GPT-4.1·续

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "logprobs": null,
      "message": {
        "annotations": [],
        "content": "Detective Lila Maren knelt beside the wrought-iron fence, her breath misting in the pale dawn light. The alley was quiet, save for the distant hum of the city waking. She scanned the scuffed cobblestones, expecting the usual—a cigarette butt, perhaps, or a scrap of torn fabric. Instead, nestled in a shallow puddle, she found a single red chess pawn, oddly pristine amid the grime.\n\nLila lifted it with gloved fingers, turning it over as she studied its glossy sheen. No markings. No blood. Just a chess piece, out of place and glinting like a secret. She frowned, recalling the message scrawled on the victim’s mirror upstairs: “Checkmate.” The game, it seemed, was just beginning.",
        "refusal": null,
        "role": "assistant"
      }
    }
  ],
  "created": 1776470819,
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "id": "chatcmpl-DVnV5b5ltpItctts03EY2jcCCWLEe",
  "model": "gpt-4.1-2025-04-14",
  "object": "chat.completion",
  "service_tier": "default",
  "system_fingerprint": "fp_7a56a8eabf",
  "usage": {
    "completion_tokens": 159,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens": 20,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    },
    "total_tokens": 179
  }
}

</details>

<details>

<summary>Streaming Response — Enable streaming for real-time output</summary>

const response = await env.AI.run(
  'openai/gpt-4.1',
  {
    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": "openai/gpt-4.1",
  "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 problem. Each time the function calls itself, it breaks the problem down into smaller subproblems. For recursion to stop, a **base case** (or termination condition) is required.

**Simple Example: Calculating Factorial**

The **factorial** of a non-negative integer `n` (written as `n!`) is the product of all positive integers less than or equal to `n`.

**Mathematically:**
- `n! = n × (n-1) × (n-2) × ... × 1`
- By definition, `0! = 1`

**Recursive Definition:**
- If `n == 0`, then `factorial(n) = 1`   (base case)
- If `n > 0`, then `factorial(n) = n × factorial(n-1)`  (recursive case)

**Code Example in Python:**
```python
def factorial(n):
    if n == 0:         # Base case
        return 1
    else:
        return n * factorial(n - 1)   # Recursive call
```

**How it works:**
To compute `factorial(4)`:
- `factorial(4)` returns `4 * factorial(3)`
- `factorial(3)` returns `3 * factorial(2)`
- `factorial(2)` returns `2 * factorial(1)`
- `factorial(1)` returns `1 * factorial(0)`
- `factorial(0)` returns `1` (base case)

So,
- `factorial(1)` = 1 × 1 = 1
- `factorial(2)` = 2 × 1 = 2
- `factorial(3)` = 3 × 2 = 6
- `factorial(4)` = 4 × 6 = 24

**In summary:**  
Recursion is when a function calls itself, and the problem gets divided into smaller parts until reaching a simple, solvable case (the base case).
[
  {
    "choices": [
      {
        "delta": {
          "content": "",
          "refusal": null,
          "role": "assistant"
        },
        "finish_reason": null,
        "index": 0,
        "logprobs": null
      }
    ],
    "created": 1776470822,
    "id": "chatcmpl-DVnV8rG1ILDUR9r3HsKDVd4dbGH0A",
    "model": "gpt-4.1-2025-04-14",
    "obfuscation": "nqlUcqwR28bhP",
    "object": "chat.completion.chunk",
    "service_tier": "default",
    "system_fingerprint": "fp_51f6d1255b",
    "usage": null
  },
  {
    "choices": [
      {
        "delta": {
          "content": "**"
        },
        "finish_reason": null,
        "index": 0,
        "logprobs": null
      }
    ],
    "created": 1776470822,
    "id": "chatcmpl-DVnV8rG1ILDUR9r3HsKDVd4dbGH0A",
    "model": "gpt-4.1-2025-04-14",
    "obfuscation": "F8I8qrGpbmKbK",
    "object": "chat.completion.chunk",
    "service_tier": "default",
    "system_fingerprint": "fp_51f6d1255b",
    "usage": null
  },
  "... 440 more chunks omitted ...",
  {
    "choices": [],
    "created": 1776470822,
    "id": "chatcmpl-DVnV8rG1ILDUR9r3HsKDVd4dbGH0A",
    "model": "gpt-4.1-2025-04-14",
    "obfuscation": "qHFF5gBP2hPp",
    "object": "chat.completion.chunk",
    "service_tier": "default",
    "system_fingerprint": "fp_51f6d1255b",
    "usage": {
      "completion_tokens": 440,
      "completion_tokens_details": {
        "accepted_prediction_tokens": 0,
        "audio_tokens": 0,
        "reasoning_tokens": 0,
        "rejected_prediction_tokens": 0
      },
      "prompt_tokens": 17,
      "prompt_tokens_details": {
        "audio_tokens": 0,
        "cached_tokens": 0
      },
      "total_tokens": 457
    }
  }
]

