const response = await env.AI.run(
  'xai/grok-4.5',
  {
    max_completion_tokens: 8192,
    messages: [
      {
        content:
          'Find and fix the bug, then explain it: function median(a){a.sort();return a[a.length/2]}',
        role: 'user',
      },
    ],
    reasoning_effort: 'low',
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "xai/grok-4.5",
  "max_completion_tokens": 8192,
  "messages": [
    {
      "content": "Find and fix the bug, then explain it: function median(a){a.sort();return a[a.length/2]}",
      "role": "user"
    }
  ],
  "reasoning_effort": "low"
}'

```js
function median(a) {
  if (!Array.isArray(a) || a.length === 0) return undefined;
  const sorted = a.slice().sort((x, y) => x - y); // copy + numeric sort
  const mid = Math.floor(sorted.length / 2);
  return sorted.length % 2
    ? sorted[mid]
    : (sorted[mid - 1] + sorted[mid]) / 2;
}
```

**Bugs fixed**
1. **Default `sort()` is lexicographic** (e.g. `[10, 2, 3]` → `["10","2","3"]`). A numeric comparator is required.
2. **`a[a.length/2]` is wrong**:
   - For odd length (e.g. 5) you get a float index `2.5` → `undefined`.
   - For even length the conventional median is the average of the two central elements, not a single one.
3. **In-place mutation** – `sort()` changes the caller’s array; a shallow copy avoids that.
4. Empty / non-array input is now handled safely.

{
  "id": "bb92a233-a9ac-9a94-bdf1-6e5e6a14c060",
  "object": "chat.completion",
  "created": 1784118539,
  "model": "grok-4.5",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "```js\nfunction median(a) {\n  if (!Array.isArray(a) || a.length === 0) return undefined;\n  const sorted = a.slice().sort((x, y) => x - y); // copy + numeric sort\n  const mid = Math.floor(sorted.length / 2);\n  return sorted.length % 2\n    ? sorted[mid]\n    : (sorted[mid - 1] + sorted[mid]) / 2;\n}\n```\n\n**Bugs fixed**\n1. **Default `sort()` is lexicographic** (e.g. `[10, 2, 3]` → `[\"10\",\"2\",\"3\"]`). A numeric comparator is required.\n2. **`a[a.length/2]` is wrong**:\n   - For odd length (e.g. 5) you get a float index `2.5` → `undefined`.\n   - For even length the conventional median is the average of the two central elements, not a single one.\n3. **In-place mutation** – `sort()` changes the caller’s array; a shallow copy avoids that.\n4. Empty / non-array input is now handled safely.",
        "reasoning_content": "The user wants me to find and fix the bug in this function: function median(a){a.sort();return a[a.length/2]}\nThe bug is that `a.length/2` coerces to an integer index (so for odd-length arrays it actually returns the element at `floor(length/2)`, not the true middle), and the default string sort makes numeric data come out wrong. It also mutates the caller’s array.",
        "refusal": null
      }
    }
  ],
  "service_tier": "default",
  "system_fingerprint": "fp_a39489019fa99b6e",
  "usage": {
    "prompt_tokens": 233,
    "completion_tokens": 250,
    "total_tokens": 1115,
    "prompt_tokens_details": {
      "text_tokens": 233,
      "audio_tokens": 0,
      "image_tokens": 0,
      "cached_tokens": 128
    },
    "completion_tokens_details": {
      "reasoning_tokens": 632,
      "audio_tokens": 0,
      "accepted_prediction_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "cost_in_usd_ticks": 55660000,
    "num_sources_used": 0
  },
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

const response = await env.AI.run(
  'xai/grok-4.5',
  {
    messages: [{ content: 'Explain the concept of recursion with a simple example.', role: 'user' }],
    stream: true,
    stream_options: { include_usage: true },
  },
)
console.log(response)

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "xai/grok-4.5",
  "messages": [
    {
      "content": "Explain the concept of recursion with a simple example.",
      "role": "user"
    }
  ],
  "stream": true,
  "stream_options": {
    "include_usage": true
  }
}'

**Recursion** is a programming technique where a function calls itself to solve a smaller instance of the same problem, until it reaches a simple stopping condition.

