GPT-4 Turbo Preview 1106 is OpenAI’s first named GPT-4 Turbo Preview text edition. It introduces a 128K context window, improved instruction following, JSON mode and function-calling updates, including requests for multiple functions in one message. Its useful output is a text answer, code proposal or structured application record grounded in the supplied material. This 1106 profile is separate from the Vision Preview and the later 0125 update.
The launch specifies a 128K context window and knowledge of world events through April 2023. Provide newer evidence when the task depends on current information. A larger context can hold related source documents or code, but the prompt still needs to establish what the model should do with them. State the question, which material is authoritative and the expected form of the answer.
For a document comparison, identify the versions and ask for the changed conditions with the passages that support them. For a coding task, include the existing behavior, the desired change and the relevant interface constraints. A useful result can be a focused patch or an explanation of a defect with the concrete case that exposes it. Keep irrelevant material out of the task so the model’s attention is directed toward the evidence that changes the result.
The producer highlights better adherence to instructions that require a particular response format. A request can define an ordered explanation, a table or a machine-readable record. Name the fields and explain what to return when the source does not establish a value. An example record-processing brief can ask for a source identifier, an extracted condition and the passage from which it was taken.
JSON mode constrains the reply to a syntactically valid JSON object in the producer’s Chat Completions flow. Valid JSON does not establish that the record contains the right fields or correct values. Keep application validation and the source check separate from the format control, especially when the next step depends on a particular identifier or status. When using the maker’s JSON mode, explicitly instruct the model to produce JSON and include the word “JSON” in the conversation. Without that instruction, it can emit whitespace until the token limit; check that a complete object was returned. The later constrained-schema output features of other models are a different mechanism.
The model can produce arguments for application-defined functions. The release adds the ability to request several functions in a single message, which can support a task needing more than one lookup. Describe each function’s purpose and required inputs, then connect the actual returned information to the next answer. The model selects and describes the request; the application executes it.
For a comparison of two records, a function can retrieve each record’s actual details before the assistant prepares the comparison. Preserve the association between the requested item and the returned result. When a source is missing or an operation fails, carry that condition into the response rather than announcing a successful outcome from the proposed arguments alone.
The launch’s beta seed control aims to produce consistent completions most of the time. Use it with the same source material and other settings when comparing a small prompt change. It does not guarantee determinism, so inspect both responses and retain the conditions under which each was produced.
The original release separates this text Preview from GPT-4 Turbo with Vision, image generation and speech-generation models. Supply a diagram’s relevant information in written form for this profile instead of transferring the Vision model’s input capability. The later 0125 Preview update targets more thorough task completion and fixes an encoding bug; the 1106 edition predates those changes. Keep the named model, source material, requested format and returned artifact together when assessing a result.
", "aboutText": "GPT-4 Turbo Preview 1106 is OpenAI’s first named GPT-4 Turbo Preview text edition. It introduces a 128K context window, improved instruction following, JSON mode and function-calling updates, including requests for multiple functions in one message. Its useful output is a text answer, code proposal or structured application record grounded in the supplied material. This 1106 profile is separate from the Vision Preview and the later 0125 update.\n\n### Put related text into one bounded task\n\nThe launch specifies a 128K context window and knowledge of world events through April 2023. Provide newer evidence when the task depends on current information. A larger context can hold related source documents or code, but the prompt still needs to establish what the model should do with them. State the question, which material is authoritative and the expected form of the answer.\n\nFor a document comparison, identify the versions and ask for the changed conditions with the passages that support them. For a coding task, include the existing behavior, the desired change and the relevant interface constraints. A useful result can be a focused patch or an explanation of a defect with the concrete case that exposes it. Keep irrelevant material out of the task so the model’s attention is directed toward the evidence that changes the result.\n\n### Follow a requested format\n\nThe producer highlights better adherence to instructions that require a particular response format. A request can define an ordered explanation, a table or a machine-readable record. Name the fields and explain what to return when the source does not establish a value. An example record-processing brief can ask for a source identifier, an extracted condition and the passage from which it was taken.\n\nJSON mode constrains the reply to a syntactically valid JSON object in the producer’s Chat Completions flow. Valid JSON does not establish that the record contains the right fields or correct values. Keep application validation and the source check separate from the format control, especially when the next step depends on a particular identifier or status. When using the maker’s JSON mode, explicitly instruct the model to produce JSON and include the word “JSON” in the conversation. Without that instruction, it can emit whitespace until the token limit; check that a complete object was returned. The later constrained-schema output features of other models are a different mechanism.