Phi-4 is Microsoft Research’s 14-billion-parameter dense decoder-only transformer for text generation. Its development focuses on high-quality training material and advanced reasoning in a relatively compact model. It accepts text, is best suited to a chat-formatted prompt and generates a textual answer, explanation or code. The exact Phi-4 edition is distinct from later reasoning, mini and multimodal releases.
The manufacturer combines quality-filtered public documents and code, newly created synthetic educational data, acquired academic books and question-answer datasets. The synthetic material teaches mathematics, coding, common-sense reasoning and general knowledge. Supervised fine-tuning and direct preference optimisation then improve instruction adherence and response behaviour.
The producer positions Phi-4 as a building block for applications with memory or compute constraints, interactive response needs and reasoning or logic tasks, primarily in English. Give a task the complete condition and the source information needed to answer it. For a mathematical problem, define the variables, domain restrictions and form of the result; for an explanation, identify the audience and the concepts it should connect.
A useful brief is: “Compare these conditions, identify whether the proposed solution satisfies each one and explain the first failure. State any missing information before drawing a conclusion.” For a source-based question, label the passages and request the finding supported by each. Ask the answer to preserve names, units and assumptions that affect the result.
A longer prompt should still have one clear purpose. The published context is 16K tokens, containing the instructions, source text, conversation and generated response together. Keep relevant evidence in the input and reserve space for the final explanation. The card’s example generation budget is illustrative and does not establish a separate universal maximum answer length.
Phi-4 can propose code, explain a function or reason through a failing input. Supply the implementation, expected behaviour and a representative case that distinguishes a correct result. Request the code artifact separately from its explanation and identify interfaces that must remain intact.
The manufacturer notes that most code training is Python-based, particularly common standard-library packages. Uses of other packages or other programming languages need careful API verification. A generated function or script has not executed merely because it looks complete; run it in the intended environment and use the actual errors or observations to revise the result.
The maker’s prompt representation separates system, user and assistant turns. A system instruction can define the role or response style, while the user message contains the actual problem. Retain the exact model’s format rather than copying a later Phi template or assuming an image-input or tool-call feature from another edition.
Phi-4 is trained primarily in English and is not intended as a multilingual model. Other languages and less-represented English varieties can have poorer performance. Supply precise wording for technical names and evaluate the answer in the language the task needs rather than treating the small multilingual share of training data as broad language support.
The public-data training cutoff is June 2024 and earlier. For current or source-sensitive claims, provide authoritative material in the prompt. Microsoft also identifies possible inaccurate, outdated or biased output despite alignment. Review the final answer against the problem conditions and sources. The useful artifact is a textual solution, explanation or code proposal whose assumptions and supporting evidence remain clear.
", "aboutText": "Phi-4 is Microsoft Research’s 14-billion-parameter dense decoder-only transformer for text generation. Its development focuses on high-quality training material and advanced reasoning in a relatively compact model. It accepts text, is best suited to a chat-formatted prompt and generates a textual answer, explanation or code. The exact Phi-4 edition is distinct from later reasoning, mini and multimodal releases.\n\n### Training and intended use\n\nThe manufacturer combines quality-filtered public documents and code, newly created synthetic educational data, acquired academic books and question-answer datasets. The synthetic material teaches mathematics, coding, common-sense reasoning and general knowledge. Supervised fine-tuning and direct preference optimisation then improve instruction adherence and response behaviour.\n\nThe producer positions Phi-4 as a building block for applications with memory or compute constraints, interactive response needs and reasoning or logic tasks, primarily in English. Give a task the complete condition and the source information needed to answer it. For a mathematical problem, define the variables, domain restrictions and form of the result; for an explanation, identify the audience and the concepts it should connect.\n\n### Reasoning from a clear problem\n\nA useful brief is: “Compare these conditions, identify whether the proposed solution satisfies each one and explain the first failure. State any missing information before drawing a conclusion.” For a source-based question, label the passages and request the finding supported by each. Ask the answer to preserve names, units and assumptions that affect the result.\n\nA longer prompt should still have one clear purpose. The published context is 16K tokens, containing the instructions, source text, conversation and generated response together. Keep relevant evidence in the input and reserve space for the final explanation. The card’s example generation budget is illustrative and does not establish a separate universal maximum answer length.