MAI-DS-R1 is a reasoning model that the Microsoft AI team post-trained from DeepSeek-R1. Its purpose is to preserve the base model’s reasoning strengths while improving responsiveness on topics that previously received unhelpful refusals and refining the model’s risk profile. Microsoft describes the release as its own post-trained model, with a 671-billion-parameter DeepSeek-R1 foundation and a mixture-of-experts architecture. It is a text-generation model, rather than one of the smaller R1 distillations.
The model card presents language understanding and generation, general-knowledge questions, multi-step problem solving, code generation and comprehension, and scientific or academic tasks as direct uses. A useful request can therefore start with a mathematical condition, a logical puzzle, a code fragment or a technical explanation that needs to be examined. The result is text: a proposed solution, a piece of code, an explanation or a coherent draft. The nature of the result should be stated in the request so that the reasoning serves a defined goal.
For a mathematics assistant, provide the full condition, definitions, known quantities and the conclusion to establish. An illustrative task is: “Check this proposed solution. Identify the first unsupported transition, explain the missing assumption and give a corrected result that satisfies the original conditions.” For a coding assistant, provide the relevant function, input examples and expected behaviour; ask for an explanation of the fault and a change that can be checked with those examples. For research drafting, give the material to compare and distinguish source statements, interpretations and questions that still need evidence.
Microsoft also presents the model as a foundation for further domain-specific fine-tuning, including mathematics tutoring, coding assistants and scientific research tools. That is a downstream adaptation use, separate from the general-purpose model described here. The post-training uses safety and non-compliance examples together with multilingual examples covering topics where biases had been reported. The change targets response behaviour; it does not turn the model into an unrestricted system or remove the need to evaluate its answers.
The manufacturer identifies meaningful use limits. Clinical diagnosis or treatment decisions, definitive legal decisions, autonomous safety-critical control and high-stakes financial or security decisions fall outside the model card’s intended reliable use. The documented role is better framed as explanation, drafting and structured problem solving with appropriate review. Microsoft notes that factual hallucinations, cultural or demographic biases and vulnerability to adversarial prompts can remain after post-training.
The release shares the original DeepSeek-R1 knowledge cutoff, so a confident answer may still lack a recent event or a specialised fact. Although post-training uses multilingual data, Microsoft expects English and Chinese to be the strongest languages. Evaluate the language and subject matter needed for the application rather than assuming equal quality for every language. Very long or complicated prompts may remain challenging; separate the source material, the task and the criterion for a successful answer.
The model card recommends clear role and task instructions, human or automated verification for sensitive uses, and monitoring or content filtering where the application needs them. Keep the source facts and intermediate assumptions available for review, and ask for a final answer that can be compared with the original problem. The read card does not publish a separate numeric context or output ceiling for this release, so those limits should be established from an exact execution specification rather than borrowed from a different DeepSeek edition. MAI-DS-R1 remains a distinct post-trained model with its own documented objectives and limitations.
", "aboutText": "MAI-DS-R1 is a reasoning model that the Microsoft AI team post-trained from DeepSeek-R1. Its purpose is to preserve the base model’s reasoning strengths while improving responsiveness on topics that previously received unhelpful refusals and refining the model’s risk profile. Microsoft describes the release as its own post-trained model, with a 671-billion-parameter DeepSeek-R1 foundation and a mixture-of-experts architecture. It is a text-generation model, rather than one of the smaller R1 distillations.\n\nThe model card presents language understanding and generation, general-knowledge questions, multi-step problem solving, code generation and comprehension, and scientific or academic tasks as direct uses. A useful request can therefore start with a mathematical condition, a logical puzzle, a code fragment or a technical explanation that needs to be examined. The result is text: a proposed solution, a piece of code, an explanation or a coherent draft. The nature of the result should be stated in the request so that the reasoning serves a defined goal.\n\nFor a mathematics assistant, provide the full condition, definitions, known quantities and the conclusion to establish. An illustrative task is: “Check this proposed solution. Identify the first unsupported transition, explain the missing assumption and give a corrected result that satisfies the original conditions.” For a coding assistant, provide the relevant function, input examples and expected behaviour; ask for an explanation of the fault and a change that can be checked with those examples. For research drafting, give the material to compare and distinguish source statements, interpretations and questions that still need evidence.