\n\n### Request functions with useful arguments\n\nThe model can produce arguments for application-defined functions. The release adds the ability to request several functions in a single message, which can support a task needing more than one lookup. Describe each function’s purpose and required inputs, then connect the actual returned information to the next answer. The model selects and describes the request; the application executes it.\n\nFor a comparison of two records, a function can retrieve each record’s actual details before the assistant prepares the comparison. Preserve the association between the requested item and the returned result. When a source is missing or an operation fails, carry that condition into the response rather than announcing a successful outcome from the proposed arguments alone.\n\n### Repeatable experiments and the selected edition\n\nThe launch’s beta seed control aims to produce consistent completions most of the time. Use it with the same source material and other settings when comparing a small prompt change. It does not guarantee determinism, so inspect both responses and retain the conditions under which each was produced.\n\nThe original release separates this text Preview from GPT-4 Turbo with Vision, image generation and speech-generation models. Supply a diagram’s relevant information in written form for this profile instead of transferring the Vision model’s input capability. The later 0125 Preview update targets more thorough task completion and fixes an encoding bug; the 1106 edition predates those changes. Keep the named model, source material, requested format and returned artifact together when assessing a result.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Extract a source-linked renewal record\n\nFrom this note, draft a JSON object with fields account, renewal_date, owner and evidence: “Account Northbridge renews on 30 June. The commercial owner has not yet been assigned.” Use null for an unstated owner, retain the date wording and include the source sentence supporting the renewal date. Return no extra prose.A requested JSON record with the four named fields, an unknown owner and source evidence.Parse the returned record and check its values against the note; requested JSON formatting does not replace field validation.gpt-4-1106-previewGPT-4 Turbo Preview 1106 handles long-context text and code tasks with a documented 128K context window. JSON mode and function calling help turn supplied material into text answers or application records, with the exact Preview edition kept separate from vision and later models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-4 Turbo Preview 1106 is OpenAI’s first named GPT-4 Turbo Preview text edition. It introduces a 128K context window, improved instruction following, JSON mode and function-calling updates, including requests for multiple functions in one message. Its useful output is a text answer, code proposal or structured application record grounded in the supplied material. This 1106 profile is separate from the Vision Preview and the later 0125 update.
The launch specifies a 128K context window and knowledge of world events through April 2023. Provide newer evidence when the task depends on current information. A larger context can hold related source documents or code, but the prompt still needs to establish what the model should do with them. State the question, which material is authoritative and the expected form of the answer.
For a document comparison, identify the versions and ask for the changed conditions with the passages that support them. For a coding task, include the existing behavior, the desired change and the relevant interface constraints. A useful result can be a focused patch or an explanation of a defect with the concrete case that exposes it. Keep irrelevant material out of the task so the model’s attention is directed toward the evidence that changes the result.
The producer highlights better adherence to instructions that require a particular response format. A request can define an ordered explanation, a table or a machine-readable record. Name the fields and explain what to return when the source does not establish a value. An example record-processing brief can ask for a source identifier, an extracted condition and the passage from which it was taken.
JSON mode constrains the reply to a syntactically valid JSON object in the producer’s Chat Completions flow. Valid JSON does not establish that the record contains the right fields or correct values. Keep application validation and the source check separate from the format control, especially when the next step depends on a particular identifier or status. When using the maker’s JSON mode, explicitly instruct the model to produce JSON and include the word “JSON” in the conversation. Without that instruction, it can emit whitespace until the token limit; check that a complete object was returned. The later constrained-schema output features of other models are a different mechanism.
The model can produce arguments for application-defined functions. The release adds the ability to request several functions in a single message, which can support a task needing more than one lookup. Describe each function’s purpose and required inputs, then connect the actual returned information to the next answer. The model selects and describes the request; the application executes it.
For a comparison of two records, a function can retrieve each record’s actual details before the assistant prepares the comparison. Preserve the association between the requested item and the returned result. When a source is missing or an operation fails, carry that condition into the response rather than announcing a successful outcome from the proposed arguments alone.
The launch’s beta seed control aims to produce consistent completions most of the time. Use it with the same source material and other settings when comparing a small prompt change. It does not guarantee determinism, so inspect both responses and retain the conditions under which each was produced.
