scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 115

docs(azure_ai.md): document anthropic model usage on azure ai

Browse source
This commit is contained in:
Krrish Dholakia 2025-12-01 14:06:31 -08:00
parent 7a46f3a083
commit c9afb86994
1 changed files with 78 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

79
docs/my-website/docs/providers/azure_ai.md
View file

@ -312,6 +312,82 @@ LiteLLM supports **ALL** azure ai models. Here's a few examples:
| mistral-large-latest | `completion(model="azure_ai/mistral-large-latest", messages)` |
| AI21-Jamba-Instruct | `completion(model="azure_ai/ai21-jamba-instruct", messages)` |
## Usage - Azure Anthropic (Azure Foundry Claude)
LiteLLM funnels Azure Claude deployments through the `azure_ai/` provider so Claude Opus models on Azure Foundry keep working with Tool Search, Effort, streaming, and the rest of the advanced feature set. Point `AZURE_AI_API_BASE` to `https://<resource>.services.ai.azure.com/anthropic` (LiteLLM appends `/v1/messages` automatically) and authenticate with `AZURE_AI_API_KEY` or an Azure AD token.
<Tabs>
<TabItem value="sdk" label="LiteLLM Python SDK">
```python
import os
from litellm import completion
# Configure Azure credentials
os.environ["AZURE_AI_API_KEY"] = "your-azure-ai-api-key"
os.environ["AZURE_AI_API_BASE"] = "https://my-resource.services.ai.azure.com/anthropic"
response = completion(
model="azure_ai/claude-opus-4-1",
messages=[{"role": "user", "content": "Explain how Azure Anthropic hosts Claude Opus differently from the public Anthropic API."}],
max_tokens=1200,
temperature=0.7,
stream=True,
)
for chunk in response:
if chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
```
</TabItem>
<TabItem value="proxy" label="LiteLLM Proxy">
**1. Set environment variables**
```bash
export AZURE_AI_API_KEY="your-azure-ai-api-key"
export AZURE_AI_API_BASE="https://my-resource.services.ai.azure.com/anthropic"
```
**2. Configure the proxy**
```yaml
model_list:
- model_name: claude-4-azure
litellm_params:
model: azure_ai/claude-opus-4-1
api_key: os.environ/AZURE_AI_API_KEY
api_base: os.environ/AZURE_AI_API_BASE
```
**3. Start LiteLLM**
```bash
litellm --config /path/to/config.yaml
```
**4. Test the Azure Claude route**
```bash
curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer $LITELLM_KEY' \
--data '{
"model": "claude-4-azure",
"messages": [
{
"role": "user",
"content": "How do I use Claude Opus 4 via Azure Anthropic in LiteLLM?"
}
],
"max_tokens": 1024
}'
```
</TabItem>
</Tabs>
## Rerank Endpoint
@ -397,4 +473,5 @@ curl http://0.0.0.0:4000/rerank \
```
</TabItem>
</Tabs>
</Tabs>