MiMo-V2-Omni is Xiaomi’s model for understanding text, images, audio and video together and using that understanding in an agentic task. Its architecture brings dedicated image, video and audio encoders into a shared backbone. The central distinction is joint perception: a question can depend on what is visible, what is audible and what the accompanying text says, rather than requiring each source to be interpreted in isolation. Its outputs support written analysis and structured tool requests.
Xiaomi describes the model as learning to connect perception, anticipation and action. It interprets the current scene, reasons about what may happen next and selects a useful next step. This is particularly relevant to recorded material where the significance of an event depends on more than one modality. For example, provide a clip and ask it to identify the sequence of visible actions, the relevant sounds and how they relate. Specify whether you need an event summary, an explanation of the scene or a list of observations for later review. Keep observed facts separate from predictions: an interpretation of what could happen is not proof that the event will occur.
Audio understanding is broader than transcription in the manufacturer’s description. Xiaomi highlights environmental sound classification, distinguishing multiple speakers and reasoning jointly over audio and visuals. It also demonstrates a structured summary of a long, uninterrupted podcast. For an audio task, state the topics or questions that matter and the output you need, such as an outline of arguments, points of disagreement or a summary by theme. For a video with speech, ask the model to connect a statement to the action or on-screen material it accompanies. If exact wording or speaker attribution matters, ask it to flag ambiguity rather than silently resolve it.
On the visual side, the producer highlights multidisciplinary image reasoning and complex chart analysis. Supply a readable chart and explain the analytical question, including what the axes, units and categories mean when that information is not clear in the image. An illustrative request is to describe the main pattern, identify an apparent change and distinguish values directly visible in the chart from a proposed explanation. For an image comparison, define the differences you care about and ask for a table tied to visible evidence. Prepare the source material so labels and relevant details are legible; a useful analysis depends on what the input actually contains.
MiMo-V2-Omni also supports structured tool calling and UI grounding. The manufacturer’s demonstrations connect the model to an agent environment that supplies browser control, file access and terminal interaction. The model interprets the current state, decides what to do and issues an action; the environment executes it and returns the updated state. For a task in that style, provide a clear goal, the relevant screen or material and descriptions of permitted actions. Ask the model to connect each next step to the observed state and to use the returned result before continuing. A tool request and the outcome of the executed action are separate pieces of information.
Xiaomi’s multimedia-production example follows the same division of work: the model designs the content and directs a programmatic process, while tools create and handle the actual media files. You can use the model to prepare a scene plan, a written explanation of a recording or a sequence of tool actions. The specific deliverable should be defined at the start, including its required contents and how completion will be recognised. Keep file creation, rendering and application operations tied to the tools that perform them, rather than treating a text response as an already-created asset.
For practical video work, supply recorded clips and a focused question. Xiaomi distinguishes this clip-processing workflow from real-time perception in its research roadmap, so continuous live control should not be assumed from a recorded demonstration. Its examples also show sustained tasks through an agent environment, rather than establishing an unlimited planning horizon or a universal completion-time promise. Review scene interpretations, chart values, speaker associations and proposed actions against the original inputs. MiMo-V2-Omni’s useful role is to bring the modalities into one reasoned interpretation of the task, with a result whose evidence and action outcomes can be inspected.
