Foundation for agent work
MiMo-V2-Pro is Xiaomi’s flagship foundation model for complex agent workloads and software engineering. Its role is to reason about a task, organize the required steps and use information returned by tools to continue toward a defined result. The model’s emphasis goes beyond composing a single answer: it is designed around connected work in which earlier decisions and observations affect what happens next.
Scale and efficient architecture
The manufacturer describes more than 1 trillion total parameters with 42 billion active parameters. Pro extends the hybrid attention approach of MiMo-V2-Flash, using a 7:1 balance of sliding-window to global attention. A lightweight multi-token prediction layer supports generation, and the advertised context reaches 1 million tokens. These are architectural and context properties of Pro; they do not specify the execution speed, memory allocation or request limits of a particular integration.
Release lineage
Hunter Alpha is identified by Xiaomi as an early internal test build preceding MiMo-V2-Pro. The released Pro model has its own name and refinements to long-context work and agent-scenario stability. This distinction matters when comparing descriptions or retaining a model identity: an earlier test build, MiMo-V2-Flash and MiMo-V2-Omni each have a separate role and specification.
Built for agents
The model is fine-tuned through supervised learning and reinforcement learning across varied agent frameworks, with attention to tool calls and multi-step reasoning. Prepare a task with an observable completion condition and descriptions of the available tools. For example, a project assistant can receive a change request, examine the supplied modules, propose the affected components and continue after a tool returns a build error. The useful output is a sequence of decisions tied to actual observations, followed by the requested code, explanation or work summary. The connected environment performs the actions.
Software engineering and frontend tasks
Xiaomi highlights system design, task planning and code-oriented problem solving. Its demonstrations include interactive web pages and a browser-based game produced within an agent environment. An illustrative development brief can specify page behavior, navigation, data states and a responsive layout, then ask for an implementation and checks against those requirements. For an existing project, supply the current files, the failing case and the interfaces that must remain unchanged. Ask for a focused change and an explanation of the dependencies it touches rather than an unrelated replacement application.
Long context and a checkable result
The context of up to 1 million tokens is useful when several files, documents, instructions and prior observations belong to the same task. Organize that material by its role: authoritative requirements, current code, reference examples and tool results. Specify the final artifact and its acceptance conditions before asking the agent to proceed. A documentation task might need a comparison with unresolved questions; an engineering task might need a patch and a record of what was checked.
Practical limitations and edition scope
A long context provides room for material but does not guarantee that a generated project is correct or that every requirement has been satisfied. Return actual errors and observations for the next step and validate the result in the intended environment. The manufacturer explicitly frames robustness across complex real tasks as something to assess and improve. This description covers the text-and-tool agent specialization of MiMo-V2-Pro; modality features of Omni and specifications of later MiMo generations belong to their respective models. The tools, available parameters and output handling remain properties of the connected application.
", "aboutText": "Foundation for agent work\n\nMiMo-V2-Pro is Xiaomi’s flagship foundation model for complex agent workloads and software engineering. Its role is to reason about a task, organize the required steps and use information returned by tools to continue toward a defined result. The model’s emphasis goes beyond composing a single answer: it is designed around connected work in which earlier decisions and observations affect what happens next.\n\nScale and efficient architecture\n\nThe manufacturer describes more than 1 trillion total parameters with 42 billion active parameters. Pro extends the hybrid attention approach of MiMo-V2-Flash, using a 7:1 balance of sliding-window to global attention. A lightweight multi-token prediction layer supports generation, and the advertised context reaches 1 million tokens. These are architectural and context properties of Pro; they do not specify the execution speed, memory allocation or request limits of a particular integration.\n\nRelease lineage\n\nHunter Alpha is identified by Xiaomi as an early internal test build preceding MiMo-V2-Pro. The released Pro model has its own name and refinements to long-context work and agent-scenario stability. This distinction matters when comparing descriptions or retaining a model identity: an earlier test build, MiMo-V2-Flash and MiMo-V2-Omni each have a separate role and specification.\n\nBuilt for agents\n\nThe model is fine-tuned through supervised learning and reinforcement learning across varied agent frameworks, with attention to tool calls and multi-step reasoning. Prepare a task with an observable completion condition and descriptions of the available tools. For example, a project assistant can receive a change request, examine the supplied modules, propose the affected components and continue after a tool returns a build error. The useful output is a sequence of decisions tied to actual observations, followed by the requested code, explanation or work summary. The connected environment performs the actions.