GPT-5.4 is OpenAI’s general-purpose reasoning model for complex professional work. Its release brings together coding, reasoning and agentic workflows with document, spreadsheet and presentation tasks. It accepts text and images and produces text. The manufacturer also documents native computer use for the model in a connected working environment.
For knowledge work, provide the relevant material, the intended audience and the requirements of the final artifact. An illustrative task is turning several project documents into a decision brief, with the supplied facts, the relationships between them and the conditions supporting a recommendation. A spreadsheet or presentation task also needs the source data and the structure or template the result should follow. The environment’s tools create or edit the actual files; the model’s written response explains or directs that work.
For coding, supply the intended behavior, related project files and the constraints the change must preserve. Ask for a proposed implementation or focused review tied to that behavior. The release describes longer workflows that combine using tools, iterating on a result and checking it. For visual or computer-use tasks, provide the actual screenshot or reference and the objective. The model can interpret the screen and choose an operation; the connected environment performs the action and returns the new state.
OpenAI’s GPT-5.4 specification lists a 1,050,000-token context window and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. Its reasoning-effort choices are none, low, medium, high and xhigh; none is the default. Context accommodates the supplied material, relevant tool results and reasoning as well as the final answer. Keep the task’s definitions and success criteria clear, especially when several steps depend on earlier evidence.
The producer lists Responses, Chat Completions and Batch interfaces, streaming, Structured Outputs, function calling, file and image inputs, web and file search and prompt caching. Its tools include image generation, code interpretation, hosted shell and patch operations, skills, computer use, MCP connections and tool search. The release explains tool search as finding a needed tool definition when it becomes relevant, rather than requiring every full definition in the initial context. The application manages its operations and provides the actual results.
The model’s release also describes improved document parsing and high-resolution visual understanding, plus broader professional tasks that combine information from several web sources. Prepare readable inputs and identify which details matter to the question. Choose a concrete final result and evidence for checking it: the proposed change and affected behavior, a structured set of findings or a document that follows the supplied requirements. Distinguish the result of a completed tool action from a step that still needs to be performed, so the final artifact is useful for continuing the work.
", "aboutText": "GPT-5.4 is OpenAI’s general-purpose reasoning model for complex professional work. Its release brings together coding, reasoning and agentic workflows with document, spreadsheet and presentation tasks. It accepts text and images and produces text. The manufacturer also documents native computer use for the model in a connected working environment.\n\nFor knowledge work, provide the relevant material, the intended audience and the requirements of the final artifact. An illustrative task is turning several project documents into a decision brief, with the supplied facts, the relationships between them and the conditions supporting a recommendation. A spreadsheet or presentation task also needs the source data and the structure or template the result should follow. The environment’s tools create or edit the actual files; the model’s written response explains or directs that work.\n\nFor coding, supply the intended behavior, related project files and the constraints the change must preserve. Ask for a proposed implementation or focused review tied to that behavior. The release describes longer workflows that combine using tools, iterating on a result and checking it. For visual or computer-use tasks, provide the actual screenshot or reference and the objective. The model can interpret the screen and choose an operation; the connected environment performs the action and returns the new state.\n\nOpenAI’s GPT-5.4 specification lists a 1,050,000-token context window and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. Its reasoning-effort choices are none, low, medium, high and xhigh; none is the default. Context accommodates the supplied material, relevant tool results and reasoning as well as the final answer. Keep the task’s definitions and success criteria clear, especially when several steps depend on earlier evidence.\n\nThe producer lists Responses, Chat Completions and Batch interfaces, streaming, Structured Outputs, function calling, file and image inputs, web and file search and prompt caching. Its tools include image generation, code interpretation, hosted shell and patch operations, skills, computer use, MCP connections and tool search. The release explains tool search as finding a needed tool definition when it becomes relevant, rather than requiring every full definition in the initial context. The application manages its operations and provides the actual results.\n\nThe model’s release also describes improved document parsing and high-resolution visual understanding, plus broader professional tasks that combine information from several web sources. Prepare readable inputs and identify which details matter to the question. Choose a concrete final result and evidence for checking it: the proposed change and affected behavior, a structured set of findings or a document that follows the supplied requirements. Distinguish the result of a completed tool action from a step that still needs to be performed, so the final artifact is useful for continuing the work.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "57166fbd272d25361f114efbed974a5849e5f050702e3e33dfac66ef89e17866", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "openai/gpt-5.4:batchGPT-5.4 combines reasoning, coding, visual understanding and native computer use for complex professional work. Supply text, images and a clear task brief to develop documents, code or a multi-step result in a tool-connected environment.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.4 is OpenAI’s general-purpose reasoning model for complex professional work. Its release brings together coding, reasoning and agentic workflows with document, spreadsheet and presentation tasks. It accepts text and images and produces text. The manufacturer also documents native computer use for the model in a connected working environment.
