MiniMax-Text-01 is MiniMax’s text-focused model for conversations, language tasks and code. Its long-context design is particularly relevant when a question depends on information spread across a large collection of material: a specification together with correspondence, several versions of a document, or a substantial body of reference text. The result is text, including explanations, written content, code and function-call information.
The architecture combines Lightning Attention, conventional Softmax Attention and a mixture of experts. MiniMax reports 456 billion parameters in total, with 45.9 billion activated for each token. The model has 80 layers and 32 experts, using top-two expert routing; a Softmax Attention layer follows each group of seven Lightning Attention layers. These are properties of the Text-01 release, not a claim that every model carrying the MiniMax name uses the same architecture.
MiniMax reports training with a context length of one million tokens and inference extension to as many as four million tokens. This distinction matters when preparing a long-document task: the training length and the extended inference length describe different stages. The manufacturer examines language understanding, instruction following, reasoning, mathematics, coding and the use of long reference material. Treat the available request budget as something to establish for the selected execution configuration, while keeping the question, supporting documents and required answer format explicit.
The published quickstart uses a role-based conversation with a system instruction and a user message, formatted through the model’s own chat template. A useful document-analysis request might provide clearly labelled excerpts and ask: “Compare the acceptance criteria in these documents. For each mismatch, return the document label, the relevant passage, the consequence and the question we need to resolve.” For writing, provide the source facts and intended reader; for code, include the relevant function, expected behaviour and examples that distinguish a correct result. These are illustrative ways to use its text capabilities, rather than predetermined output guarantees.
Function calling is a documented feature of Text-01. The application describes available functions, their purpose and parameters; the parameter definition is expressed with JSON Schema and can include nested objects and arrays. The model can identify that a request needs an external function and propose its name with structured arguments. The manufacturer’s guide walks through a weather-query function, then shows how to parse the proposed call, execute it outside the model and return a structured result to the conversation.
This gives a practical separation of responsibilities. The model chooses a proposed operation from the supplied descriptions; the application decides how to validate and carry it out. For example, a document assistant could be given a lookup function and asked to retrieve the missing product field before composing an explanation. Write precise parameter descriptions, identify required values and make the returned data easy for the model to interpret. Providing a function does not force a call: MiniMax explicitly notes that the model may judge that an ordinary answer is more appropriate.
Text-01 and MiniMax-VL-01 are separate releases. The latter adds visual components; this Text-01 description concerns text processing and its documented tools. A long context also calls for careful source preparation: mark document boundaries, distinguish quoted material from instructions and request a way to associate conclusions with supplied passages. The model card does not establish a separate universal maximum for generated output, so the four-million-token context figure should not be read as an output allowance. Choose an answer length that fits the task, and validate factual statements, extracted fields and generated code against the material or checks you supplied.
", "aboutText": "MiniMax-Text-01 is MiniMax’s text-focused model for conversations, language tasks and code. Its long-context design is particularly relevant when a question depends on information spread across a large collection of material: a specification together with correspondence, several versions of a document, or a substantial body of reference text. The result is text, including explanations, written content, code and function-call information.\n\nThe architecture combines Lightning Attention, conventional Softmax Attention and a mixture of experts. MiniMax reports 456 billion parameters in total, with 45.9 billion activated for each token. The model has 80 layers and 32 experts, using top-two expert routing; a Softmax Attention layer follows each group of seven Lightning Attention layers. These are properties of the Text-01 release, not a claim that every model carrying the MiniMax name uses the same architecture.\n\nMiniMax reports training with a context length of one million tokens and inference extension to as many as four million tokens. This distinction matters when preparing a long-document task: the training length and the extended inference length describe different stages. The manufacturer examines language understanding, instruction following, reasoning, mathematics, coding and the use of long reference material. Treat the available request budget as something to establish for the selected execution configuration, while keeping the question, supporting documents and required answer format explicit.\n\nThe published quickstart uses a role-based conversation with a system instruction and a user message, formatted through the model’s own chat template. A useful document-analysis request might provide clearly labelled excerpts and ask: “Compare the acceptance criteria in these documents. For each mismatch, return the document label, the relevant passage, the consequence and the question we need to resolve.” For writing, provide the source facts and intended reader; for code, include the relevant function, expected behaviour and examples that distinguish a correct result. These are illustrative ways to use its text capabilities, rather than predetermined output guarantees.