GPT-4 32K is OpenAI’s extended-context GPT-4 text profile for tasks that need more related material in one request. The manufacturer documents a 32,768-token context, compared with the original GPT-4 profile’s 8,192 tokens. It takes text and returns text, including natural-language explanations, drafts and code. Its defining distinction is the larger context, rather than the 128K window or multimodal capabilities of later GPT-4 Turbo profiles.
Supply the documents or code relevant to a clearly stated task. A requirements comparison can place several specifications together and ask which conditions agree, which conflict and which source governs a decision. Give each source an identifier and request the passage that supports an important finding. Keeping related evidence together can help the model compare it, while the result still needs to preserve the connection between a conclusion and its source.
For a codebase question, include the relevant functions, their callers and the behavior being investigated. Ask for an explanation of the dependency or a focused change tied to that behavior. The larger context can hold useful surrounding code, but it does not remove the need to define the question or the completion criterion. A code proposal should identify the input case that motivates it and the expected result that can be checked.
The GPT-4 release describes system-message steerability: the developer can specify the model’s task, tone and style. Use that instruction to establish whether the response should be a short explanation, a comparison, a draft or a record with named fields. Define how missing information should appear and distinguish supplied facts from assumptions. A document-processing task can ask for a list of conditions with the source identifier and the relevant passage beside each condition.
Maintain those instructions as the conversation develops. Include the actual previous result when the next request revises it, and identify what should change. A useful follow-up narrows a disagreement in a comparison or asks for a correction to one part of a draft instead of assuming that a new isolated prompt preserves the entire earlier task.
The producer’s 0613 update adds the function-calling improvements of GPT-4 to the extended-context edition. The developer describes a function and its parameters, and the model can return a JSON object containing arguments for that function. The application executes the operation and supplies the returned result. The useful capability is a structured request connected to application behavior, rather than the model directly completing an external action.
For an information assistant, a function can retrieve the actual record needed to answer a question. Keep the requested identifier and the returned record associated, then ask for an answer based on that result. Check whether a proposed action is supported by the user’s request and whether the function actually completed it. The updated function interface is separate from the later JSON-mode and parallel-calling additions of GPT-4 Turbo.
The original GPT-4 release identifies factual hallucinations, reasoning errors and limited knowledge of newer events as material limitations. Supply current evidence for a question whose answer has changed, and check the important figures, names and code behavior against the source. A confident explanation can still misinterpret a condition or introduce a defect.
Keep the requested artifact proportionate to the task and the available context. The 32K figure is a context capacity, not a promise of an equally long finished answer or perfect comprehension of every included passage. Retain the selected model profile, instructions, source material and result together. This makes a long-document comparison, a code explanation or a revised draft concrete enough to inspect and continue.
", "aboutText": "GPT-4 32K is OpenAI’s extended-context GPT-4 text profile for tasks that need more related material in one request. The manufacturer documents a 32,768-token context, compared with the original GPT-4 profile’s 8,192 tokens. It takes text and returns text, including natural-language explanations, drafts and code. Its defining distinction is the larger context, rather than the 128K window or multimodal capabilities of later GPT-4 Turbo profiles.\n\n### Use the context for related evidence\n\nSupply the documents or code relevant to a clearly stated task. A requirements comparison can place several specifications together and ask which conditions agree, which conflict and which source governs a decision. Give each source an identifier and request the passage that supports an important finding. Keeping related evidence together can help the model compare it, while the result still needs to preserve the connection between a conclusion and its source.\n\nFor a codebase question, include the relevant functions, their callers and the behavior being investigated. Ask for an explanation of the dependency or a focused change tied to that behavior. The larger context can hold useful surrounding code, but it does not remove the need to define the question or the completion criterion. A code proposal should identify the input case that motivates it and the expected result that can be checked.\n\n### State the task and response style\n\nThe GPT-4 release describes system-message steerability: the developer can specify the model’s task, tone and style. Use that instruction to establish whether the response should be a short explanation, a comparison, a draft or a record with named fields. Define how missing information should appear and distinguish supplied facts from assumptions. A document-processing task can ask for a list of conditions with the source identifier and the relevant passage beside each condition.\n\nMaintain those instructions as the conversation develops. Include the actual previous result when the next request revises it, and identify what should change. A useful follow-up narrows a disagreement in a comparison or asks for a correction to one part of a draft instead of assuming that a new isolated prompt preserves the entire earlier task.