For knowledge work, provide the relevant material, the intended audience and the requirements of the final artifact. An illustrative task is turning several project documents into a decision brief, with the supplied facts, the relationships between them and the conditions supporting a recommendation. A spreadsheet or presentation task also needs the source data and the structure or template the result should follow. The environment’s tools create or edit the actual files; the model’s written response explains or directs that work.
For coding, supply the intended behavior, related project files and the constraints the change must preserve. Ask for a proposed implementation or focused review tied to that behavior. The release describes longer workflows that combine using tools, iterating on a result and checking it. For visual or computer-use tasks, provide the actual screenshot or reference and the objective. The model can interpret the screen and choose an operation; the connected environment performs the action and returns the new state.
OpenAI’s GPT-5.4 specification lists a 1,050,000-token context window and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. Its reasoning-effort choices are none, low, medium, high and xhigh; none is the default. Context accommodates the supplied material, relevant tool results and reasoning as well as the final answer. Keep the task’s definitions and success criteria clear, especially when several steps depend on earlier evidence.
The producer lists Responses, Chat Completions and Batch interfaces, streaming, Structured Outputs, function calling, file and image inputs, web and file search and prompt caching. Its tools include image generation, code interpretation, hosted shell and patch operations, skills, computer use, MCP connections and tool search. The release explains tool search as finding a needed tool definition when it becomes relevant, rather than requiring every full definition in the initial context. The application manages its operations and provides the actual results.
The model’s release also describes improved document parsing and high-resolution visual understanding, plus broader professional tasks that combine information from several web sources. Prepare readable inputs and identify which details matter to the question. Choose a concrete final result and evidence for checking it: the proposed change and affected behavior, a structured set of findings or a document that follows the supplied requirements. Distinguish the result of a completed tool action from a step that still needs to be performed, so the final artifact is useful for continuing the work.
POST /v1/batchestexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldendpoint | Typestring | RequirementRequired | Values & limits /v1/chat/completions | Default— |
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5.4:batch | Default— |
Fieldrequests | Typebatch_item[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldrequests[].custom_id | Typestring | RequirementRequired | Values & limits | Default— |
Fieldrequests[].body.messages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldcompletion_window | Typestring | RequirementOptional | Values & limits 24h | Default— |
Fieldprovider | Typeobject|null | RequirementOptional | Values & limits | Default— |
Fieldrequests[].body.model | Typestring | RequirementOptional | Values & limits openai/gpt-5.4:batch, openai/gpt-5.4 | Default— |
Fieldprovider.only | Typestring[] | RequirementOptional | Values & limits openai | Default— |
Fieldprovider.allow_fallbacks | Typeboolean|null | RequirementOptional | Values & limits false, null | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractendpoint, model, requests |
Parametermaterial_types | Contracttext |
Parameterrepresentation | Contractinline requests[]; each item has custom_id and body |
Parameterrequest_endpoint_profile | Contract/v1/chat/completions |
Parameterfile_material | ContractCaller may read actual UTF-8 JSONL locally into requests[]. No upload purpose, input_file_id or file reference is used. Missing/empty customer material stops preparation before POST. |
Parameterserialization_order | Contractendpoint, model, provider (if supplied), completion_window (if supplied), requests last |
Parameteroptional_controls | Contractprovider.only, provider.allow_fallbacks, completion_window |
Parameterschema_scope | ContractText Chat Completions bodies in the documented inline Batch envelope. |
Lifecycle: asynchronous
GET /v1/batches/{operation_id} · actual original create response.id; same user/key/group
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.0025 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and including272,000 | Charge Input · Input tokens $0.0025 / 1K tokens Output · Output tokens $0.015 / 1K tokens Input · Cache read $0.00025 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 2 | Rate schedule— | Context tokens, more than272,000 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.005 / 1K tokens Output · Output tokens $0.0225 / 1K tokens Input · Cache read $0.0005 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json\nfrom pathlib import Path\nbody=json.loads('{"endpoint":"/v1/chat/completions","model":"openai/gpt-5.4:batch","requests":[{"custom_id":"req-0001","body":{"messages":[{"role":"user","content":"Hello!"