\n\nSoftware engineering and frontend tasks\n\nXiaomi highlights system design, task planning and code-oriented problem solving. Its demonstrations include interactive web pages and a browser-based game produced within an agent environment. An illustrative development brief can specify page behavior, navigation, data states and a responsive layout, then ask for an implementation and checks against those requirements. For an existing project, supply the current files, the failing case and the interfaces that must remain unchanged. Ask for a focused change and an explanation of the dependencies it touches rather than an unrelated replacement application.\n\nLong context and a checkable result\n\nThe context of up to 1 million tokens is useful when several files, documents, instructions and prior observations belong to the same task. Organize that material by its role: authoritative requirements, current code, reference examples and tool results. Specify the final artifact and its acceptance conditions before asking the agent to proceed. A documentation task might need a comparison with unresolved questions; an engineering task might need a patch and a record of what was checked.\n\nPractical limitations and edition scope\n\nA long context provides room for material but does not guarantee that a generated project is correct or that every requirement has been satisfied. Return actual errors and observations for the next step and validate the result in the intended environment. The manufacturer explicitly frames robustness across complex real tasks as something to assess and improve. This description covers the text-and-tool agent specialization of MiMo-V2-Pro; modality features of Omni and specifications of later MiMo generations belong to their respective models. The tools, available parameters and output handling remain properties of the connected application.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Correct an error-state transition\n\nA text specification says a search box has idle, loading, results and error states. Existing logic sets loading=true before fetch and false only on success, so failures leave the spinner visible. Propose pseudocode that preserves results on success, shows an error on failure and always clears loading. Include the two distinguishing checks.Focused async pseudocode and success/failure checks covering final loading state and visible result or error.Check that loading is cleared in both branches without suppressing the error.mimo-v2-proMiMo-V2-Pro is Xiaomi’s agent-focused text model for software engineering, multi-step planning and tool-driven work. Its context of up to 1 million tokens helps keep substantial project material, task constraints and successive observations within a coherent workflow.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Foundation for agent work
MiMo-V2-Pro is Xiaomi’s flagship foundation model for complex agent workloads and software engineering. Its role is to reason about a task, organize the required steps and use information returned by tools to continue toward a defined result. The model’s emphasis goes beyond composing a single answer: it is designed around connected work in which earlier decisions and observations affect what happens next.
Scale and efficient architecture
The manufacturer describes more than 1 trillion total parameters with 42 billion active parameters. Pro extends the hybrid attention approach of MiMo-V2-Flash, using a 7:1 balance of sliding-window to global attention. A lightweight multi-token prediction layer supports generation, and the advertised context reaches 1 million tokens. These are architectural and context properties of Pro; they do not specify the execution speed, memory allocation or request limits of a particular integration.
Release lineage
Hunter Alpha is identified by Xiaomi as an early internal test build preceding MiMo-V2-Pro. The released Pro model has its own name and refinements to long-context work and agent-scenario stability. This distinction matters when comparing descriptions or retaining a model identity: an earlier test build, MiMo-V2-Flash and MiMo-V2-Omni each have a separate role and specification.
Built for agents
The model is fine-tuned through supervised learning and reinforcement learning across varied agent frameworks, with attention to tool calls and multi-step reasoning. Prepare a task with an observable completion condition and descriptions of the available tools. For example, a project assistant can receive a change request, examine the supplied modules, propose the affected components and continue after a tool returns a build error. The useful output is a sequence of decisions tied to actual observations, followed by the requested code, explanation or work summary. The connected environment performs the actions.
Software engineering and frontend tasks
Xiaomi highlights system design, task planning and code-oriented problem solving. Its demonstrations include interactive web pages and a browser-based game produced within an agent environment. An illustrative development brief can specify page behavior, navigation, data states and a responsive layout, then ask for an implementation and checks against those requirements. For an existing project, supply the current files, the failing case and the interfaces that must remain unchanged. Ask for a focused change and an explanation of the dependencies it touches rather than an unrelated replacement application.
Long context and a checkable result
The context of up to 1 million tokens is useful when several files, documents, instructions and prior observations belong to the same task. Organize that material by its role: authoritative requirements, current code, reference examples and tool results. Specify the final artifact and its acceptance conditions before asking the agent to proceed. A documentation task might need a comparison with unresolved questions; an engineering task might need a patch and a record of what was checked.
