GPT-4 Turbo Preview 0125 is OpenAI’s updated text-focused GPT-4 Turbo research-preview edition. It handles written instructions, source material and code, producing text answers or application-oriented records. The January update specifically targets more complete task execution in areas such as code generation and fixes a bug affecting non-English UTF-8 generation. This named 0125 edition is distinct from the earlier 1106 Preview and from GPT-4 Turbo with Vision.
The producer’s Preview card lists a 128,000-token context window and up to 4,096 output tokens, with a December 1, 2023 knowledge cutoff. The large input window can hold related documents or code alongside a detailed question; the output allowance is much smaller and should shape the requested artifact. Supply current evidence when a question depends on information beyond the model’s stored knowledge.
For a requirements comparison, include the relevant documents, identify which one governs a disagreement and ask for the changed requirement, its supporting passage and its effect on the stated workflow. For a code task, give the behavior to achieve, the relevant functions and the expected result. Ask for a complete change within that scope and identify what counts as completion, rather than treating a convincing fragment as the whole task.
The GPT-4 Turbo Preview family adds stronger format-following and JSON mode. The producer describes JSON mode as constraining a response to syntactically valid JSON; it does not independently verify that a field’s value is correct or that a record meets every business rule. Define the fields, permitted values and handling of missing information in the instruction, then inspect the returned object against those requirements. 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.
An extraction task can request an item identifier, the source text that establishes its status and the next action supported by that evidence. Keep the original material with the record so a value can be checked. A parser accepting the returned JSON is one part of the workflow; a correct association between the source and the extracted fields is another.
OpenAI’s Preview release documents function calling, including requesting multiple functions in one message. The developer describes each function and its parameters, and the model returns arguments for the requested operation. The surrounding application performs the operation and returns the actual result. A lookup request is therefore separate from the retrieved record, and a proposed action is separate from its completion.
Provide functions that fit the task and name the evidence the next answer should use. A comparison assistant can request the records for two named items and then explain their differences using the returned values. If one lookup fails or gives incomplete material, preserve that condition instead of creating a plausible replacement. Retain the function identifiers and results with the continuation.
The Preview family’s seed control is documented as a beta aid to obtaining consistent completions most of the time. It is useful for comparing a prompt change while holding other settings steady; it is not a guarantee that every repeated request produces identical output. Keep the instruction, source material and settings together when comparing responses.
This profile’s listed modalities are text input and text output. Image analysis belongs to the separately named Vision Preview or later multimodal profiles. JSON mode is also distinct from newer constrained-schema features. The 0125 update’s improvements in completeness and encoding do not remove the need to inspect a code change, an extracted field or a conclusion against the supplied evidence. Choose a bounded artifact that fits the output allowance and retain the exact named edition with the result.
", "aboutText": "GPT-4 Turbo Preview 0125 is OpenAI’s updated text-focused GPT-4 Turbo research-preview edition. It handles written instructions, source material and code, producing text answers or application-oriented records. The January update specifically targets more complete task execution in areas such as code generation and fixes a bug affecting non-English UTF-8 generation. This named 0125 edition is distinct from the earlier 1106 Preview and from GPT-4 Turbo with Vision.\n\n### Large-context text work\n\nThe producer’s Preview card lists a 128,000-token context window and up to 4,096 output tokens, with a December 1, 2023 knowledge cutoff. The large input window can hold related documents or code alongside a detailed question; the output allowance is much smaller and should shape the requested artifact. Supply current evidence when a question depends on information beyond the model’s stored knowledge.\n\nFor a requirements comparison, include the relevant documents, identify which one governs a disagreement and ask for the changed requirement, its supporting passage and its effect on the stated workflow. For a code task, give the behavior to achieve, the relevant functions and the expected result. Ask for a complete change within that scope and identify what counts as completion, rather than treating a convincing fragment as the whole task.\n\n### Formats and JSON mode\n\nThe GPT-4 Turbo Preview family adds stronger format-following and JSON mode. The producer describes JSON mode as constraining a response to syntactically valid JSON; it does not independently verify that a field’s value is correct or that a record meets every business rule. Define the fields, permitted values and handling of missing information in the instruction, then inspect the returned object against those requirements. 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.