\n\nFunction calling is a documented feature of Text-01. The application describes available functions, their purpose and parameters; the parameter definition is expressed with JSON Schema and can include nested objects and arrays. The model can identify that a request needs an external function and propose its name with structured arguments. The manufacturer’s guide walks through a weather-query function, then shows how to parse the proposed call, execute it outside the model and return a structured result to the conversation.\n\nThis gives a practical separation of responsibilities. The model chooses a proposed operation from the supplied descriptions; the application decides how to validate and carry it out. For example, a document assistant could be given a lookup function and asked to retrieve the missing product field before composing an explanation. Write precise parameter descriptions, identify required values and make the returned data easy for the model to interpret. Providing a function does not force a call: MiniMax explicitly notes that the model may judge that an ordinary answer is more appropriate.\n\nText-01 and MiniMax-VL-01 are separate releases. The latter adds visual components; this Text-01 description concerns text processing and its documented tools. A long context also calls for careful source preparation: mark document boundaries, distinguish quoted material from instructions and request a way to associate conclusions with supplied passages. The model card does not establish a separate universal maximum for generated output, so the four-million-token context figure should not be read as an output allowance. Choose an answer length that fits the task, and validate factual statements, extracted fields and generated code against the material or checks you supplied.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Reconcile acceptance documents\n\nSpecification S1 says: 'An export is accepted when it contains all active accounts.' Email E1 says: 'Include suspended accounts in the acceptance sample.' Test note T1 says: 'The sample contains only active accounts.' Produce a mismatch record with source labels, practical consequence and one question for the owner. Do not silently choose a new acceptance rule.A source-labeled mismatch record, consequence and clarification question.The record must distinguish the coverage rule from the actual sample rather than declare acceptance achieved.MiniMax-Text-01MiniMax-Text-01 is a long-context text model for document analysis, writing, coding and tool-assisted workflows. It combines hybrid attention with a mixture of experts and can propose function calls with structured arguments.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax-Text-01 is MiniMax’s text-focused model for conversations, language tasks and code. Its long-context design is particularly relevant when a question depends on information spread across a large collection of material: a specification together with correspondence, several versions of a document, or a substantial body of reference text. The result is text, including explanations, written content, code and function-call information.
The architecture combines Lightning Attention, conventional Softmax Attention and a mixture of experts. MiniMax reports 456 billion parameters in total, with 45.9 billion activated for each token. The model has 80 layers and 32 experts, using top-two expert routing; a Softmax Attention layer follows each group of seven Lightning Attention layers. These are properties of the Text-01 release, not a claim that every model carrying the MiniMax name uses the same architecture.
MiniMax reports training with a context length of one million tokens and inference extension to as many as four million tokens. This distinction matters when preparing a long-document task: the training length and the extended inference length describe different stages. The manufacturer examines language understanding, instruction following, reasoning, mathematics, coding and the use of long reference material. Treat the available request budget as something to establish for the selected execution configuration, while keeping the question, supporting documents and required answer format explicit.
The published quickstart uses a role-based conversation with a system instruction and a user message, formatted through the model’s own chat template. A useful document-analysis request might provide clearly labelled excerpts and ask: “Compare the acceptance criteria in these documents. For each mismatch, return the document label, the relevant passage, the consequence and the question we need to resolve.” For writing, provide the source facts and intended reader; for code, include the relevant function, expected behaviour and examples that distinguish a correct result. These are illustrative ways to use its text capabilities, rather than predetermined output guarantees.
Function calling is a documented feature of Text-01. The application describes available functions, their purpose and parameters; the parameter definition is expressed with JSON Schema and can include nested objects and arrays. The model can identify that a request needs an external function and propose its name with structured arguments. The manufacturer’s guide walks through a weather-query function, then shows how to parse the proposed call, execute it outside the model and return a structured result to the conversation.
This gives a practical separation of responsibilities. The model chooses a proposed operation from the supplied descriptions; the application decides how to validate and carry it out. For example, a document assistant could be given a lookup function and asked to retrieve the missing product field before composing an explanation. Write precise parameter descriptions, identify required values and make the returned data easy for the model to interpret. Providing a function does not force a call: MiniMax explicitly notes that the model may judge that an ordinary answer is more appropriate.