\n\n### Coding assistance\n\nPhi-4 can propose code, explain a function or reason through a failing input. Supply the implementation, expected behaviour and a representative case that distinguishes a correct result. Request the code artifact separately from its explanation and identify interfaces that must remain intact.\n\nThe manufacturer notes that most code training is Python-based, particularly common standard-library packages. Uses of other packages or other programming languages need careful API verification. A generated function or script has not executed merely because it looks complete; run it in the intended environment and use the actual errors or observations to revise the result.\n\n### Chat format and language\n\nThe maker’s prompt representation separates system, user and assistant turns. A system instruction can define the role or response style, while the user message contains the actual problem. Retain the exact model’s format rather than copying a later Phi template or assuming an image-input or tool-call feature from another edition.\n\nPhi-4 is trained primarily in English and is not intended as a multilingual model. Other languages and less-represented English varieties can have poorer performance. Supply precise wording for technical names and evaluate the answer in the language the task needs rather than treating the small multilingual share of training data as broad language support.\n\n### Reliability boundaries\n\nThe public-data training cutoff is June 2024 and earlier. For current or source-sensitive claims, provide authoritative material in the prompt. Microsoft also identifies possible inaccurate, outdated or biased output despite alignment. Review the final answer against the problem conditions and sources. The useful artifact is a textual solution, explanation or code proposal whose assumptions and supporting evidence remain clear.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a proposed batch size\n\nA machine makes exactly 12 parts per batch. A supervisor proposes five batches to supply 67 parts and says there will be three spare. Check the proposal using whole batches only. Give the first incorrect claim, the minimum sufficient batch count and the resulting spare-part count. Show the arithmetic briefly.A concise numerical check identifying the failing claim, sufficient batches and surplus.The calculation must use whole batches and meet the 67-part requirement.microsoft/phi-4Phi-4 is Microsoft Research’s 14B text model for English-language reasoning, mathematics and coding assistance. It uses a 16K context and a chat-oriented instruction format, producing explanations and proposed code from a complete problem statement and supplied text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Phi-4 is Microsoft Research’s 14-billion-parameter dense decoder-only transformer for text generation. Its development focuses on high-quality training material and advanced reasoning in a relatively compact model. It accepts text, is best suited to a chat-formatted prompt and generates a textual answer, explanation or code. The exact Phi-4 edition is distinct from later reasoning, mini and multimodal releases.
The manufacturer combines quality-filtered public documents and code, newly created synthetic educational data, acquired academic books and question-answer datasets. The synthetic material teaches mathematics, coding, common-sense reasoning and general knowledge. Supervised fine-tuning and direct preference optimisation then improve instruction adherence and response behaviour.
The producer positions Phi-4 as a building block for applications with memory or compute constraints, interactive response needs and reasoning or logic tasks, primarily in English. Give a task the complete condition and the source information needed to answer it. For a mathematical problem, define the variables, domain restrictions and form of the result; for an explanation, identify the audience and the concepts it should connect.
A useful brief is: “Compare these conditions, identify whether the proposed solution satisfies each one and explain the first failure. State any missing information before drawing a conclusion.” For a source-based question, label the passages and request the finding supported by each. Ask the answer to preserve names, units and assumptions that affect the result.
A longer prompt should still have one clear purpose. The published context is 16K tokens, containing the instructions, source text, conversation and generated response together. Keep relevant evidence in the input and reserve space for the final explanation. The card’s example generation budget is illustrative and does not establish a separate universal maximum answer length.
Phi-4 can propose code, explain a function or reason through a failing input. Supply the implementation, expected behaviour and a representative case that distinguishes a correct result. Request the code artifact separately from its explanation and identify interfaces that must remain intact.
The manufacturer notes that most code training is Python-based, particularly common standard-library packages. Uses of other packages or other programming languages need careful API verification. A generated function or script has not executed merely because it looks complete; run it in the intended environment and use the actual errors or observations to revise the result.
The maker’s prompt representation separates system, user and assistant turns. A system instruction can define the role or response style, while the user message contains the actual problem. Retain the exact model’s format rather than copying a later Phi template or assuming an image-input or tool-call feature from another edition.
Phi-4 is trained primarily in English and is not intended as a multilingual model. Other languages and less-represented English varieties can have poorer performance. Supply precise wording for technical names and evaluate the answer in the language the task needs rather than treating the small multilingual share of training data as broad language support.