}],"max_tokens":16}}]}')\nPath("batch-request.json").write_text(json.dumps(body,ensure_ascii=False),encoding="utf-8")\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/batches \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @batch-request.json -D batch-response-headers.txt -o batch-create-response.json\nimport json, os\nfrom pathlib import Path\nfrom urllib.request import Request, urlopen\n\ndef prepare_requests(customer_path):\n path = Path(customer_path)\n if not path.is_file(): raise ValueError("Customer JSONL file is missing")\n items = [json.loads(line) for line in path.read_text(encoding="utf-8").splitlines() if line.strip()]\n if not items: raise ValueError("Customer JSONL contains no requests")\n ids = set()\n for item in items:\n if set(item) != {"custom_id", "body"}: raise ValueError("Each item needs custom_id and body")\n cid = item["custom_id"]\n if not isinstance(cid, str) or not cid.strip() or cid in ids: raise ValueError("custom_id must be nonempty and unique")\n ids.add(cid)\n if not isinstance(item["body"], dict) or not item["body"].get("messages"): raise ValueError("Supply actual text messages")\n supplied_model = item["body"].get("model")\n if supplied_model is not None and supplied_model not in ['openai/gpt-5.4:batch', 'openai/gpt-5.4']: raise ValueError("body.model must be an exact documented caller or wire ID")\n return {"endpoint":"/v1/chat/completions", "model":"openai/gpt-5.4:batch", "requests":items}\n\nif __name__ == "__main__":\n material = os.environ.get("AILOOT_BATCH_REQUESTS_JSONL", "")\n if not material: raise SystemExit("Set AILOOT_BATCH_REQUESTS_JSONL to your actual customer file")\n body = prepare_requests(material)\n key = os.environ.get("AILOOT_API_KEY", "")\n if not key: raise SystemExit("Set AILOOT_API_KEY")\n request = Request("https://api.ailoot.ai/v1/batches", data=json.dumps(body, ensure_ascii=False).encode("utf-8"), headers={"Authorization":"Bearer " + key, "Content-Type":"application/json"}, method="POST")\n with urlopen(request) as response:\n raw = response.read()\n Path("batch-create-response.json").write_bytes(raw)\n print(raw.decode("utf-8"))\nimport json\nfrom pathlib import Path\nraw = Path("batch-status-response.json").read_bytes()\nresponse = json.loads(raw)\nif response.get("status") != "completed":\n raise SystemExit("Keep the original operation; read its status without resubmitting")\nresults = response.get("results")\nif not isinstance(results, list) or not results:\n raise SystemExit("Preserve the original response; completed results are missing")\nPath("batch-results.jsonl").write_text("".join(json.dumps(item, ensure_ascii=False) + "\\n" for item in results), encoding="utf-8")\n# Preserve batch-status-response.json with aggregate usage and every result/error.\ninline results[].response.body JSON
GET /v1/batches/{operation_id}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nBATCH_OPERATION_ID="$(python3 - <<'PY_ID'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nresponse = json.loads(Path("batch-create-response.json").read_text(encoding="utf-8"))\noperation = response.get("id")\nif not isinstance(operation, str) or not operation: raise SystemExit("No actual original operation ID; preserve the response and do not resubmit")\nprint(quote(operation, safe=""))\nPY_ID\n)"\ncurl --fail-with-body --silent --show-error "https://api.ailoot.ai/v1/batches/$BATCH_OPERATION_ID" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -o batch-status-response.json\nKeep every complete returned response, file and content part.
Preserve the full original status JSON, every result/custom_id and complete response or error body. Save completed results[] as JSONL without filtering.
Preserve the original operation ID. 503 result_pending_check has X-Should-Retry:false; never resubmit an unknown original batch.
| Field | Type |
|---|---|
Fieldresults[].custom_id | Typestring |
Fieldresults[].response.body.choices[].message.content | Typestring|null |
Fieldresults[].error | Typeobject|null |
Fieldusage | Typeobject|null |
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldendpoint | Typestring |
Fieldstatus | Typestring |
Fieldrequest_counts | Typeobject |
Fieldresults[].id | Typestring |
Fieldresults[].response.status_code | Typeinteger |
Fieldresults[].response.request_id | Typestring |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid documented inline envelope, duplicate keys, item identity, or configured model capabilities conflict. | Next stepCorrect the indicated fields before any new submission. |
Response401 · authentication_error | ConditionInvalid API key. | Next stepUse the authorized Ailoot key. |
Response403 · permission_error | ConditionBatch group unavailable. | Next stepCheck key/group entitlement. |
Response422 · invalid_request_error | ConditionBatch uses balance billing; subscription creation is rejected. | Next stepUse the authorized balance-billed group. |
Response422 · price_unavailable | ConditionBatch input cannot be quoted. | Next stepPreserve response; use documented family input. |
Response402 · billing_error | ConditionBatch reserve unavailable. | Next stepResolve admission before a new request. |
Response503 · price_unavailable | ConditionBatch method price/native rates unavailable. | Next stepPreserve response; do not substitute prices. |
Response503 · api_error | ConditionExact supplier route unavailable. | Next stepPreserve response for route repair. |
Response503 · result_pending_check | ConditionOriginal result requires checking; X-Should-Retry:false. | Next stepKeep original operation_id/id and read its status; never repeat original POST. |
Response404 · not_found | ConditionBatch status operation absent or owned by another identity. | Next stepUse exact original id and same user/key/group. |
Ailoot Ultra openai/gpt-5.4:batch
Use the method paths shown above.