🟡 Adding Azure AI Foundry Clients
# questionst
thegamedefault
11/22/2025, 4:23 AMHow to add Azure AI foundary clients ?
I can see azure now provides openai response api models as well.
thegamedefault
11/22/2025, 4:31 AMhttps://{resource.name}-eastus2.cognitiveservices.azure.com/openai/responses?api-version=2025-04-01-preview
a
Antonio Sarosi (BAML 🐑)
11/22/2025, 5:12 PMThere are some docs [here](https://docs.boundaryml.com/ref/llm-client-providers/azure-ai-foundary).
But yes you're on the right track, you use OpenAI API format:
Copy code
ts
client<llm> AzureAiFoundary {
provider "openai-generic"
options {
base_url "https://RESOURCE_NAME.REGION.models.ai.azure.com"
api_key env.MY_API_KEY
}
}t
thegamedefault
11/23/2025, 7:12 AMTried with both full url and base url getting
Copy code
Unspecified error code: 404 Request failed with status code: 404 Not Found,
{"error":{"code":"404","message": "Resource not found"}}
Request options: {}thegamedefault
11/23/2025, 7:55 AM Copy code
client<llm> AzureOpenAI5_1_Chat {
provider "azure-openai"
options {
base_url "https://{{resource}}-eastus2.cognitiveservices.azure.com/openai/deployments/gpt-5.1-chat"
api_version "2024-12-01-preview"
api_key env.AZURE_OPENAI_API_KEY
// max_completion_tokens 4096
}
} Copy code
Unspecified error code: 400 Request failed with status code: 400 Bad Request,
{
"error": {
"message": "Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.",
"type": "invalid_request_error",
"param": "max_tokens",
"code": "unsupported_parameter"
}
}
Request options: {"max_tokens":4096}