\n\nMicrosoft also presents the model as a foundation for further domain-specific fine-tuning, including mathematics tutoring, coding assistants and scientific research tools. That is a downstream adaptation use, separate from the general-purpose model described here. The post-training uses safety and non-compliance examples together with multilingual examples covering topics where biases had been reported. The change targets response behaviour; it does not turn the model into an unrestricted system or remove the need to evaluate its answers.\n\nThe manufacturer identifies meaningful use limits. Clinical diagnosis or treatment decisions, definitive legal decisions, autonomous safety-critical control and high-stakes financial or security decisions fall outside the model card’s intended reliable use. The documented role is better framed as explanation, drafting and structured problem solving with appropriate review. Microsoft notes that factual hallucinations, cultural or demographic biases and vulnerability to adversarial prompts can remain after post-training.\n\nThe release shares the original DeepSeek-R1 knowledge cutoff, so a confident answer may still lack a recent event or a specialised fact. Although post-training uses multilingual data, Microsoft expects English and Chinese to be the strongest languages. Evaluate the language and subject matter needed for the application rather than assuming equal quality for every language. Very long or complicated prompts may remain challenging; separate the source material, the task and the criterion for a successful answer.\n\nThe model card recommends clear role and task instructions, human or automated verification for sensitive uses, and monitoring or content filtering where the application needs them. Keep the source facts and intermediate assumptions available for review, and ask for a final answer that can be compared with the original problem. The read card does not publish a separate numeric context or output ceiling for this release, so those limits should be established from an exact execution specification rather than borrowed from a different DeepSeek edition. MAI-DS-R1 remains a distinct post-trained model with its own documented objectives and limitations.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "acfec631f46883c77d301c267770279b577987779d22a745e77b2f3750d7a221", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "MAI-DS-R1MAI-DS-R1 is Microsoft’s post-trained DeepSeek-R1 model for text reasoning, mathematics, code and research. It retains the R1 reasoning foundation while addressing response gaps and refining how the model handles sensitive topics.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MAI-DS-R1 is a reasoning model that the Microsoft AI team post-trained from DeepSeek-R1. Its purpose is to preserve the base model’s reasoning strengths while improving responsiveness on topics that previously received unhelpful refusals and refining the model’s risk profile. Microsoft describes the release as its own post-trained model, with a 671-billion-parameter DeepSeek-R1 foundation and a mixture-of-experts architecture. It is a text-generation model, rather than one of the smaller R1 distillations.
The model card presents language understanding and generation, general-knowledge questions, multi-step problem solving, code generation and comprehension, and scientific or academic tasks as direct uses. A useful request can therefore start with a mathematical condition, a logical puzzle, a code fragment or a technical explanation that needs to be examined. The result is text: a proposed solution, a piece of code, an explanation or a coherent draft. The nature of the result should be stated in the request so that the reasoning serves a defined goal.
For a mathematics assistant, provide the full condition, definitions, known quantities and the conclusion to establish. An illustrative task is: “Check this proposed solution. Identify the first unsupported transition, explain the missing assumption and give a corrected result that satisfies the original conditions.” For a coding assistant, provide the relevant function, input examples and expected behaviour; ask for an explanation of the fault and a change that can be checked with those examples. For research drafting, give the material to compare and distinguish source statements, interpretations and questions that still need evidence.
Microsoft also presents the model as a foundation for further domain-specific fine-tuning, including mathematics tutoring, coding assistants and scientific research tools. That is a downstream adaptation use, separate from the general-purpose model described here. The post-training uses safety and non-compliance examples together with multilingual examples covering topics where biases had been reported. The change targets response behaviour; it does not turn the model into an unrestricted system or remove the need to evaluate its answers.
The manufacturer identifies meaningful use limits. Clinical diagnosis or treatment decisions, definitive legal decisions, autonomous safety-critical control and high-stakes financial or security decisions fall outside the model card’s intended reliable use. The documented role is better framed as explanation, drafting and structured problem solving with appropriate review. Microsoft notes that factual hallucinations, cultural or demographic biases and vulnerability to adversarial prompts can remain after post-training.
The release shares the original DeepSeek-R1 knowledge cutoff, so a confident answer may still lack a recent event or a specialised fact. Although post-training uses multilingual data, Microsoft expects English and Chinese to be the strongest languages. Evaluate the language and subject matter needed for the application rather than assuming equal quality for every language. Very long or complicated prompts may remain challenging; separate the source material, the task and the criterion for a successful answer.