</details>

<details>

<summary>Web Search — Letting the model use OpenAI's built-in web search tool to answer with current information</summary>

const response = await env.AI.run(
  'openai/gpt-4.1',
  {
    input: 'What were the top news stories about Cloudflare this week? Summarise in three bullets.',
    max_output_tokens: 4096,
    tools: [{ type: 'web_search_preview' }],
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-4.1",
  "input": "What were the top news stories about Cloudflare this week? Summarise in three bullets.",
  "max_output_tokens": 4096,
  "tools": [
    {
      "type": "web_search_preview"
    }
  ]
}'
Here are the top news stories about Cloudflare this week:

- **Launch of New Partner Initiative for AI and SASE Adoption**: Cloudflare introduced the Cloudflare One Design Partner designation and an AI-powered toolkit to accelerate the adoption of artificial intelligence (AI) and secure access service edge (SASE) architectures. This initiative aims to help organizations modernize legacy security infrastructures and overcome challenges like configuration risks and lengthy deployment times. ([itpro.com](https://www.itpro.com/technology/artificial-intelligence/cloudflare-launches-new-partner-initiative-to-support-ai-and-sase-adoption?utm_source=openai))

- **Completion of Agent Infrastructure Stack with Browser Run Rebuild**: Cloudflare completed its agent infrastructure stack by rebuilding Browser Run on its own Containers platform. This upgrade delivers higher concurrency, faster response times, and support for WebGL and WebMCP, enhancing the performance and scalability of AI agents. ([infoq.com](https://www.infoq.com/news/2026/05/cloudflare-agent-platform-stack/?utm_source=openai))

- **Workforce Reduction Amid AI Adoption**: Cloudflare announced plans to reduce its global workforce by about 20%, cutting more than 1,100 jobs. This restructuring is part of the company's shift towards an AI-first operating model, reflecting the rapid adoption of AI tools and the resulting changes in operational processes. ([business-standard.com](https://www.business-standard.com/technology/tech-news/cloudflare-to-cut-about-20-workforce-as-ai-adoption-reshapes-operations-126050800117_1.html?utm_source=openai))
{
  "id": "resp_0fdf05943aa0606d016a398f3d52b48198b359c259da57fcf2",
  "object": "response",
  "created_at": 1782157117,
  "model": "gpt-4.1-2025-04-14",
  "output": [
    {
      "id": "ws_0fdf05943aa0606d016a398f3db07c8198a82f9fb39e0ca765",
      "type": "web_search_call",
      "status": "completed",
      "action": {
        "type": "search",
        "queries": [
          "Cloudflare top news stories this week"
        ],
        "query": "Cloudflare top news stories this week"
      }
    },
    {
      "id": "msg_0fdf05943aa0606d016a398f3f38808198be80ca5b78103aaf",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [
            {
              "type": "url_citation",
              "end_index": 658,
              "start_index": 494,
              "title": "Cloudflare launches new partner initiative to support AI and SASE adoption",
              "url": "https://www.itpro.com/technology/artificial-intelligence/cloudflare-launches-new-partner-initiative-to-support-ai-and-sase-adoption?utm_source=openai"
            },
            {
              "type": "url_citation",
              "end_index": 1098,
              "start_index": 998,
              "title": "Cloudflare Completes Its Agent Infrastructure Stack with Browser Run Rebuild and Six-Layer Platform - InfoQ",
              "url": "https://www.infoq.com/news/2026/05/cloudflare-agent-platform-stack/?utm_source=openai"
            },
            {
              "type": "url_citation",
              "end_index": 1618,
              "start_index": 1427,
              "title": "Cloudflare to cut about 20% workforce as AI adoption reshapes operations | Tech News - Business Standard",
              "url": "https://www.business-standard.com/technology/tech-news/cloudflare-to-cut-about-20-workforce-as-ai-adoption-reshapes-operations-126050800117_1.html?utm_source=openai"
            }
          ],
          "logprobs": [],
          "text": "Here are the top news stories about Cloudflare this week:\n\n- **Launch of New Partner Initiative for AI and SASE Adoption**: Cloudflare introduced the Cloudflare One Design Partner designation and an AI-powered toolkit to accelerate the adoption of artificial intelligence (AI) and secure access service edge (SASE) architectures. This initiative aims to help organizations modernize legacy security infrastructures and overcome challenges like configuration risks and lengthy deployment times. ([itpro.com](https://www.itpro.com/technology/artificial-intelligence/cloudflare-launches-new-partner-initiative-to-support-ai-and-sase-adoption?utm_source=openai))\n\n- **Completion of Agent Infrastructure Stack with Browser Run Rebuild**: Cloudflare completed its agent infrastructure stack by rebuilding Browser Run on its own Containers platform. This upgrade delivers higher concurrency, faster response times, and support for WebGL and WebMCP, enhancing the performance and scalability of AI agents. ([infoq.com](https://www.infoq.com/news/2026/05/cloudflare-agent-platform-stack/?utm_source=openai))\n\n- **Workforce Reduction Amid AI Adoption**: Cloudflare announced plans to reduce its global workforce by about 20%, cutting more than 1,100 jobs. This restructuring is part of the company's shift towards an AI-first operating model, reflecting the rapid adoption of AI tools and the resulting changes in operational processes. ([business-standard.com](https://www.business-standard.com/technology/tech-news/cloudflare-to-cut-about-20-workforce-as-ai-adoption-reshapes-operations-126050800117_1.html?utm_source=openai)) "
        }
      ],
      "role": "assistant"
    }
  ],
  "status": "completed",
  "usage": {
    "input_tokens": 320,
    "output_tokens": 343,
    "total_tokens": 663,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens_details": {
      "reasoning_tokens": 0
    }
  },
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1782157123,
  "error": null,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 4096,
  "max_tool_calls": null,
  "moderation": null,
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "context": null,
    "effort": null,
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [
    {
      "type": "web_search_preview",
      "search_content_types": [
        "text"
      ],
      "search_context_size": "medium",
      "user_location": {
        "type": "approximate",
        "city": null,
        "country": "US",
        "region": null,
        "timezone": null
      }
    }
  ],
  "top_logprobs": 0,
  "top_p": 1,
  "truncation": "disabled",
  "user": null,
  "metadata": {},
  "gatewayMetadata": {
    "keySource": "Unified"
  }
}

