GPT-5.4 pro·续

GPT-5.4 pro·续

- Monterey is great for the aquarium, Cannery Row, and ocean views.  
- San Luis Obispo is a fun lunch stop with a charming downtown and Mission Plaza.  
- Santa Barbara offers beaches, palm-lined streets, and an easy coastal break.

{
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1777421276,
  "created_at": 1777421147,
  "error": null,
  "frequency_penalty": 0,
  "gatewayMetadata": {
    "keySource": "BYOK"
  },
  "id": "resp_08addd0821ac85160169f14b5b16d881968c58b918efd0d015",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 16000,
  "max_tool_calls": null,
  "metadata": {},
  "model": "gpt-5.4-pro-2026-03-05",
  "moderation": null,
  "object": "response",
  "output": [
    {
      "id": "rs_08addd0821ac85160169f14bdca35c819696eb984a7f0beead",
      "summary": [],
      "type": "reasoning"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "- Monterey is great for the aquarium, Cannery Row, and ocean views.  \n- San Luis Obispo is a fun lunch stop with a charming downtown and Mission Plaza.  \n- Santa Barbara offers beaches, palm-lined streets, and an easy coastal break.",
          "type": "output_text"
        }
      ],
      "id": "msg_08addd0821ac85160169f14bdca4ec8196a5b40b76291544f5",
      "phase": "final_answer",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 78,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 104,
    "output_tokens_details": {
      "reasoning_tokens": 46
    },
    "total_tokens": 182
  },
  "user": null
}

</details>

<summary>Temperature Control — Using temperature for creative responses</summary>

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  { input: 'Write a haiku about artificial intelligence', temperature: 1 },
)
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-5.4-pro",
  "input": "Write a haiku about artificial intelligence",
  "temperature": 1
}'

Silent circuits dream  
Learning patterns in the dark  
Dawn wakes metal minds

{
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1777054190,
  "created_at": 1777054156,
  "error": null,
  "frequency_penalty": 0,
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "id": "resp_01b04056ffd5d9ac0169ebb1cc85348196a164e1d9e99ac1f5",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {},
  "model": "gpt-5.4-pro-2026-03-05",
  "moderation": null,
  "object": "response",
  "output": [
    {
      "id": "rs_01b04056ffd5d9ac0169ebb1ee42688196859b0cd089b7924c",
      "summary": [],
      "type": "reasoning"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "Silent circuits dream  \nLearning patterns in the dark  \nDawn wakes metal minds",
          "type": "output_text"
        }
      ],
      "id": "msg_01b04056ffd5d9ac0169ebb1ee44248196aa66c63d28c6a59b",
      "phase": "final_answer",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 13,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 122,
    "output_tokens_details": {
      "reasoning_tokens": 101
    },
    "total_tokens": 135
  },
  "user": null
}

</details>

<summary>With Reasoning — Using reasoning effort for complex problems</summary>

const response = await env.AI.run(
  'openai/gpt-5.4-pro',
  {
    input:
      'Solve this problem step by step: A train leaves Chicago at 60mph heading east. Another train leaves New York at 80mph heading west. They are 900 miles apart. When do they meet?',
    reasoning: { effort: 'medium' },
  },
)
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-5.4-pro",
  "input": "Solve this problem step by step: A train leaves Chicago at 60mph heading east. Another train leaves New York at 80mph heading west. They are 900 miles apart. When do they meet?",
  "reasoning": {
    "effort": "medium"
  }
}'

Step 1: Find their combined speed since they are moving toward each other.

- Train from Chicago: **60 mph**
- Train from New York: **80 mph**

Combined speed:

**60 + 80 = 140 mph**

Step 2: Use the distance formula:

\[
\text{time}=\frac{\text{distance}}{\text{speed}}
\]

\[
\text{time}=\frac{900}{140}
\]

\[
\text{time}=6.428571\text{ hours}
\]

Step 3: Convert the decimal part to minutes.

\[
0.428571 \times 60 \approx 25.7 \text{ minutes}
\]

So they meet after about:

**6 hours 26 minutes**

Final answer: **The trains meet about 6 hours 26 minutes after they leave.**

{
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1777054263,
  "created_at": 1777054191,
  "error": null,
  "frequency_penalty": 0,
  "gatewayMetadata": {
    "keySource": "Unified"
  },
  "id": "resp_01e1e7671514bf440169ebb1ef8af88190b68b1e60a0cb59ed",
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": {},
  "model": "gpt-5.4-pro-2026-03-05",
  "moderation": null,
  "object": "response",
  "output": [
    {
      "id": "rs_01e1e7671514bf440169ebb236f1e88190931dc758c55a4050",
      "summary": [],
      "type": "reasoning"
    },
    {
      "content": [
        {
          "annotations": [],
          "logprobs": [],
          "text": "Step 1: Find their combined speed since they are moving toward each other.\n\n- Train from Chicago: **60 mph**\n- Train from New York: **80 mph**\n\nCombined speed:\n\n**60 + 80 = 140 mph**\n\nStep 2: Use the distance formula:\n\n\\[\n\\text{time}=\\frac{\\text{distance}}{\\text{speed}}\n\\]\n\n\\[\n\\text{time}=\\frac{900}{140}\n\\]\n\n\\[\n\\text{time}=6.428571\\text{ hours}\n\\]\n\nStep 3: Convert the decimal part to minutes.\n\n\\[\n0.428571 \\times 60 \\approx 25.7 \\text{ minutes}\n\\]\n\nSo they meet after about:\n\n**6 hours 26 minutes**\n\nFinal answer: **The trains meet about 6 hours 26 minutes after they leave.**",
          "type": "output_text"
        }
      ],
      "id": "msg_01e1e7671514bf440169ebb236f3a88190b6a99b6fc6389fde",
      "phase": "final_answer",
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "in_memory",
  "reasoning": {
    "effort": "medium",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "status": "completed",
  "store": false,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 48,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 272,
    "output_tokens_details": {
      "reasoning_tokens": 88
    },
    "total_tokens": 320
  },
  "user": null
}

</details>

Parameters

▶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

string

object

stringconst: response

created_at

number

model

string

▶output[]

array

output_text

string

status

stringenum: in_progress, completed, failed, incomplete

▶usage{}

object

API Schemas (Raw)

Input Open Download

Output Open Download

Was this helpful?

YesNo

{"@context":"https://schema.org","@type":"TechArticle","@id":"https://developers.cloudflare.com/ai/models/openai/gpt-5.4-pro/#page","headline":"GPT-5.4 pro","description":"GPT-5.4 pro uses OpenAI's Responses API with built-in tools, improved reasoning, and stateful context management.","url":"https://developers.cloudflare.com/ai/models/openai/gpt-5.4-pro/","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: GPT-5.5 is OpenAI's flagship model with strong coding, reasoning, and multimodal capabilities. title: GPT-5.5 image: https://developers.cloudflare.com/og-docs.png

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.

GPT-5.4 pro·续

GPT-5.4 pro·续

Parameters

API Schemas (Raw)

On this page