### Core Idea
- Break a problem into smaller subproblems of the same type.
- Each recursive call works on a reduced version of the input.
- Eventually hit a **base case** that returns a value without further calls (this prevents infinite recursion).
- Combine the results as the calls unwind.

Without a proper base case, recursion continues forever (or until the call stack overflows).

### Simple Example: Factorial
The factorial of a non-negative integer \( n \) (written \( n! \)) is:

- \( 0! = 1 \) and \( 1! = 1 \)
- \( n! = n \times (n-1)! \) for \( n > 1 \)

**Python implementation:**

```python
def factorial(n):
    # Base case: stops the recursion
    if n == 0 or n == 1:
        return 1
    # Recursive case: calls itself with a smaller argument
    else:
        return n * factorial(n - 1)
```

**How it works for `factorial(5)`:**

1. `factorial(5)` → \( 5 \times \) `factorial(4)`
2. `factorial(4)` → \( 4 \times \) `factorial(3)`
3. `factorial(3)` → \( 3 \times \) `factorial(2)`
4. `factorial(2)` → \( 2 \times \) `factorial(1)`
5. `factorial(1)` → returns `1` (base case)

Now the calls return and multiply:

- \( 2 \times 1 = 2 \)
- \( 3 \times 2 = 6 \)
- \( 4 \times 6 = 24 \)
- \( 5 \times 24 = 120 \)

Result: `120`

### Why This Works
Each call reduces \( n \) by 1, guaranteed to eventually hit the base case. The multiplications happen on the way back up the call stack.

### Quick Tips
- Always define a clear base case first.
- Ensure every recursive path moves toward that base case.
- Recursion is elegant for problems with natural recursive structure (trees, divide-and-conquer, factorial, Fibonacci, etc.), but deep recursion can cause stack overflows—iteration or tail-call optimization can be alternatives when needed.

This pattern (base case + recursive case that shrinks the problem) is the essence of recursion.

[
  {
    "id": "b2ed7fb2-3e57-96e3-9a6c-464dd11745eb",
    "object": "chat.completion.chunk",
    "created": 1784118545,
    "model": "grok-4.5",
    "choices": [
      {
        "index": 0,
        "delta": {
          "reasoning_content": "The",
          "role": "assistant"
        }
      }
    ],
    "system_fingerprint": "fp_a39489019fa99b6e",
    "service_tier": "default"
  },
  {
    "id": "b2ed7fb2-3e57-96e3-9a6c-464dd11745eb",
    "object": "chat.completion.chunk",
    "created": 1784118545,
    "model": "grok-4.5",
    "choices": [
      {
        "index": 0,
        "delta": {
          "reasoning_content": " user"
        }
      }
    ],
    "system_fingerprint": "fp_a39489019fa99b6e",
    "service_tier": "default"
  },
  "... 559 more chunks omitted ...",
  {
    "id": "b2ed7fb2-3e57-96e3-9a6c-464dd11745eb",
    "object": "chat.completion.chunk",
    "created": 1784118551,
    "model": "grok-4.5",
    "choices": [],
    "usage": {
      "prompt_tokens": 216,
      "completion_tokens": 544,
      "total_tokens": 1040,
      "prompt_tokens_details": {
        "text_tokens": 216,
        "audio_tokens": 0,
        "image_tokens": 0,
        "cached_tokens": 128
      },
      "completion_tokens_details": {
        "reasoning_tokens": 280,
        "audio_tokens": 0,
        "accepted_prediction_tokens": 0,
        "rejected_prediction_tokens": 0
      },
      "num_sources_used": 0,
      "cost_in_usd_ticks": 51840000
    },
    "system_fingerprint": "fp_a39489019fa99b6e",
    "service_tier": "default"
  }
]

const response = await env.AI.run(
  'xai/grok-4.5',
  {
    messages: [
      {
        content: [
          {
            image_url: { url: 'https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png' },
            type: 'image_url',
          },
          {
            text: 'Describe the person in this image and their surroundings in one sentence.',
            type: 'text',
          },
        ],
        role: 'user',
      },
    ],
  },
)
console.log(response)