", "aboutText": "MiMo-V2-Omni is Xiaomi’s model for understanding text, images, audio and video together and using that understanding in an agentic task. Its architecture brings dedicated image, video and audio encoders into a shared backbone. The central distinction is joint perception: a question can depend on what is visible, what is audible and what the accompanying text says, rather than requiring each source to be interpreted in isolation. Its outputs support written analysis and structured tool requests.\n\nXiaomi describes the model as learning to connect perception, anticipation and action. It interprets the current scene, reasons about what may happen next and selects a useful next step. This is particularly relevant to recorded material where the significance of an event depends on more than one modality. For example, provide a clip and ask it to identify the sequence of visible actions, the relevant sounds and how they relate. Specify whether you need an event summary, an explanation of the scene or a list of observations for later review. Keep observed facts separate from predictions: an interpretation of what could happen is not proof that the event will occur.\n\nAudio understanding is broader than transcription in the manufacturer’s description. Xiaomi highlights environmental sound classification, distinguishing multiple speakers and reasoning jointly over audio and visuals. It also demonstrates a structured summary of a long, uninterrupted podcast. For an audio task, state the topics or questions that matter and the output you need, such as an outline of arguments, points of disagreement or a summary by theme. For a video with speech, ask the model to connect a statement to the action or on-screen material it accompanies. If exact wording or speaker attribution matters, ask it to flag ambiguity rather than silently resolve it.\n\nOn the visual side, the producer highlights multidisciplinary image reasoning and complex chart analysis. Supply a readable chart and explain the analytical question, including what the axes, units and categories mean when that information is not clear in the image. An illustrative request is to describe the main pattern, identify an apparent change and distinguish values directly visible in the chart from a proposed explanation. For an image comparison, define the differences you care about and ask for a table tied to visible evidence. Prepare the source material so labels and relevant details are legible; a useful analysis depends on what the input actually contains.\n\nMiMo-V2-Omni also supports structured tool calling and UI grounding. The manufacturer’s demonstrations connect the model to an agent environment that supplies browser control, file access and terminal interaction. The model interprets the current state, decides what to do and issues an action; the environment executes it and returns the updated state. For a task in that style, provide a clear goal, the relevant screen or material and descriptions of permitted actions. Ask the model to connect each next step to the observed state and to use the returned result before continuing. A tool request and the outcome of the executed action are separate pieces of information.\n\nXiaomi’s multimedia-production example follows the same division of work: the model designs the content and directs a programmatic process, while tools create and handle the actual media files. You can use the model to prepare a scene plan, a written explanation of a recording or a sequence of tool actions. The specific deliverable should be defined at the start, including its required contents and how completion will be recognised. Keep file creation, rendering and application operations tied to the tools that perform them, rather than treating a text response as an already-created asset.\n\nFor practical video work, supply recorded clips and a focused question. Xiaomi distinguishes this clip-processing workflow from real-time perception in its research roadmap, so continuous live control should not be assumed from a recorded demonstration. Its examples also show sustained tasks through an agent environment, rather than establishing an unlimited planning horizon or a universal completion-time promise. Review scene interpretations, chart values, speaker associations and proposed actions against the original inputs. MiMo-V2-Omni’s useful role is to bring the modalities into one reasoned interpretation of the task, with a result whose evidence and action outcomes can be inspected.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Summarize a supplied podcast transcript\n\nSummarize this podcast transcript by theme. Speaker A: Smaller batches reduced our queue, but we measured only one week. Speaker B: Returns rose that week; we have not linked them to batch size. Speaker A: We should compare another week before expanding. Return agreements, unresolved relationships and the proposed next step, preserving speaker attribution.A theme-based summary with speaker labels, the agreed next step and unresolved causal claims.Check that the summary does not attribute the rise in returns to batch size or report a multi-week measurement.mimo-v2-omniMiMo-V2-Omni is Xiaomi’s model for joint text, image, audio and video understanding. It connects perception with structured tool requests and interface grounding, supporting scene analysis, chart interpretation and agentic workflows that use actual tool results.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2-Omni is Xiaomi’s model for understanding text, images, audio and video together and using that understanding in an agentic task. Its architecture brings dedicated image, video and audio encoders into a shared backbone. The central distinction is joint perception: a question can depend on what is visible, what is audible and what the accompanying text says, rather than requiring each source to be interpreted in isolation. Its outputs support written analysis and structured tool requests.
Xiaomi describes the model as learning to connect perception, anticipation and action. It interprets the current scene, reasons about what may happen next and selects a useful next step. This is particularly relevant to recorded material where the significance of an event depends on more than one modality. For example, provide a clip and ask it to identify the sequence of visible actions, the relevant sounds and how they relate. Specify whether you need an event summary, an explanation of the scene or a list of observations for later review. Keep observed facts separate from predictions: an interpretation of what could happen is not proof that the event will occur.
Audio understanding is broader than transcription in the manufacturer’s description. Xiaomi highlights environmental sound classification, distinguishing multiple speakers and reasoning jointly over audio and visuals. It also demonstrates a structured summary of a long, uninterrupted podcast. For an audio task, state the topics or questions that matter and the output you need, such as an outline of arguments, points of disagreement or a summary by theme. For a video with speech, ask the model to connect a statement to the action or on-screen material it accompanies. If exact wording or speaker attribution matters, ask it to flag ambiguity rather than silently resolve it.
On the visual side, the producer highlights multidisciplinary image reasoning and complex chart analysis. Supply a readable chart and explain the analytical question, including what the axes, units and categories mean when that information is not clear in the image. An illustrative request is to describe the main pattern, identify an apparent change and distinguish values directly visible in the chart from a proposed explanation. For an image comparison, define the differences you care about and ask for a table tied to visible evidence. Prepare the source material so labels and relevant details are legible; a useful analysis depends on what the input actually contains.
