chore: import upstream snapshot with attribution

examples/provider-aiml-api/README.md

@@ -0,0 +1,40 @@
+# provider-aiml-api (AI/ML API Provider)
+
+This example shows how to use AI/ML API to compare different language models on a fun task - telling jokes!
+
+AI/ML API provides access to 300+ models through a single API key, making it easy to compare models from different providers.
+
+## Setup
+
+1. Get your API key from [AI/ML API](https://aimlapi.com)
+
+2. Set your API key:
+
+   ```bash
+   export AIML_API_KEY=your_api_key_here
+   ```
+
+3. Run the evaluation:
+   ```bash
+   npx promptfoo@latest eval
+   ```
+
+## What this example does
+
+This example compares three different models:
+
+- **DeepSeek R1** - Advanced reasoning model
+- **GPT-4.1 Mini** - Fast and cost-effective
+- **Claude 4 Sonnet** - Balanced performance
+
+The models are asked to tell jokes about different topics, and we evaluate:
+
+- Whether the joke contains relevant keywords
+- Whether the joke is actually funny (using an LLM judge)
+
+You can run this example with:
+
+```bash
+npx promptfoo@latest init --example provider-aiml-api
+cd provider-aiml-api
+```

examples/provider-aiml-api/promptfooconfig.yaml

@@ -0,0 +1,27 @@
+# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
+description: Compare AI models with AI/ML API
+
+providers:
+  - aimlapi:chat:deepseek-r1
+  - aimlapi:chat:gpt-4.1-mini
+  - aimlapi:chat:claude-4-sonnet
+
+prompts:
+  - 'Tell me a joke about {{topic}}'
+
+tests:
+  - vars:
+      topic: 'programming'
+    assert:
+      - type: contains-any
+        value: ['code', 'bug', 'debug', 'programmer', 'developer', 'software']
+      - type: llm-rubric
+        value: 'Is this actually funny?'
+
+  - vars:
+      topic: 'artificial intelligence'
+    assert:
+      - type: contains-any
+        value: ['AI', 'robot', 'machine', 'learning', 'neural']
+      - type: llm-rubric
+        value: 'Does the joke make sense and is it appropriate?'