'] = 'DEBUG'
+  request_timeout: 180
+  drop_params: true
+  fallbacks:
+    - v0: [gemini-2.5-flash-lite,gemini-2.5-flash]
+    - kimi-k2.5: [gemini-2.5-flash-lite]
+    # - gemini-2.5-flash: [gemini-2.5-flash-lite]
+router_settings:
+  model_group_alias:
+    gpt-4o: gemini-2.5-flash-lite
+    gpt-4.1-mini: gemini-2.5-flash-lite
+    gpt-5-codex: kimi-k2.5
+    gpt-5.1-codex: kimi-k2.5

litellm_config.yaml

@@ -103,10 +103,14 @@ litellm_settings:
   fallbacks:
     - v0: [gemini-2.5-flash-lite,gemini-2.5-flash]
     - kimi-k2.5: [gemini-2.5-flash-lite]
+    - claude-4.6-sonnet: [openrouter/claude-4.6-sonnet,openrouter/claude-4.5-sonnet,v0]
+    - claude-4.5-sonnet: [openrouter/claude-4.5-sonnet,v0]
+
     # - gemini-2.5-flash: [gemini-2.5-flash-lite]
+
 router_settings:
   model_group_alias:
     gpt-4o: gemini-2.5-flash-lite
     gpt-4.1-mini: gemini-2.5-flash-lite
-    gpt-5-codex: kimi-k2.5
-    gpt-5.1-codex: kimi-k2.5
+    gpt-5-codex: claude-4.5-sonnet
+    gpt-5.1-codex: claude-4.5-sonnet