Text-01 and MiniMax-VL-01 are separate releases. The latter adds visual components; this Text-01 description concerns text processing and its documented tools. A long context also calls for careful source preparation: mark document boundaries, distinguish quoted material from instructions and request a way to associate conclusions with supplied passages. The model card does not establish a separate universal maximum for generated output, so the four-million-token context figure should not be read as an output allowance. Choose an answer length that fits the task, and validate factual statements, extracted fields and generated code against the material or checks you supplied.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MiniMax-Text-01 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.000308 / 1K tokens Output · Output tokens $0.002464 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "MiniMax-Text-01", "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-Text-01',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-Text-01',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-Text-01
Use the method paths shown above.
MiniMax-Text-01MiniMax-Text-01 is a long-context text model for document analysis, writing, coding and tool-assisted workflows. It combines hybrid attention with a mixture of experts and can propose function calls with structured arguments.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiniMax-Text-01 is MiniMax’s text-focused model for conversations, language tasks and code. Its long-context design is particularly relevant when a question depends on information spread across a large collection of material: a specification together with correspondence, several versions of a document, or a substantial body of reference text. The result is text, including explanations, written content, code and function-call information.
The architecture combines Lightning Attention, conventional Softmax Attention and a mixture of experts. MiniMax reports 456 billion parameters in total, with 45.9 billion activated for each token. The model has 80 layers and 32 experts, using top-two expert routing; a Softmax Attention layer follows each group of seven Lightning Attention layers. These are properties of the Text-01 release, not a claim that every model carrying the MiniMax name uses the same architecture.
MiniMax reports training with a context length of one million tokens and inference extension to as many as four million tokens. This distinction matters when preparing a long-document task: the training length and the extended inference length describe different stages. The manufacturer examines language understanding, instruction following, reasoning, mathematics, coding and the use of long reference material. Treat the available request budget as something to establish for the selected execution configuration, while keeping the question, supporting documents and required answer format explicit.
The published quickstart uses a role-based conversation with a system instruction and a user message, formatted through the model’s own chat template. A useful document-analysis request might provide clearly labelled excerpts and ask: “Compare the acceptance criteria in these documents. For each mismatch, return the document label, the relevant passage, the consequence and the question we need to resolve.” For writing, provide the source facts and intended reader; for code, include the relevant function, expected behaviour and examples that distinguish a correct result. These are illustrative ways to use its text capabilities, rather than predetermined output guarantees.
Function calling is a documented feature of Text-01. The application describes available functions, their purpose and parameters; the parameter definition is expressed with JSON Schema and can include nested objects and arrays. The model can identify that a request needs an external function and propose its name with structured arguments. The manufacturer’s guide walks through a weather-query function, then shows how to parse the proposed call, execute it outside the model and return a structured result to the conversation.
This gives a practical separation of responsibilities. The model chooses a proposed operation from the supplied descriptions; the application decides how to validate and carry it out. For example, a document assistant could be given a lookup function and asked to retrieve the missing product field before composing an explanation. Write precise parameter descriptions, identify required values and make the returned data easy for the model to interpret. Providing a function does not force a call: MiniMax explicitly notes that the model may judge that an ordinary answer is more appropriate.
Text-01 and MiniMax-VL-01 are separate releases. The latter adds visual components; this Text-01 description concerns text processing and its documented tools. A long context also calls for careful source preparation: mark document boundaries, distinguish quoted material from instructions and request a way to associate conclusions with supplied passages. The model card does not establish a separate universal maximum for generated output, so the four-million-token context figure should not be read as an output allowance. Choose an answer length that fits the task, and validate factual statements, extracted fields and generated code against the material or checks you supplied.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits MiniMax-Text-01 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
| Configuration | Rate schedule | Charge |
|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Charge Input · Input tokens $0.000308 / 1K tokens Output · Output tokens $0.002464 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "MiniMax-Text-01",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-Text-01', '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-Text-01', '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-Text-01
Use the method paths shown above.
Technical example in English
Reconcile acceptance documents\n\nSpecification S1 says: 'An export is accepted when it contains all active accounts.' Email E1 says: 'Include suspended accounts in the acceptance sample.' Test note T1 says: 'The sample contains only active accounts.' Produce a mismatch record with source labels, practical consequence and one question for the owner. Do not silently choose a new acceptance rule.A source-labeled mismatch record, consequence and clarification question.The record must distinguish the coverage rule from the actual sample rather than declare acceptance achieved.