\n\n### Function calling in the updated 32K line\n\nThe producer’s 0613 update adds the function-calling improvements of GPT-4 to the extended-context edition. The developer describes a function and its parameters, and the model can return a JSON object containing arguments for that function. The application executes the operation and supplies the returned result. The useful capability is a structured request connected to application behavior, rather than the model directly completing an external action.\n\nFor an information assistant, a function can retrieve the actual record needed to answer a question. Keep the requested identifier and the returned record associated, then ask for an answer based on that result. Check whether a proposed action is supported by the user’s request and whether the function actually completed it. The updated function interface is separate from the later JSON-mode and parallel-calling additions of GPT-4 Turbo.\n\n### Review the answer against the material\n\nThe original GPT-4 release identifies factual hallucinations, reasoning errors and limited knowledge of newer events as material limitations. Supply current evidence for a question whose answer has changed, and check the important figures, names and code behavior against the source. A confident explanation can still misinterpret a condition or introduce a defect.\n\nKeep the requested artifact proportionate to the task and the available context. The 32K figure is a context capacity, not a promise of an equally long finished answer or perfect comprehension of every included passage. Retain the selected model profile, instructions, source material and result together. This makes a long-document comparison, a code explanation or a revised draft concrete enough to inspect and continue.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Compare requirements using a precedence rule\n\nCompare three labelled specifications. BASE: exports include all orders and run nightly. ADDENDUM: exports include paid orders only; cadence is unchanged. OPERATIONS: exports run hourly. The signed ADDENDUM overrides BASE, while OPERATIONS is an unsigned proposal. Produce the effective requirements and unresolved proposal, citing the governing source for each.An effective-requirements table plus a separate unresolved-proposal entry with source references.Paid orders and nightly cadence are retained as effective; hourly cadence remains an unsigned proposal.gpt-4-32k-0613GPT-4 32K is the extended-context GPT-4 text profile for working with larger collections of documents or code. Its documented 32,768-token context supports related material in one task, with system instructions guiding the response and function calling documented in the updated 0613 edition.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-4 32K is OpenAI’s extended-context GPT-4 text profile for tasks that need more related material in one request. The manufacturer documents a 32,768-token context, compared with the original GPT-4 profile’s 8,192 tokens. It takes text and returns text, including natural-language explanations, drafts and code. Its defining distinction is the larger context, rather than the 128K window or multimodal capabilities of later GPT-4 Turbo profiles.
Supply the documents or code relevant to a clearly stated task. A requirements comparison can place several specifications together and ask which conditions agree, which conflict and which source governs a decision. Give each source an identifier and request the passage that supports an important finding. Keeping related evidence together can help the model compare it, while the result still needs to preserve the connection between a conclusion and its source.
For a codebase question, include the relevant functions, their callers and the behavior being investigated. Ask for an explanation of the dependency or a focused change tied to that behavior. The larger context can hold useful surrounding code, but it does not remove the need to define the question or the completion criterion. A code proposal should identify the input case that motivates it and the expected result that can be checked.
The GPT-4 release describes system-message steerability: the developer can specify the model’s task, tone and style. Use that instruction to establish whether the response should be a short explanation, a comparison, a draft or a record with named fields. Define how missing information should appear and distinguish supplied facts from assumptions. A document-processing task can ask for a list of conditions with the source identifier and the relevant passage beside each condition.
Maintain those instructions as the conversation develops. Include the actual previous result when the next request revises it, and identify what should change. A useful follow-up narrows a disagreement in a comparison or asks for a correction to one part of a draft instead of assuming that a new isolated prompt preserves the entire earlier task.
The producer’s 0613 update adds the function-calling improvements of GPT-4 to the extended-context edition. The developer describes a function and its parameters, and the model can return a JSON object containing arguments for that function. The application executes the operation and supplies the returned result. The useful capability is a structured request connected to application behavior, rather than the model directly completing an external action.
For an information assistant, a function can retrieve the actual record needed to answer a question. Keep the requested identifier and the returned record associated, then ask for an answer based on that result. Check whether a proposed action is supported by the user’s request and whether the function actually completed it. The updated function interface is separate from the later JSON-mode and parallel-calling additions of GPT-4 Turbo.
The original GPT-4 release identifies factual hallucinations, reasoning errors and limited knowledge of newer events as material limitations. Supply current evidence for a question whose answer has changed, and check the important figures, names and code behavior against the source. A confident explanation can still misinterpret a condition or introduce a defect.