\n\nAn extraction task can request an item identifier, the source text that establishes its status and the next action supported by that evidence. Keep the original material with the record so a value can be checked. A parser accepting the returned JSON is one part of the workflow; a correct association between the source and the extracted fields is another.\n\n### Function calls and actual results\n\nOpenAI’s Preview release documents function calling, including requesting multiple functions in one message. The developer describes each function and its parameters, and the model returns arguments for the requested operation. The surrounding application performs the operation and returns the actual result. A lookup request is therefore separate from the retrieved record, and a proposed action is separate from its completion.\n\nProvide functions that fit the task and name the evidence the next answer should use. A comparison assistant can request the records for two named items and then explain their differences using the returned values. If one lookup fails or gives incomplete material, preserve that condition instead of creating a plausible replacement. Retain the function identifiers and results with the continuation.\n\n### Repeatability and edition boundaries\n\nThe Preview family’s seed control is documented as a beta aid to obtaining consistent completions most of the time. It is useful for comparing a prompt change while holding other settings steady; it is not a guarantee that every repeated request produces identical output. Keep the instruction, source material and settings together when comparing responses.\n\nThis profile’s listed modalities are text input and text output. Image analysis belongs to the separately named Vision Preview or later multimodal profiles. JSON mode is also distinct from newer constrained-schema features. The 0125 update’s improvements in completeness and encoding do not remove the need to inspect a code change, an extracted field or a conclusion against the supplied evidence. Choose a bounded artifact that fits the output allowance and retain the exact named edition with the result.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Complete a CSV escaping function\n\nWrite a complete Python function csv_cell(value) that converts value to text and wraps it in double quotes only when it contains a comma, double quote or newline. Embedded double quotes must be doubled. Return the function and tests for plain text, a comma, a quotation mark and a newline. Use no third-party packages.A complete function and four concrete test cases covering each escaping condition.The quotation-mark test checks both outer quoting and doubling of the embedded quote.gpt-4-0125-previewGPT-4 Turbo Preview 0125 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 0125 is OpenAI’s updated text-focused GPT-4 Turbo research-preview edition. It handles written instructions, source material and code, producing text answers or application-oriented records. The January update specifically targets more complete task execution in areas such as code generation and fixes a bug affecting non-English UTF-8 generation. This named 0125 edition is distinct from the earlier 1106 Preview and from GPT-4 Turbo with Vision.
The producer’s Preview card lists a 128,000-token context window and up to 4,096 output tokens, with a December 1, 2023 knowledge cutoff. The large input window can hold related documents or code alongside a detailed question; the output allowance is much smaller and should shape the requested artifact. Supply current evidence when a question depends on information beyond the model’s stored knowledge.
For a requirements comparison, include the relevant documents, identify which one governs a disagreement and ask for the changed requirement, its supporting passage and its effect on the stated workflow. For a code task, give the behavior to achieve, the relevant functions and the expected result. Ask for a complete change within that scope and identify what counts as completion, rather than treating a convincing fragment as the whole task.
The GPT-4 Turbo Preview family adds stronger format-following and JSON mode. The producer describes JSON mode as constraining a response to syntactically valid JSON; it does not independently verify that a field’s value is correct or that a record meets every business rule. Define the fields, permitted values and handling of missing information in the instruction, then inspect the returned object against those requirements. 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.
An extraction task can request an item identifier, the source text that establishes its status and the next action supported by that evidence. Keep the original material with the record so a value can be checked. A parser accepting the returned JSON is one part of the workflow; a correct association between the source and the extracted fields is another.
OpenAI’s Preview release documents function calling, including requesting multiple functions in one message. The developer describes each function and its parameters, and the model returns arguments for the requested operation. The surrounding application performs the operation and returns the actual result. A lookup request is therefore separate from the retrieved record, and a proposed action is separate from its completion.
Provide functions that fit the task and name the evidence the next answer should use. A comparison assistant can request the records for two named items and then explain their differences using the returned values. If one lookup fails or gives incomplete material, preserve that condition instead of creating a plausible replacement. Retain the function identifiers and results with the continuation.