Practical limitations and edition scope
A long context provides room for material but does not guarantee that a generated project is correct or that every requirement has been satisfied. Return actual errors and observations for the next step and validate the result in the intended environment. The manufacturer explicitly frames robustness across complex real tasks as something to assess and improve. This description covers the text-and-tool agent specialization of MiMo-V2-Pro; modality features of Omni and specifications of later MiMo generations belong to their respective models. The tools, available parameters and output handling remain properties of the connected application.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mimo-v2-pro | 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 $0.0022 / 1K tokens Output · Output tokens $0.0066 / 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": "mimo-v2-pro", "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='mimo-v2-pro',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='mimo-v2-pro',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 mimo-v2-pro
Use the method paths shown above.
mimo-v2-proMiMo-V2-Pro is Xiaomi’s agent-focused text model for software engineering, multi-step planning and tool-driven work. Its context of up to 1 million tokens helps keep substantial project material, task constraints and successive observations within a coherent workflow.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Foundation for agent work
MiMo-V2-Pro is Xiaomi’s flagship foundation model for complex agent workloads and software engineering. Its role is to reason about a task, organize the required steps and use information returned by tools to continue toward a defined result. The model’s emphasis goes beyond composing a single answer: it is designed around connected work in which earlier decisions and observations affect what happens next.
Scale and efficient architecture
The manufacturer describes more than 1 trillion total parameters with 42 billion active parameters. Pro extends the hybrid attention approach of MiMo-V2-Flash, using a 7:1 balance of sliding-window to global attention. A lightweight multi-token prediction layer supports generation, and the advertised context reaches 1 million tokens. These are architectural and context properties of Pro; they do not specify the execution speed, memory allocation or request limits of a particular integration.
Release lineage
Hunter Alpha is identified by Xiaomi as an early internal test build preceding MiMo-V2-Pro. The released Pro model has its own name and refinements to long-context work and agent-scenario stability. This distinction matters when comparing descriptions or retaining a model identity: an earlier test build, MiMo-V2-Flash and MiMo-V2-Omni each have a separate role and specification.
Built for agents
The model is fine-tuned through supervised learning and reinforcement learning across varied agent frameworks, with attention to tool calls and multi-step reasoning. Prepare a task with an observable completion condition and descriptions of the available tools. For example, a project assistant can receive a change request, examine the supplied modules, propose the affected components and continue after a tool returns a build error. The useful output is a sequence of decisions tied to actual observations, followed by the requested code, explanation or work summary. The connected environment performs the actions.
Software engineering and frontend tasks
Xiaomi highlights system design, task planning and code-oriented problem solving. Its demonstrations include interactive web pages and a browser-based game produced within an agent environment. An illustrative development brief can specify page behavior, navigation, data states and a responsive layout, then ask for an implementation and checks against those requirements. For an existing project, supply the current files, the failing case and the interfaces that must remain unchanged. Ask for a focused change and an explanation of the dependencies it touches rather than an unrelated replacement application.
Long context and a checkable result
The context of up to 1 million tokens is useful when several files, documents, instructions and prior observations belong to the same task. Organize that material by its role: authoritative requirements, current code, reference examples and tool results. Specify the final artifact and its acceptance conditions before asking the agent to proceed. A documentation task might need a comparison with unresolved questions; an engineering task might need a patch and a record of what was checked.
Practical limitations and edition scope
A long context provides room for material but does not guarantee that a generated project is correct or that every requirement has been satisfied. Return actual errors and observations for the next step and validate the result in the intended environment. The manufacturer explicitly frames robustness across complex real tasks as something to assess and improve. This description covers the text-and-tool agent specialization of MiMo-V2-Pro; modality features of Omni and specifications of later MiMo generations belong to their respective models. The tools, available parameters and output handling remain properties of the connected application.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mimo-v2-pro | 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 $0.0022 / 1K tokens Output · Output tokens $0.0066 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "mimo-v2-pro",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'mimo-v2-pro', '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': 'mimo-v2-pro', '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 mimo-v2-pro
Use the method paths shown above.
Technical example in English
Correct an error-state transition\n\nA text specification says a search box has idle, loading, results and error states. Existing logic sets loading=true before fetch and false only on success, so failures leave the spinner visible. Propose pseudocode that preserves results on success, shows an error on failure and always clears loading. Include the two distinguishing checks.Focused async pseudocode and success/failure checks covering final loading state and visible result or error.Check that loading is cleared in both branches without suppressing the error.