Update LiteLLM models

.claude/commands/update-litellm-models.md

@@ -0,0 +1,80 @@
+---
+description: Update LiteLLM config/config.yaml to use the latest model versions from each provider
+---
+
+Update the LiteLLM model configuration to use the latest available model IDs, removing outdated versions.
+
+## Config file location
+
+Read the current config via:
+```bash
+docker exec litellm cat /app/config.yaml
+```
+
+The source file is at `docker/ai/litellm/config/config.yaml`.
+
+## Step 1: Look up latest models per provider (run searches in parallel)
+
+Search the web for the current model IDs for each provider present in the config:
+
+- **Anthropic**: Search "Anthropic Claude latest models API model IDs" → check https://docs.anthropic.com/en/docs/about-claude/models/overview
+- **OpenAI**: Search "OpenAI latest models API model IDs" → check https://platform.openai.com/docs/models
+- **Google Gemini**: Search "Google Gemini latest models API model IDs" → check https://ai.google.dev/gemini-api/docs/models
+- **OpenRouter (Meta Llama)**: Search "Meta Llama latest models openrouter model IDs"
+- **OpenRouter (DeepSeek)**: Search "DeepSeek latest models openrouter model IDs"
+- **OpenRouter (xAI Grok)**: Search "xAI Grok latest models openrouter model IDs"
+
+For each provider, identify:
+1. The **latest stable** model ID (not preview/experimental unless that's the only option)
+2. Whether the currently configured model has been **superseded** by a newer release
+3. The **exact API model ID string** to use in LiteLLM params
+
+## Step 2: Determine what to change
+
+For each model in the config, decide:
+- **Update**: A newer stable version exists → update the `model_name` key and `litellm_params.model` value
+- **Keep**: Still the latest stable model → no change needed
+- **Remove**: Superseded by a newer model already listed in the same config (avoid duplicates)
+
+Preserve without changes:
+- Local Ollama models (`ollama_chat/...`) — these are managed separately
+- The overall YAML structure, comments, and provider groupings
+- `api_key` and `api_base` references
+
+## Step 3: Update the file
+
+Write the updated config using:
+```bash
+tee "$(git rev-parse --show-toplevel)/docker/ai/litellm/config/config.yaml" > /dev/null << 'EOF'
+<updated content>
+EOF
+```
+
+Also update `router_settings.fallbacks` to reflect any renamed models.
+
+## Step 4: Verify
+
+Confirm the file was written correctly:
+```bash
+docker exec litellm cat /app/config.yaml
+```
+
+## LiteLLM model ID format reference
+
+| Provider               | LiteLLM format                     |
+| ---------------------- | ---------------------------------- |
+| Anthropic (direct)     | `anthropic/<model-id>`             |
+| OpenAI (direct)        | `openai/<model-id>`                |
+| Google Gemini (direct) | `gemini/<model-id>`                |
+| OpenRouter             | `openrouter/<provider>/<model-id>` |
+| Ollama (local)         | `ollama_chat/<model-name>`         |
+
+Example: `openrouter/meta-llama/llama-4-maverick`, `anthropic/claude-sonnet-4-6`
+
+## Summary output
+
+After completing the update, show a table of what changed:
+
+| Model | Old ID | New ID | Action                   |
+| ----- | ------ | ------ | ------------------------ |
+| ...   | ...    | ...    | Updated / Removed / Kept |

docker/ai/litellm/config/config.yaml

@@ -20,24 +20,19 @@ model_list:
   #  Create API key: https://platform.claude.com/settings/keys
   #  Buy credits: https://platform.claude.com/settings/billing
 
-  - model_name: claude-sonnet-4-0                # RECEIVED MODEL NAME
+  - model_name: claude-sonnet-4-6                # RECEIVED MODEL NAME
     litellm_params:                              # All params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input
-      model: anthropic/claude-sonnet-4-0         # MODEL NAME sent to `litellm.completion()`
+      model: anthropic/claude-sonnet-4-6         # MODEL NAME sent to `litellm.completion()`
       api_key: "os.environ/ANTHROPIC_API_KEY"    # Does os.getenv("ANTHROPIC_API_KEY")
 
-  - model_name: claude-sonnet-4-5
+  - model_name: claude-opus-4-6
     litellm_params:
-      model: anthropic/claude-sonnet-4-5
-      api_key: "os.environ/ANTHROPIC_API_KEY"
-
-  - model_name: claude-opus-4-5
-    litellm_params:
-      model: anthropic/claude-opus-4-5
+      model: anthropic/claude-opus-4-6
       api_key: "os.environ/ANTHROPIC_API_KEY"
 
   - model_name: claude-haiku-4-5
     litellm_params:
-      model: anthropic/claude-haiku-4-5
+      model: anthropic/claude-haiku-4-5-20251001
       api_key: "os.environ/ANTHROPIC_API_KEY"
 
   # --- Via OpenAI
@@ -78,16 +73,16 @@ model_list:
   #  Create API Key: https://openrouter.ai/settings/keys
   #  Buy credits: https://openrouter.ai/settings/credits
 
-  # https://openrouter.ai/openai/openai/gpt-4o
-  - model_name: gpt-4o
+  # https://openrouter.ai/openai/gpt-4.1
+  - model_name: gpt-4.1
     litellm_params:
-      model: openrouter/openai/gpt-4o
+      model: openrouter/openai/gpt-4.1
       api_key: "os.environ/OPENROUTER_API_KEY"
 
-  # https://openrouter.ai/openai/gpt-4o-mini
-  - model_name: gpt-4o-mini
+  # https://openrouter.ai/openai/gpt-4.1-mini
+  - model_name: gpt-4.1-mini
     litellm_params:
-      model: openrouter/openai/gpt-4o-mini
+      model: openrouter/openai/gpt-4.1-mini
       api_key: "os.environ/OPENROUTER_API_KEY"
 
   # https://openrouter.ai/openai/o4-mini-high
@@ -96,16 +91,16 @@ model_list:
       model: openrouter/openai/o4-mini-high
       api_key: "os.environ/OPENROUTER_API_KEY"
 
-  # https://openrouter.ai/meta-llama/llama-3.3-70b-instruct
-  - model_name: llama-3.3-70b-instruct
+  # https://openrouter.ai/meta-llama/llama-4-maverick
+  - model_name: llama-4-maverick
     litellm_params:
-      model: openrouter/meta-llama/llama-3.3-70b-instruct
+      model: openrouter/meta-llama/llama-4-maverick
       api_key: "os.environ/OPENROUTER_API_KEY"
 
-  # https://openrouter.ai/deepseek/deepseek-r1-distill-llama-70b
-  - model_name: deepseek-r1-distill-llama-70b
+  # https://openrouter.ai/deepseek/deepseek-v3.2
+  - model_name: deepseek-v3.2
     litellm_params:
-      model: openrouter/deepseek/deepseek-r1-distill-llama-70b
+      model: openrouter/deepseek/deepseek-v3.2
       api_key: "os.environ/OPENROUTER_API_KEY"
 
   # https://openrouter.ai/deepseek/deepseek-r1
@@ -141,8 +136,8 @@ model_list:
 router_settings:
   fallbacks:
     - gpt-5:
-        - gpt-4o
+        - gpt-4.1
     - gpt-5-mini:
-        - gpt-4o-mini
+        - gpt-4.1-mini
     - ollama-mac-mistral:
         - ollama-local-phi