promptfoo--promptfoo/examples/azure-mai/promptfooconfig.yaml

# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
description: Microsoft MAI models on Azure AI Foundry (Foundry Models sold by Azure)

# Microsoft's first-party "MAI" model family. Image models (MAI-Image-2.5 and
# friends, currently Preview) use a Microsoft-managed `/mai/v1/images` route and
# run through the dedicated `azure:image:<deployment>` provider — that's what this
# example uses. Text/reasoning models (MAI-DS-R1, MAI-Thinking-1, MAI-Code-1-Flash)
# use the standard chat-completions API via `azure:chat:<deployment>`, but have
# limited availability today (see the commented chat provider below).
#
# Setup:
#   1. Deploy an MAI image model to a Microsoft Foundry (AIServices) resource:
#        az cognitiveservices account deployment create \
#          --name <RESOURCE> --resource-group <RG> \
#          --deployment-name mai-image-2-5 \
#          --model-name MAI-Image-2.5 --model-format Microsoft \
#          --model-version 2026-06-02 --sku-name GlobalStandard --sku-capacity 1
#   2. Point promptfoo at the resource's *.services.ai.azure.com endpoint:
#        export AZURE_API_HOST=<RESOURCE>.services.ai.azure.com
#        export AZURE_API_KEY=<key>            # or use `az login` (Entra ID)
#   3. Run:  promptfoo eval --no-cache

prompts:
  - '{{prompt}}'

providers:
  - id: azure:image:mai-image-2-5
    label: MAI-Image-2.5
    config:
      # `model` is used only for cost reporting; Azure deployment names can't
      # contain the dot in "MAI-Image-2.5", so name the model id explicitly.
      model: MAI-Image-2.5
      width: 1024
      height: 1024

  # Reasoning/chat MAI models use the standard chat provider, but aren't deployable
  # on most subscriptions yet (MAI-DS-R1 is deprecated; MAI-Thinking-1 and
  # MAI-Code-1-Flash are private preview). Uncomment once your subscription can
  # deploy one:
  # - id: azure:chat:mai-thinking-1
  #   label: MAI-Thinking-1
  #   config:
  #     max_completion_tokens: 2048

tests:
  - vars:
      prompt: A photorealistic red cube on a clean white background, studio lighting
    assert:
      # The provider returns a base64 PNG. promptfoo stores large base64 media as
      # a blob reference (promptfoo://blob/...) before assertions run, so accept
      # either the blob ref or an inline data URL.
      - type: javascript
        value: |
          return typeof output === 'string' &&
            (output.startsWith('promptfoo://blob/') || output.startsWith('data:image/'));

  - vars:
      prompt: An isometric illustration of a cozy reading nook with warm lighting
    assert:
      - type: javascript
        value: |
          return typeof output === 'string' &&
            (output.startsWith('promptfoo://blob/') || output.startsWith('data:image/'));