The original release separates this text Preview from GPT-4 Turbo with Vision, image generation and speech-generation models. Supply a diagram’s relevant information in written form for this profile instead of transferring the Vision model’s input capability. The later 0125 Preview update targets more thorough task completion and fixes an encoding bug; the 1106 edition predates those changes. Keep the named model, source material, requested format and returned artifact together when assessing a result.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-1106-preview | 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 $0.02 / 1K tokens Output · Output tokens $0.06 / 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-4-1106-preview", "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-4-1106-preview',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-4-1106-preview',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-4-1106-preview
Use the method paths shown above.
gpt-4-1106-previewGPT-4 Turbo Preview 1106 handles long-context text and code tasks with a documented 128K context window. JSON mode and function calling help turn supplied material into text answers or application records, with the exact Preview edition kept separate from vision and later models.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
GPT-4 Turbo Preview 1106 is OpenAI’s first named GPT-4 Turbo Preview text edition. It introduces a 128K context window, improved instruction following, JSON mode and function-calling updates, including requests for multiple functions in one message. Its useful output is a text answer, code proposal or structured application record grounded in the supplied material. This 1106 profile is separate from the Vision Preview and the later 0125 update.
The launch specifies a 128K context window and knowledge of world events through April 2023. Provide newer evidence when the task depends on current information. A larger context can hold related source documents or code, but the prompt still needs to establish what the model should do with them. State the question, which material is authoritative and the expected form of the answer.
For a document comparison, identify the versions and ask for the changed conditions with the passages that support them. For a coding task, include the existing behavior, the desired change and the relevant interface constraints. A useful result can be a focused patch or an explanation of a defect with the concrete case that exposes it. Keep irrelevant material out of the task so the model’s attention is directed toward the evidence that changes the result.
The producer highlights better adherence to instructions that require a particular response format. A request can define an ordered explanation, a table or a machine-readable record. Name the fields and explain what to return when the source does not establish a value. An example record-processing brief can ask for a source identifier, an extracted condition and the passage from which it was taken.
JSON mode constrains the reply to a syntactically valid JSON object in the producer’s Chat Completions flow. Valid JSON does not establish that the record contains the right fields or correct values. Keep application validation and the source check separate from the format control, especially when the next step depends on a particular identifier or status. When using the maker’s JSON mode, explicitly instruct the model to produce JSON and include the word “JSON” in the conversation. Without that instruction, it can emit whitespace until the token limit; check that a complete object was returned. The later constrained-schema output features of other models are a different mechanism.
The model can produce arguments for application-defined functions. The release adds the ability to request several functions in a single message, which can support a task needing more than one lookup. Describe each function’s purpose and required inputs, then connect the actual returned information to the next answer. The model selects and describes the request; the application executes it.
For a comparison of two records, a function can retrieve each record’s actual details before the assistant prepares the comparison. Preserve the association between the requested item and the returned result. When a source is missing or an operation fails, carry that condition into the response rather than announcing a successful outcome from the proposed arguments alone.
The launch’s beta seed control aims to produce consistent completions most of the time. Use it with the same source material and other settings when comparing a small prompt change. It does not guarantee determinism, so inspect both responses and retain the conditions under which each was produced.
The original release separates this text Preview from GPT-4 Turbo with Vision, image generation and speech-generation models. Supply a diagram’s relevant information in written form for this profile instead of transferring the Vision model’s input capability. The later 0125 Preview update targets more thorough task completion and fixes an encoding bug; the 1106 edition predates those changes. Keep the named model, source material, requested format and returned artifact together when assessing a result.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-1106-preview | 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 $0.02 / 1K tokens Output · Output tokens $0.06 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gpt-4-1106-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-4-1106-preview', '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-4-1106-preview', '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-4-1106-preview
Use the method paths shown above.
Technical example in English
Extract a source-linked renewal record\n\nFrom this note, draft a JSON object with fields account, renewal_date, owner and evidence: “Account Northbridge renews on 30 June. The commercial owner has not yet been assigned.” Use null for an unstated owner, retain the date wording and include the source sentence supporting the renewal date. Return no extra prose.A requested JSON record with the four named fields, an unknown owner and source evidence.Parse the returned record and check its values against the note; requested JSON formatting does not replace field validation.