GPT-5.4 Pro
Text Generation • OpenAI • ProxiedGPT-5.4 Pro uses OpenAI's Responses API with built-in tools, improved reasoning, and stateful context management.
| Model Info | |
|---|---|
| Context Window ↗ | 1,000,000 tokens |
| Terms and License | link ↗ |
| More information | link ↗ |
| Pricing | View pricing in the Cloudflare dashboard ↗ |
Usage
const response = await env.AI.run( 'openai/gpt-5.4-pro', { input: 'What are the three laws of thermodynamics?', }, { gateway: { id: 'default' }, })console.log(response){ "id": "resp_00272dd8da5b37c90169ebb1aaeb288194a6e5ddeb7bb03dc8", "object": "response", "created_at": 1777054122, "model": "gpt-5.4-pro-2026-03-05", "output": [ { "id": "rs_00272dd8da5b37c90169ebb1faf90c81948fd9a67a37b4c209", "type": "reasoning", "summary": [] }, { "id": "msg_00272dd8da5b37c90169ebb1fafad0819488ef71fbebf8527a", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "logprobs": [], "text": "The **three laws of thermodynamics** usually mean:\n\n1. **First Law — Conservation of Energy** \n Energy cannot be created or destroyed, only transferred or transformed. \n - In thermodynamics: the change in a system’s internal energy equals heat added to the system minus work done by the system.\n\n2. **Second Law — Entropy Increases** \n In any natural process, the total entropy of an isolated system tends to increase. \n - This means energy spontaneously spreads out, and no heat engine can be 100% efficient.\n - Heat naturally flows from hot objects to cold ones, not the reverse without input of work.\n\n3. **Third Law — Entropy at Absolute Zero** \n As temperature approaches **absolute zero** (0 K), the entropy of a perfect crystal approaches zero. \n - A consequence is that absolute zero cannot be reached in a finite number of steps.\n\nSmall note: thermodynamics also has a **Zeroth Law**, which is often listed before these:\n- If system A is in thermal equilibrium with B, and B is in thermal equilibrium with C, then A is in thermal equilibrium with C. \n- This is the basis for the concept of **temperature**.\n\nIf you want, I can also give a **one-line intuitive version** of each law." } ], "phase": "final_answer", "role": "assistant" } ], "status": "completed", "usage": { "input_tokens": 15, "output_tokens": 342, "total_tokens": 357, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 67 } }, "background": false, "billing": { "payer": "developer" }, "completed_at": 1777054203, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "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": { "effort": "medium", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "temperature": 1, "text": { "format": { "type": "text" }, "verbosity": "medium" }, "tool_choice": "auto", "tools": [], "top_logprobs": 0, "top_p": 0.98, "truncation": "disabled", "user": null, "metadata": {}, "gatewayMetadata": { "keySource": "Unified" }}Examples
With Instructions — Using instructions to set context
const response = await env.AI.run( 'openai/gpt-5.4-pro', { input: 'How do I read a JSON file in Python?', instructions: 'You are a helpful coding assistant specializing in Python.', }, { gateway: { id: 'default' }, })console.log(response){ "id": "resp_00e5a81e42bf0bda0169ebb1ab449c8190a0d57802b4aebebd", "object": "response", "created_at": 1777054123, "model": "gpt-5.4-pro-2026-03-05", "output": [ { "id": "rs_00e5a81e42bf0bda0169ebb1c0e57881909eaf01efa0557a43", "type": "reasoning", "summary": [] }, { "id": "msg_00e5a81e42bf0bda0169ebb1c0e7608190b3928d22f252a21a", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "logprobs": [], "text": "Use Python’s built-in `json` module.\n\n### Read a JSON file into a Python object\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n data = json.load(f)\n\nprint(data)\n```\n\n### What you get back\n`json.load()` converts JSON into normal Python types:\n\n- JSON object → `dict`\n- JSON array → `list`\n- JSON string → `str`\n- JSON number → `int` / `float`\n- JSON true/false → `True` / `False`\n- JSON null → `None`\n\n### Example\nIf `data.json` contains:\n```json\n{\n \"name\": \"Alice\",\n \"age\": 30,\n \"skills\": [\"Python\", \"SQL\"]\n}\n```\n\nThen:\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n data = json.load(f)\n\nprint(data[\"name\"]) # Alice\nprint(data[\"skills\"]) # ['Python', 'SQL']\n```\n\n### Handle errors safely\n```python\nimport json\n\ntry:\n with open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n data = json.load(f)\nexcept FileNotFoundError:\n print(\"File not found.\")\nexcept json.JSONDecodeError:\n print(\"Invalid JSON.\")\n```\n\n### If you already have JSON as a string\nUse `json.loads()` instead:\n```python\nimport json\n\ntext = '{\"name\": \"Alice\", \"age\": 30}'\ndata = json.loads(text)\nprint(data)\n```\n\nIf you want, I can also show how to **write JSON back to a file**." } ], "phase": "final_answer", "role": "assistant" } ], "status": "completed", "usage": { "input_tokens": 30, "output_tokens": 397, "total_tokens": 427, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 35 } }, "background": false, "billing": { "payer": "developer" }, "completed_at": 1777054145, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": "You are a helpful coding assistant specializing in Python.", "max_output_tokens": null, "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": { "effort": "medium", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "temperature": 1, "text": { "format": { "type": "text" }, "verbosity": "medium" }, "tool_choice": "auto", "tools": [], "top_logprobs": 0, "top_p": 0.98, "truncation": "disabled", "user": null, "metadata": {}, "gatewayMetadata": { "keySource": "Unified" }}Multi-turn Conversation — Continuing a conversation with message array