The Preview family’s seed control is documented as a beta aid to obtaining consistent completions most of the time. It is useful for comparing a prompt change while holding other settings steady; it is not a guarantee that every repeated request produces identical output. Keep the instruction, source material and settings together when comparing responses.
This profile’s listed modalities are text input and text output. Image analysis belongs to the separately named Vision Preview or later multimodal profiles. JSON mode is also distinct from newer constrained-schema features. The 0125 update’s improvements in completeness and encoding do not remove the need to inspect a code change, an extracted field or a conclusion against the supplied evidence. Choose a bounded artifact that fits the output allowance and retain the exact named edition with the result.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-0125-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-4-0125-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-4-0125-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-4-0125-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-4-0125-preview
Use the method paths shown above.
gpt-4-0125-previewGPT-4 Turbo Preview 0125 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 0125 is OpenAI’s updated text-focused GPT-4 Turbo research-preview edition. It handles written instructions, source material and code, producing text answers or application-oriented records. The January update specifically targets more complete task execution in areas such as code generation and fixes a bug affecting non-English UTF-8 generation. This named 0125 edition is distinct from the earlier 1106 Preview and from GPT-4 Turbo with Vision.
The producer’s Preview card lists a 128,000-token context window and up to 4,096 output tokens, with a December 1, 2023 knowledge cutoff. The large input window can hold related documents or code alongside a detailed question; the output allowance is much smaller and should shape the requested artifact. Supply current evidence when a question depends on information beyond the model’s stored knowledge.
For a requirements comparison, include the relevant documents, identify which one governs a disagreement and ask for the changed requirement, its supporting passage and its effect on the stated workflow. For a code task, give the behavior to achieve, the relevant functions and the expected result. Ask for a complete change within that scope and identify what counts as completion, rather than treating a convincing fragment as the whole task.
The GPT-4 Turbo Preview family adds stronger format-following and JSON mode. The producer describes JSON mode as constraining a response to syntactically valid JSON; it does not independently verify that a field’s value is correct or that a record meets every business rule. Define the fields, permitted values and handling of missing information in the instruction, then inspect the returned object against those requirements. 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.
An extraction task can request an item identifier, the source text that establishes its status and the next action supported by that evidence. Keep the original material with the record so a value can be checked. A parser accepting the returned JSON is one part of the workflow; a correct association between the source and the extracted fields is another.
OpenAI’s Preview release documents function calling, including requesting multiple functions in one message. The developer describes each function and its parameters, and the model returns arguments for the requested operation. The surrounding application performs the operation and returns the actual result. A lookup request is therefore separate from the retrieved record, and a proposed action is separate from its completion.
Provide functions that fit the task and name the evidence the next answer should use. A comparison assistant can request the records for two named items and then explain their differences using the returned values. If one lookup fails or gives incomplete material, preserve that condition instead of creating a plausible replacement. Retain the function identifiers and results with the continuation.
The Preview family’s seed control is documented as a beta aid to obtaining consistent completions most of the time. It is useful for comparing a prompt change while holding other settings steady; it is not a guarantee that every repeated request produces identical output. Keep the instruction, source material and settings together when comparing responses.
This profile’s listed modalities are text input and text output. Image analysis belongs to the separately named Vision Preview or later multimodal profiles. JSON mode is also distinct from newer constrained-schema features. The 0125 update’s improvements in completeness and encoding do not remove the need to inspect a code change, an extracted field or a conclusion against the supplied evidence. Choose a bounded artifact that fits the output allowance and retain the exact named edition with the result.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits gpt-4-0125-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 $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "gpt-4-0125-preview",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-4-0125-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-4-0125-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-4-0125-preview
Use the method paths shown above.
Technical example in English
Complete a CSV escaping function\n\nWrite a complete Python function csv_cell(value) that converts value to text and wraps it in double quotes only when it contains a comma, double quote or newline. Embedded double quotes must be doubled. Return the function and tests for plain text, a comma, a quotation mark and a newline. Use no third-party packages.A complete function and four concrete test cases covering each escaping condition.The quotation-mark test checks both outer quoting and doubling of the embedded quote.