GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.
The release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.
Frontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.
OpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.
The dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.
The release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.
Define what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.
", "aboutText": "GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.\n\nThe release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.\n\nFrontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.\n\nOpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.\n\nThe dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.\n\nThe release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.\n\nDefine what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Patch a parser and its caller\n\nPropose a coordinated patch for two Python excerpts. parser.py: def parse_line(line): return line.split(":"). runner.py: key, value = parse_line(line). A value may contain colons; blank lines must be skipped. For "title:a:b", preserve value "a:b". Return both changed excerpts and tests for a colon-bearing value, a blank line and a missing delimiter.Two focused code changes with a clear malformed-line contract and tests covering the three supplied cases.Check that the parser and caller agree on skipped and malformed lines and that value colons are preserved.gpt-5.3-codexA Codex-specialized model for agentic coding and long-running technical tasks. It accepts text and images, works with tool results and supports compaction so a task can continue beyond a single context window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.
The release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.
Frontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.
OpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.
The dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.
The release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.
Define what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-5.3-codex | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
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 $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 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 includingNo upper bound | Charge Input · Input tokens $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"gpt-5.3-codex","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="gpt-5.3-codex", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra gpt-5.3-codex, openai/gpt-5.3-codex
/chat/completions
gpt-5.3-codexA Codex-specialized model for agentic coding and long-running technical tasks. It accepts text and images, works with tool results and supports compaction so a task can continue beyond a single context window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.
The release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.
Frontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.
OpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.
The dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.
The release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.
Define what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-5.3-codex | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
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 $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 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 includingNo upper bound | Charge Input · Input tokens $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gpt-5.3-codex",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'gpt-5.3-codex', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'gpt-5.3-codex', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra gpt-5.3-codex, openai/gpt-5.3-codex
/chat/completions
openai/gpt-5.3-codexA Codex-specialized model for agentic coding and long-running technical tasks. It accepts text and images, works with tool results and supports compaction so a task can continue beyond a single context window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.
The release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.
Frontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.
OpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.
The dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.
The release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.
Define what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5.3-codex | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
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 $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 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 includingNo upper bound | Charge Input · Input tokens $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "openai/gpt-5.3-codex", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='openai/gpt-5.3-codex',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='openai/gpt-5.3-codex',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra gpt-5.3-codex, openai/gpt-5.3-codex
/chat/completions
openai/gpt-5.3-codexA Codex-specialized model for agentic coding and long-running technical tasks. It accepts text and images, works with tool results and supports compaction so a task can continue beyond a single context window.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-5.3-Codex is OpenAI’s model specialized for agentic coding in Codex and similar tool-connected environments. It combines coding with reasoning and professional knowledge, accepts text and images and produces text. Its role extends from generating code to inspecting a project, making decisions from tool evidence and continuing a technical task through its subsequent steps.
The release describes implementation, debugging, testing and other work across the software lifecycle, including product requirements, technical documents and data analysis. For a coding request, give the model the behavior to implement, the relevant project material and the constraints it must preserve. An illustrative task is tracing how an input reaches its result, identifying the dependencies involved and developing a coordinated patch with an explanation of the affected behavior.
Frontend work can combine the written brief with screenshots or other visual references. Identify the interaction or layout that matters and the expected user result. In a coding environment, file contents, command output and the results of checks become evidence for the next decision. The application executes the tools and returns actual output; the model should distinguish a proposed change from a change made and checked in that environment.
OpenAI specifies a 400,000-token context window, a maximum input of 272,000 tokens and a maximum output of 128,000 tokens, with a knowledge cutoff of August 31, 2025. The model supports low, medium, high and xhigh reasoning effort. The dedicated prompting guide recommends medium as a practical starting point for interactive coding and higher effort for difficult work. Its documented interface is Responses, with streaming, Structured Outputs, function calling, image input, web search and prompt caching. The exact model-card tool set includes functions, web search, hosted shell and skills.
The dedicated Codex guide documents first-class compaction for long trajectories. When the conversation grows, the application can produce compacted context that retains key prior state for later requests. The guide also requires preserving assistant-message phase information: intermediate commentary and the final answer have different roles, and losing that distinction can cause early stopping or degraded behavior. A progress message should therefore remain a progress message rather than being treated as the completed task result.
The release describes steering and interacting with the model during work in the Codex environment. Provide corrections or additional requirements while keeping the original objective and relevant evidence explicit. It also describes automatic monitoring and controls for requests assessed as higher-risk cybersecurity work. Those producer controls are separate from the permissions and tools supplied by a particular working environment.
Define what a completed task should include. For a bug fix, supply the observed failure and expected behavior, then request the affected files, the significant change and the result of the checks actually performed. For a review, ask for concrete issues tied to the intended behavior. A useful final artifact connects the proposed or completed work to the original request and lists the evidence obtained, along with any specific step that remains unresolved.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits openai/gpt-5.3-codex | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
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 $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 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 includingNo upper bound | Charge Input · Input tokens $0.0035 / 1K tokens Output · Output tokens $0.028 / 1K tokens Input · Cache read $0.00035 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "openai/gpt-5.3-codex",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'openai/gpt-5.3-codex', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'openai/gpt-5.3-codex', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra gpt-5.3-codex, openai/gpt-5.3-codex
/chat/completions
Technical example in English
Patch a parser and its caller\n\nPropose a coordinated patch for two Python excerpts. parser.py: def parse_line(line): return line.split(":"). runner.py: key, value = parse_line(line). A value may contain colons; blank lines must be skipped. For "title:a:b", preserve value "a:b". Return both changed excerpts and tests for a colon-bearing value, a blank line and a missing delimiter.Two focused code changes with a clear malformed-line contract and tests covering the three supplied cases.Check that the parser and caller agree on skipped and malformed lines and that value colons are preserved.