MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.
The manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.
For a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.
M1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.
For code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.
MiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.
State whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.
M1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.
Keep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.
The useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.
", "aboutText": "MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.\n\n### Context and reasoning editions\n\nThe manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.\n\nFor a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.\n\n### Training for real-world reasoning\n\nM1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.\n\nFor code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.\n\n### Producer prompting guidance\n\nMiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.\n\nState whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.\n\n### Function calling\n\nM1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.\n\nKeep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.\n\nThe useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Check a batch-processing invariant\n\nA worker reads pending jobs, marks each running, then records completion. On restart it reads only pending jobs. Analyse what happens if the process stops after marking a job running but before recording completion. Propose a recovery rule that avoids losing the job and prevents an already completed external action from being repeated blindly. Give two failure-point tests.A failure analysis, a bounded recovery/state-reconciliation proposal and tests for interruption before and after an external action.Recovery checks the original action's outcome before deciding whether another execution is safe.MiniMax-M1MiniMax M1 is MiniMax’s hybrid-attention reasoning model for long-source analysis, mathematics, coding and tools. Its producer family has a native one-million-token context and distinct 40K and 80K thinking-budget editions, returning text and structured function-call content.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.
The manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.
For a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.
M1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.
For code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.
MiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.
State whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.
M1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.
Keep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.
The useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MiniMax-M1 | 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model":"MiniMax-M1","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="MiniMax-M1", 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 MiniMax-M1, minimax/minimax-m1
/chat/completions
MiniMax-M1MiniMax M1 is MiniMax’s hybrid-attention reasoning model for long-source analysis, mathematics, coding and tools. Its producer family has a native one-million-token context and distinct 40K and 80K thinking-budget editions, returning text and structured function-call content.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.
The manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.
For a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.
M1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.
For code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.
MiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.
State whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.
M1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.
Keep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.
The useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MiniMax-M1 | 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "MiniMax-M1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'MiniMax-M1', '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': 'MiniMax-M1', '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 MiniMax-M1, minimax/minimax-m1
/chat/completions
minimax/minimax-m1MiniMax M1 is MiniMax’s hybrid-attention reasoning model for long-source analysis, mathematics, coding and tools. Its producer family has a native one-million-token context and distinct 40K and 80K thinking-budget editions, returning text and structured function-call content.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.
The manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.
For a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.
M1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.
For code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.
MiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.
State whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.
M1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.
Keep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.
The useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits minimax/minimax-m1 | 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "minimax/minimax-m1", "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='minimax/minimax-m1',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='minimax/minimax-m1',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 MiniMax-M1, minimax/minimax-m1
/chat/completions
minimax/minimax-m1MiniMax M1 is MiniMax’s hybrid-attention reasoning model for long-source analysis, mathematics, coding and tools. Its producer family has a native one-million-token context and distinct 40K and 80K thinking-budget editions, returning text and structured function-call content.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax M1 is MiniMax’s hybrid-attention reasoning language model for tasks with long inputs and substantial analysis. It builds on MiniMax-Text-01 with mixture-of-experts components and Lightning Attention, at 456 billion total parameters and 45.9 billion activated per token. The input is written instructions and source context; the output is text such as a solution, code, analysis or function-call information.
The manufacturer describes a native one-million-token context and releases two M1 editions with 40K and 80K thinking budgets. Those budget names refer to the reasoning editions and should not be read as identical universal final-answer ceilings. The generic M1 choice remains distinct from those fixed budget profiles and from the earlier Text-01 model’s inference extension.
For a long-document task, give the materials names, identify the relevant sections and state the question they should support. A useful brief is: “Compare these requirements with the implementation notes, identify each unresolved condition and return the supporting passage beside the finding.” Reserve room in the task context for reasoning and the final answer, not only the initial source material.
M1 uses large-scale reinforcement learning across mathematics and sandbox-based software-engineering problems. The producer introduces CISPO, which clips importance-sampling weights rather than token updates, as part of its reinforcement-learning approach. This is a training distinction of the reasoning release; it does not make a generated code artifact or proposed action an executed result.
For code, provide the relevant implementation, a representative input, expected behaviour and constraints to preserve. Ask for a focused change and the evidence that justifies it. For mathematics, supply the complete condition and request the final result with its assumptions. The maker recommends a stepwise solution with the final result in boxed mathematical notation.
MiniMax recommends temperature 1.0 and top-p 0.95 for its reference profile. It also recommends tailoring the system instruction to the task. A general assistant can use a simple helpful role; a web-development assignment can specify the complete code artifact and the output format. Its illustrative web prompt asks for one complete HTML artifact rather than fragmented snippets.
State whether the answer should be an explanation, a structured comparison or code only. The instruction should identify the actual deliverable and what counts as completion. A visual implementation still needs to run in the intended application, with its observed result returned for any revision.
M1 supports supplied function definitions with names, descriptions, argument types and required fields. The native representation distinguishes reasoning from tool calls and structured JSON arguments. The producer guide shows both a dedicated parser path and manual interpretation of that representation. The application validates and executes the selected functions and returns named results in the conversation for the model to use.
Keep the tool purpose and allowed actions explicit. A document lookup can supply a missing field before the model completes an explanation, while a development tool can return the actual code or error to analyse. A proposed operation is distinct from execution and an observed result.
The useful output is a text solution, code proposal or analytical record tied to the provided sources and actual tool observations. Keep the original M1 identity and its budget distinctions, and do not infer another MiniMax model’s visual inputs, output ceilings or control defaults from the shared family name.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits minimax/minimax-m1 | 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 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 $0.0008 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read — / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "minimax/minimax-m1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'minimax/minimax-m1', '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': 'minimax/minimax-m1', '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 MiniMax-M1, minimax/minimax-m1
/chat/completions
Technical example in English
Check a batch-processing invariant\n\nA worker reads pending jobs, marks each running, then records completion. On restart it reads only pending jobs. Analyse what happens if the process stops after marking a job running but before recording completion. Propose a recovery rule that avoids losing the job and prevents an already completed external action from being repeated blindly. Give two failure-point tests.A failure analysis, a bounded recovery/state-reconciliation proposal and tests for interruption before and after an external action.Recovery checks the original action's outcome before deciding whether another execution is safe.