updated claude-code docs and deployment faq

2026-08-13 10:23:08 +00:00 · 2025-08-19 16:52:46 -04:00
parent 195ea6515e
commit 2edcc51e57
2 changed files with 72 additions and 50 deletions
@@ -1010,5 +1010,19 @@ User-agent: *
 Disallow: /
 ```

+## Deployment FAQ
+
+### Database Support
+
+**Q: Is Postgres the only supported database, or do you support other ones (like Mongo)?**
+
+A: We explored MySQL but that was hard to maintain and led to bugs for customers. Currently, PostgreSQL is our primary supported database for production deployments.
+
+### Database Downtime Handling
+
+**Q: If there is Postgres downtime, how does LiteLLM react? Does it fail-open or is there API downtime?**
+
+A: You can gracefully handle DB unavailability if it's on your VPC. See our production guide for more details: [Gracefully Handle DB Unavailability](https://docs.litellm.ai/docs/proxy/prod#6-if-running-litellm-on-vpc-gracefully-handle-db-unavailability)
+


@@ -4,11 +4,11 @@ import TabItem from '@theme/TabItem';

 # Claude Code

-This tutorial shows how to call the Responses API models like `codex-mini` and `o3-pro` from the Claude Code endpoint on LiteLLM.
+This tutorial shows how to call Claude models through LiteLLM proxy from Claude Code.

 :::info 

-This tutorial is based on [Anthropic's official LiteLLM configuration documentation](https://docs.anthropic.com/en/docs/claude-code/llm-gateway#litellm-configuration). This integration allows you to use any LiteLLM supported model through Claude Code.
+This tutorial is based on [Anthropic's official LiteLLM configuration documentation](https://docs.anthropic.com/en/docs/claude-code/llm-gateway#litellm-configuration). This integration allows you to use any LiteLLM supported model through Claude Code with centralized authentication, usage tracking, and cost controls.

 :::

@@ -31,19 +31,18 @@ Create a secure configuration using environment variables:

 ```yaml
 model_list:
-  # Responses API models
-  - model_name: codex-mini    
+  # Claude models
+  - model_name: claude-3-5-sonnet-20241022    
    litellm_params:
-      model: openai/codex-mini
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://api.openai.com/v1
+      model: anthropic/claude-3-5-sonnet-20241022
+      api_key: os.environ/ANTHROPIC_API_KEY
  
-  - model_name: o3-pro
+  - model_name: claude-3-5-haiku-20241022
    litellm_params:
-      model: openai/o3-pro
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://api.openai.com/v1
+      model: anthropic/claude-3-5-haiku-20241022
+      api_key: os.environ/ANTHROPIC_API_KEY

+  
 litellm_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
 ```
@@ -51,7 +50,7 @@ litellm_settings:
 Set your environment variables:

 ```bash
-export OPENAI_API_KEY="your-openai-api-key"
+export ANTHROPIC_API_KEY="your-anthropic-api-key"
 export LITELLM_MASTER_KEY="sk-1234567890"  # Generate a secure key
 ```

@@ -72,31 +71,43 @@ curl -X POST http://0.0.0.0:4000/v1/messages \
 -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
 -H "Content-Type: application/json" \
 -d '{
-    "model": "codex-mini",
+    "model": "claude-3-5-sonnet-20241022",
+    "max_tokens": 1000,
    "messages": [{"role": "user", "content": "What is the capital of France?"}]
 }'
 ```

 ### 4. Configure Claude Code

-Setup Claude Code to use your LiteLLM proxy:
+#### Method 1: Unified Endpoint (Recommended)
+
+Configure Claude Code to use LiteLLM's unified endpoint:

 ```bash
 export ANTHROPIC_BASE_URL="http://0.0.0.0:4000"
 export ANTHROPIC_AUTH_TOKEN="$LITELLM_MASTER_KEY"
 ```

-### 5. Use Claude Code
+#### Method 2: Provider-specific Pass-through Endpoint

-Start Claude Code with any configured model:
+Alternatively, use the Anthropic pass-through endpoint:

 ```bash
-# Use Responses API models
-claude --model codex-mini
-claude --model o3-pro
+export ANTHROPIC_BASE_URL="http://0.0.0.0:4000/anthropic"
+export ANTHROPIC_AUTH_TOKEN="$LITELLM_MASTER_KEY"
+```

-# Or use the latest model alias
-claude --model codex-mini-latest
+### 5. Use Claude Code
+
+Start Claude Code and it will automatically use your configured models:
+
+```bash
+# Claude Code will use the models configured in your LiteLLM proxy
+claude
+
+# Or specify a model if you have multiple configured
+claude --model claude-3-5-sonnet-20241022
+claude --model claude-3-5-haiku-20241022
 ```

 Example conversation:
@@ -112,7 +123,8 @@ Common issues and solutions:

 **Authentication errors:**
 - Verify your environment variables are set: `echo $LITELLM_MASTER_KEY`
- Check that your OpenAI API key is valid and has sufficient credits
+- Check that your API keys are valid and have sufficient credits
+- Ensure the `ANTHROPIC_AUTH_TOKEN` matches your LiteLLM master key

 **Model not found:**
 - Ensure the model name in Claude Code matches exactly with your `config.yaml`
@@ -123,48 +135,44 @@ Common issues and solutions:
 Expand your configuration to support multiple providers and models:

 <Tabs>
-<TabItem value="responses-plus" label="Responses + Standard Models">
+<TabItem value="multi-provider" label="Multi-Provider Setup">

 ```yaml
 model_list:
-  # Responses API models
-  - model_name: codex-mini
-    litellm_params:
-      model: openai/codex-mini
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://api.openai.com/v1
-  
-  - model_name: o3-pro
-    litellm_params:
-      model: openai/o3-pro
-      api_key: os.environ/OPENAI_API_KEY
-      api_base: https://api.openai.com/v1
-
-  # Standard models
-  - model_name: gpt-4o
-    litellm_params:
-      model: openai/gpt-4o
-      api_key: os.environ/OPENAI_API_KEY
-
-  - model_name: claude-3-5-sonnet
+  # Anthropic models
+  - model_name: claude-3-5-sonnet-20241022
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20241022
      api_key: os.environ/ANTHROPIC_API_KEY
+  
+  - model_name: claude-3-5-haiku-20241022
+    litellm_params:
+      model: anthropic/claude-3-5-haiku-20241022
+      api_key: os.environ/ANTHROPIC_API_KEY
+
+  # AWS Bedrock
+  - model_name: claude-bedrock
+    litellm_params:
+      model: bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0
+      aws_access_key_id: os.environ/AWS_ACCESS_KEY_ID
+      aws_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY
+      aws_region_name: us-east-1

 litellm_settings:
  master_key: os.environ/LITELLM_MASTER_KEY
 ```

-Switch between models seamlessly:
+Use different models based on your needs:

 ```bash
-# Use Responses API models for advanced reasoning
-claude --model o3-pro
-claude --model codex-mini
+# Use Claude for complex reasoning
+claude --model claude-3-5-sonnet-20241022

-# Use standard models for general tasks
-claude --model gpt-4o
-claude --model claude-3-5-sonnet
+# Use Haiku for fast responses
+claude --model claude-3-5-haiku-20241022
+
+# Use Bedrock deployment
+claude --model claude-bedrock
 ```

 </TabItem>