Keep the requested artifact proportionate to the task and the available context. The 32K figure is a context capacity, not a promise of an equally long finished answer or perfect comprehension of every included passage. Retain the selected model profile, instructions, source material and result together. This makes a long-document comparison, a code explanation or a revised draft concrete enough to inspect and continue.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-32k-0613 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.12 / 1K tokens Output · Output tokens $0.24 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "gpt-4-32k-0613", "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='gpt-4-32k-0613',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='gpt-4-32k-0613',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-4-32k-0613
Use the method paths shown above.
gpt-4-32k-0613GPT-4 32K is the extended-context GPT-4 text profile for working with larger collections of documents or code. Its documented 32,768-token context supports related material in one task, with system instructions guiding the response and function calling documented in the updated 0613 edition.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-4 32K is OpenAI’s extended-context GPT-4 text profile for tasks that need more related material in one request. The manufacturer documents a 32,768-token context, compared with the original GPT-4 profile’s 8,192 tokens. It takes text and returns text, including natural-language explanations, drafts and code. Its defining distinction is the larger context, rather than the 128K window or multimodal capabilities of later GPT-4 Turbo profiles.
Supply the documents or code relevant to a clearly stated task. A requirements comparison can place several specifications together and ask which conditions agree, which conflict and which source governs a decision. Give each source an identifier and request the passage that supports an important finding. Keeping related evidence together can help the model compare it, while the result still needs to preserve the connection between a conclusion and its source.
For a codebase question, include the relevant functions, their callers and the behavior being investigated. Ask for an explanation of the dependency or a focused change tied to that behavior. The larger context can hold useful surrounding code, but it does not remove the need to define the question or the completion criterion. A code proposal should identify the input case that motivates it and the expected result that can be checked.
The GPT-4 release describes system-message steerability: the developer can specify the model’s task, tone and style. Use that instruction to establish whether the response should be a short explanation, a comparison, a draft or a record with named fields. Define how missing information should appear and distinguish supplied facts from assumptions. A document-processing task can ask for a list of conditions with the source identifier and the relevant passage beside each condition.
Maintain those instructions as the conversation develops. Include the actual previous result when the next request revises it, and identify what should change. A useful follow-up narrows a disagreement in a comparison or asks for a correction to one part of a draft instead of assuming that a new isolated prompt preserves the entire earlier task.
The producer’s 0613 update adds the function-calling improvements of GPT-4 to the extended-context edition. The developer describes a function and its parameters, and the model can return a JSON object containing arguments for that function. The application executes the operation and supplies the returned result. The useful capability is a structured request connected to application behavior, rather than the model directly completing an external action.
For an information assistant, a function can retrieve the actual record needed to answer a question. Keep the requested identifier and the returned record associated, then ask for an answer based on that result. Check whether a proposed action is supported by the user’s request and whether the function actually completed it. The updated function interface is separate from the later JSON-mode and parallel-calling additions of GPT-4 Turbo.
The original GPT-4 release identifies factual hallucinations, reasoning errors and limited knowledge of newer events as material limitations. Supply current evidence for a question whose answer has changed, and check the important figures, names and code behavior against the source. A confident explanation can still misinterpret a condition or introduce a defect.
Keep the requested artifact proportionate to the task and the available context. The 32K figure is a context capacity, not a promise of an equally long finished answer or perfect comprehension of every included passage. Retain the selected model profile, instructions, source material and result together. This makes a long-document comparison, a code explanation or a revised draft concrete enough to inspect and continue.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-32k-0613 | 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.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.12 / 1K tokens Output · Output tokens $0.24 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gpt-4-32k-0613",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-4-32k-0613', '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-4-32k-0613', '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-4-32k-0613
Use the method paths shown above.
Technical example in English
Compare requirements using a precedence rule\n\nCompare three labelled specifications. BASE: exports include all orders and run nightly. ADDENDUM: exports include paid orders only; cadence is unchanged. OPERATIONS: exports run hourly. The signed ADDENDUM overrides BASE, while OPERATIONS is an unsigned proposal. Produce the effective requirements and unresolved proposal, citing the governing source for each.An effective-requirements table plus a separate unresolved-proposal entry with source references.Paid orders and nightly cadence are retained as effective; hourly cadence remains an unsigned proposal.