The model card recommends clear role and task instructions, human or automated verification for sensitive uses, and monitoring or content filtering where the application needs them. Keep the source facts and intermediate assumptions available for review, and ask for a final answer that can be compared with the original problem. The read card does not publish a separate numeric context or output ceiling for this release, so those limits should be established from an exact execution specification rather than borrowed from a different DeepSeek edition. MAI-DS-R1 remains a distinct post-trained model with its own documented objectives and limitations.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MAI-DS-R1 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00132 / 1K tokens Output · Output tokens $0.00506 / 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"MAI-DS-R1","messages":[{"role":"user","content":"hello"}],"stream":false}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model="MAI-DS-R1", messages=[{"role":"user","content":"hello"}], stream=False)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra MAI-DS-R1
/chat/completions
MAI-DS-R1MAI-DS-R1 is Microsoft’s post-trained DeepSeek-R1 model for text reasoning, mathematics, code and research. It retains the R1 reasoning foundation while addressing response gaps and refining how the model handles sensitive topics.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MAI-DS-R1 is a reasoning model that the Microsoft AI team post-trained from DeepSeek-R1. Its purpose is to preserve the base model’s reasoning strengths while improving responsiveness on topics that previously received unhelpful refusals and refining the model’s risk profile. Microsoft describes the release as its own post-trained model, with a 671-billion-parameter DeepSeek-R1 foundation and a mixture-of-experts architecture. It is a text-generation model, rather than one of the smaller R1 distillations.
The model card presents language understanding and generation, general-knowledge questions, multi-step problem solving, code generation and comprehension, and scientific or academic tasks as direct uses. A useful request can therefore start with a mathematical condition, a logical puzzle, a code fragment or a technical explanation that needs to be examined. The result is text: a proposed solution, a piece of code, an explanation or a coherent draft. The nature of the result should be stated in the request so that the reasoning serves a defined goal.
For a mathematics assistant, provide the full condition, definitions, known quantities and the conclusion to establish. An illustrative task is: “Check this proposed solution. Identify the first unsupported transition, explain the missing assumption and give a corrected result that satisfies the original conditions.” For a coding assistant, provide the relevant function, input examples and expected behaviour; ask for an explanation of the fault and a change that can be checked with those examples. For research drafting, give the material to compare and distinguish source statements, interpretations and questions that still need evidence.
Microsoft also presents the model as a foundation for further domain-specific fine-tuning, including mathematics tutoring, coding assistants and scientific research tools. That is a downstream adaptation use, separate from the general-purpose model described here. The post-training uses safety and non-compliance examples together with multilingual examples covering topics where biases had been reported. The change targets response behaviour; it does not turn the model into an unrestricted system or remove the need to evaluate its answers.
The manufacturer identifies meaningful use limits. Clinical diagnosis or treatment decisions, definitive legal decisions, autonomous safety-critical control and high-stakes financial or security decisions fall outside the model card’s intended reliable use. The documented role is better framed as explanation, drafting and structured problem solving with appropriate review. Microsoft notes that factual hallucinations, cultural or demographic biases and vulnerability to adversarial prompts can remain after post-training.
The release shares the original DeepSeek-R1 knowledge cutoff, so a confident answer may still lack a recent event or a specialised fact. Although post-training uses multilingual data, Microsoft expects English and Chinese to be the strongest languages. Evaluate the language and subject matter needed for the application rather than assuming equal quality for every language. Very long or complicated prompts may remain challenging; separate the source material, the task and the criterion for a successful answer.
The model card recommends clear role and task instructions, human or automated verification for sensitive uses, and monitoring or content filtering where the application needs them. Keep the source facts and intermediate assumptions available for review, and ask for a final answer that can be compared with the original problem. The read card does not publish a separate numeric context or output ceiling for this release, so those limits should be established from an exact execution specification rather than borrowed from a different DeepSeek edition. MAI-DS-R1 remains a distinct post-trained model with its own documented objectives and limitations.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MAI-DS-R1 | 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 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 $0.00132 / 1K tokens Output · Output tokens $0.00506 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "MAI-DS-R1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'MAI-DS-R1', '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': 'MAI-DS-R1', '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 MAI-DS-R1
/chat/completions