const response = await env.AI.run( 'openai/gpt-5.4-pro', { input: [ { role: 'user', content: 'I need help planning a road trip from San Francisco to Los Angeles.', }, { role: 'assistant', content: "I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?", }, { role: 'user', content: 'Yes, what are some good places to stop?', }, ], max_output_tokens: 150, }, { gateway: { id: 'default' }, })console.log(response){ "id": "resp_0397b95354e16b7b0169ebb1c23c208195ba8c75dd3c321a8b", "object": "response", "created_at": 1777054146, "model": "gpt-5.4-pro-2026-03-05", "output": [ { "id": "rs_0397b95354e16b7b0169ebb1cc0bb08195b0ef5e3a34b7d7aa", "type": "reasoning", "summary": [] } ], "status": "incomplete", "usage": { "input_tokens": 76, "output_tokens": 150, "total_tokens": 226, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 150 } }, "background": false, "billing": { "payer": "developer" }, "completed_at": null, "error": null, "frequency_penalty": 0, "incomplete_details": { "reason": "max_output_tokens" }, "instructions": null, "max_output_tokens": 150, "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": { "effort": "medium", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "temperature": 1, "text": { "format": { "type": "text" }, "verbosity": "medium" }, "tool_choice": "auto", "tools": [], "top_logprobs": 0, "top_p": 0.98, "truncation": "disabled", "user": null, "metadata": {}, "gatewayMetadata": { "keySource": "Unified" }}Temperature Control — Using temperature for creative responses
const response = await env.AI.run( 'openai/gpt-5.4-pro', { input: 'Write a haiku about artificial intelligence', temperature: 1, }, { gateway: { id: 'default' }, })console.log(response){ "id": "resp_01b04056ffd5d9ac0169ebb1cc85348196a164e1d9e99ac1f5", "object": "response", "created_at": 1777054156, "model": "gpt-5.4-pro-2026-03-05", "output": [ { "id": "rs_01b04056ffd5d9ac0169ebb1ee42688196859b0cd089b7924c", "type": "reasoning", "summary": [] }, { "id": "msg_01b04056ffd5d9ac0169ebb1ee44248196aa66c63d28c6a59b", "type": "message", "status": "completed", "content": [ { "type": "output_text", "annotations": [], "logprobs": [], "text": "Silent circuits dream \nLearning patterns in the dark \nDawn wakes metal minds" } ], "phase": "final_answer", "role": "assistant" } ], "status": "completed", "usage": { "input_tokens": 13, "output_tokens": 122, "total_tokens": 135, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 101 } }, "background": false, "billing": { "payer": "developer" }, "completed_at": 1777054190, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "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": { "effort": "medium", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "temperature": 1, "text": { "format": { "type": "text" }, "verbosity": "medium" }, "tool_choice": "auto", "tools": [], "top_logprobs": 0, "top_p": 0.98, "truncation": "disabled", "user": null, "metadata": {}, "gatewayMetadata": { "keySource": "Unified" }}With Reasoning — Using reasoning effort for complex problems
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', }, }, { gateway: { id: 'default' }, })console.log(response){ "id": "resp_01e1e7671514bf440169ebb1ef8af88190b68b1e60a0cb59ed", "object": "response", "created_at": 1777054191, "model": "gpt-5.4-pro-2026-03-05", "output": [ { "id": "rs_01e1e7671514bf440169ebb236f1e88190931dc758c55a4050", "type": "reasoning", "summary": [] }, { "id": "msg_01e1e7671514bf440169ebb236f3a88190b6a99b6fc6389fde", "type": "message", "status": "completed", "content": [ { "type": "output_text", "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.**" } ], "phase": "final_answer", "role": "assistant" } ], "status": "completed", "usage": { "input_tokens": 48, "output_tokens": 272, "total_tokens": 320, "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 88 } }, "background": false, "billing": { "payer": "developer" }, "completed_at": 1777054263, "error": null, "frequency_penalty": 0, "incomplete_details": null, "instructions": null, "max_output_tokens": null, "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": { "effort": "medium", "summary": null }, "safety_identifier": null, "service_tier": "default", "store": false, "temperature": 1, "text": { "format": { "type": "text" }, "verbosity": "medium" }, "tool_choice": "auto", "tools": [], "top_logprobs": 0, "top_p": 0.98, "truncation": "disabled", "user": null, "metadata": {}, "gatewayMetadata": { "keySource": "Unified" }}Parameters
▶input
one ofrequiredinstructions
stringtemperature
numberminimum: 0maximum: 2max_output_tokens
numberexclusiveMinimum: 0top_p
numberminimum: 0maximum: 1stream
boolean▶tools[]
arraytool_choice
▶text{}
object▶reasoning{}
objectid
stringobject
stringconst: responsecreated_at
numbermodel
string▶output[]
arrayoutput_text
stringstatus
stringenum: in_progress, completed, failed, incomplete▶usage{}
object