</details>

Parameters

Schema variant

ResponsesChat Completions

▶input

one ofrequired

instructions

string

temperature

numberminimum: 0maximum: 2

max_output_tokens

numberexclusiveMinimum: 0

top_p

numberminimum: 0maximum: 1

stream

boolean

▶tools[]

array

tool_choice

▶text{}

object

▶reasoning{}

object

▶messages[]

arrayrequired

temperature

numberminimum: 0maximum: 2

max_tokens

numberexclusiveMinimum: 0

max_completion_tokens

numberexclusiveMinimum: 0

top_p

numberminimum: 0maximum: 1

frequency_penalty

numberminimum: -2maximum: 2

presence_penalty

numberminimum: -2maximum: 2

stream

boolean

▶stream_options{}

object

▶tools[]

array

tool_choice

response_format

▶modalities[]

array

▶audio{}

object

reasoning_effort

stringOptional reasoning control; availability and accepted values are model-dependent.

id

string

object

stringconst: response

created_at

number

model

string

▶output[]

array

output_text

string

status

stringenum: in_progress, completed, failed, incomplete

▶usage{}

object

id

string

object

string

created

number

model

string

▶choices[]

array

▶usage{}

object

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

On this page

GPT-4.1·续 - 图1Docs

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/openai/gpt-4.1/#page","headline":"GPT-4.1","description":"OpenAI's flagship GPT model for complex tasks with a million-token context window.","url":"https://developers.cloudflare.com/ai/models/openai/gpt-4.1/","inLanguage":"en","image":"https://developers.cloudflare.com/og-docs.png","publisher":{"@type":"Organization","name":"Cloudflare","description":"One platform for your apps, agents, and workforce. Build, secure, and scale without managing infrastructure","url":"https://www.cloudflare.com/","sameAs":["https://github.com/cloudflare","https://www.linkedin.com/company/cloudflare","https://x.com/cloudflare"],"logo":{"@type":"ImageObject","url":"https://developers.cloudflare.com/logo.svg"},"address":{"@type":"PostalAddress","streetAddress":"101 Townsend St","addressLocality":"San Francisco","addressRegion":"CA","postalCode":"94107","addressCountry":"US"},"contactPoint":[{"@type":"ContactPoint","contactType":"Customer Support","url":"https://support.cloudflare.com/","availableLanguage":["English"]},{"@type":"ContactPoint","contactType":"Sales","url":"https://www.cloudflare.com/contact/","availableLanguage":["English"]}]},"isPartOf":{"@type":"WebSite","@id":"https://developers.cloudflare.com/#website","name":"Cloudflare Docs","url":"https://developers.cloudflare.com/"}}


description: Fast, affordable version of GPT-4.1 with a million-token context window. title: GPT-4.1 mini image: https://developers.cloudflare.com/og-docs.png


Skip to content

Documentation Index
Fetch the complete documentation index at: https://developers.cloudflare.com/llms.txt
Use this file to discover all available pages before exploring further.

OpenAI logo