The public-data training cutoff is June 2024 and earlier. For current or source-sensitive claims, provide authoritative material in the prompt. Microsoft also identifies possible inaccurate, outdated or biased output despite alignment. Review the final answer against the problem conditions and sources. The useful artifact is a textual solution, explanation or code proposal whose assumptions and supporting evidence remain clear.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits microsoft/phi-4 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00014 / 1K tokens Output · Output tokens $0.00028 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00014 / 1K tokens Output · Output tokens $0.00028 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "microsoft/phi-4", "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='microsoft/phi-4',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='microsoft/phi-4',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 microsoft/phi-4
Use the method paths shown above.
microsoft/phi-4Phi-4 is Microsoft Research’s 14B text model for English-language reasoning, mathematics and coding assistance. It uses a 16K context and a chat-oriented instruction format, producing explanations and proposed code from a complete problem statement and supplied text.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Phi-4 is Microsoft Research’s 14-billion-parameter dense decoder-only transformer for text generation. Its development focuses on high-quality training material and advanced reasoning in a relatively compact model. It accepts text, is best suited to a chat-formatted prompt and generates a textual answer, explanation or code. The exact Phi-4 edition is distinct from later reasoning, mini and multimodal releases.
The manufacturer combines quality-filtered public documents and code, newly created synthetic educational data, acquired academic books and question-answer datasets. The synthetic material teaches mathematics, coding, common-sense reasoning and general knowledge. Supervised fine-tuning and direct preference optimisation then improve instruction adherence and response behaviour.
The producer positions Phi-4 as a building block for applications with memory or compute constraints, interactive response needs and reasoning or logic tasks, primarily in English. Give a task the complete condition and the source information needed to answer it. For a mathematical problem, define the variables, domain restrictions and form of the result; for an explanation, identify the audience and the concepts it should connect.
A useful brief is: “Compare these conditions, identify whether the proposed solution satisfies each one and explain the first failure. State any missing information before drawing a conclusion.” For a source-based question, label the passages and request the finding supported by each. Ask the answer to preserve names, units and assumptions that affect the result.
A longer prompt should still have one clear purpose. The published context is 16K tokens, containing the instructions, source text, conversation and generated response together. Keep relevant evidence in the input and reserve space for the final explanation. The card’s example generation budget is illustrative and does not establish a separate universal maximum answer length.
Phi-4 can propose code, explain a function or reason through a failing input. Supply the implementation, expected behaviour and a representative case that distinguishes a correct result. Request the code artifact separately from its explanation and identify interfaces that must remain intact.
The manufacturer notes that most code training is Python-based, particularly common standard-library packages. Uses of other packages or other programming languages need careful API verification. A generated function or script has not executed merely because it looks complete; run it in the intended environment and use the actual errors or observations to revise the result.
The maker’s prompt representation separates system, user and assistant turns. A system instruction can define the role or response style, while the user message contains the actual problem. Retain the exact model’s format rather than copying a later Phi template or assuming an image-input or tool-call feature from another edition.
Phi-4 is trained primarily in English and is not intended as a multilingual model. Other languages and less-represented English varieties can have poorer performance. Supply precise wording for technical names and evaluate the answer in the language the task needs rather than treating the small multilingual share of training data as broad language support.
The public-data training cutoff is June 2024 and earlier. For current or source-sensitive claims, provide authoritative material in the prompt. Microsoft also identifies possible inaccurate, outdated or biased output despite alignment. Review the final answer against the problem conditions and sources. The useful artifact is a textual solution, explanation or code proposal whose assumptions and supporting evidence remain clear.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits microsoft/phi-4 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00014 / 1K tokens Output · Output tokens $0.00028 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00014 / 1K tokens Output · Output tokens $0.00028 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "microsoft/phi-4",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'microsoft/phi-4', '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': 'microsoft/phi-4', '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 microsoft/phi-4
Use the method paths shown above.
Technical example in English
Check a proposed batch size\n\nA machine makes exactly 12 parts per batch. A supervisor proposes five batches to supply 67 parts and says there will be three spare. Check the proposal using whole batches only. Give the first incorrect claim, the minimum sufficient batch count and the resulting spare-part count. Show the arithmetic briefly.A concise numerical check identifying the failing claim, sufficient batches and surplus.The calculation must use whole batches and meet the 67-part requirement.