MiMo-V2-Omni also supports structured tool calling and UI grounding. The manufacturer’s demonstrations connect the model to an agent environment that supplies browser control, file access and terminal interaction. The model interprets the current state, decides what to do and issues an action; the environment executes it and returns the updated state. For a task in that style, provide a clear goal, the relevant screen or material and descriptions of permitted actions. Ask the model to connect each next step to the observed state and to use the returned result before continuing. A tool request and the outcome of the executed action are separate pieces of information.
Xiaomi’s multimedia-production example follows the same division of work: the model designs the content and directs a programmatic process, while tools create and handle the actual media files. You can use the model to prepare a scene plan, a written explanation of a recording or a sequence of tool actions. The specific deliverable should be defined at the start, including its required contents and how completion will be recognised. Keep file creation, rendering and application operations tied to the tools that perform them, rather than treating a text response as an already-created asset.
For practical video work, supply recorded clips and a focused question. Xiaomi distinguishes this clip-processing workflow from real-time perception in its research roadmap, so continuous live control should not be assumed from a recorded demonstration. Its examples also show sustained tasks through an agent environment, rather than establishing an unlimited planning horizon or a universal completion-time promise. Review scene interpretations, chart values, speaker associations and proposed actions against the original inputs. MiMo-V2-Omni’s useful role is to bring the modalities into one reasoned interpretation of the task, with a result whose evidence and action outcomes can be inspected.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mimo-v2-omni | 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 $0.00088 / 1K tokens Output · Output tokens $0.0044 / 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-omni", "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-omni',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-omni',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-omni
Use the method paths shown above.
mimo-v2-omniMiMo-V2-Omni is Xiaomi’s model for joint text, image, audio and video understanding. It connects perception with structured tool requests and interface grounding, supporting scene analysis, chart interpretation and agentic workflows that use actual tool results.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2-Omni is Xiaomi’s model for understanding text, images, audio and video together and using that understanding in an agentic task. Its architecture brings dedicated image, video and audio encoders into a shared backbone. The central distinction is joint perception: a question can depend on what is visible, what is audible and what the accompanying text says, rather than requiring each source to be interpreted in isolation. Its outputs support written analysis and structured tool requests.
Xiaomi describes the model as learning to connect perception, anticipation and action. It interprets the current scene, reasons about what may happen next and selects a useful next step. This is particularly relevant to recorded material where the significance of an event depends on more than one modality. For example, provide a clip and ask it to identify the sequence of visible actions, the relevant sounds and how they relate. Specify whether you need an event summary, an explanation of the scene or a list of observations for later review. Keep observed facts separate from predictions: an interpretation of what could happen is not proof that the event will occur.
Audio understanding is broader than transcription in the manufacturer’s description. Xiaomi highlights environmental sound classification, distinguishing multiple speakers and reasoning jointly over audio and visuals. It also demonstrates a structured summary of a long, uninterrupted podcast. For an audio task, state the topics or questions that matter and the output you need, such as an outline of arguments, points of disagreement or a summary by theme. For a video with speech, ask the model to connect a statement to the action or on-screen material it accompanies. If exact wording or speaker attribution matters, ask it to flag ambiguity rather than silently resolve it.
On the visual side, the producer highlights multidisciplinary image reasoning and complex chart analysis. Supply a readable chart and explain the analytical question, including what the axes, units and categories mean when that information is not clear in the image. An illustrative request is to describe the main pattern, identify an apparent change and distinguish values directly visible in the chart from a proposed explanation. For an image comparison, define the differences you care about and ask for a table tied to visible evidence. Prepare the source material so labels and relevant details are legible; a useful analysis depends on what the input actually contains.
MiMo-V2-Omni also supports structured tool calling and UI grounding. The manufacturer’s demonstrations connect the model to an agent environment that supplies browser control, file access and terminal interaction. The model interprets the current state, decides what to do and issues an action; the environment executes it and returns the updated state. For a task in that style, provide a clear goal, the relevant screen or material and descriptions of permitted actions. Ask the model to connect each next step to the observed state and to use the returned result before continuing. A tool request and the outcome of the executed action are separate pieces of information.
Xiaomi’s multimedia-production example follows the same division of work: the model designs the content and directs a programmatic process, while tools create and handle the actual media files. You can use the model to prepare a scene plan, a written explanation of a recording or a sequence of tool actions. The specific deliverable should be defined at the start, including its required contents and how completion will be recognised. Keep file creation, rendering and application operations tied to the tools that perform them, rather than treating a text response as an already-created asset.
For practical video work, supply recorded clips and a focused question. Xiaomi distinguishes this clip-processing workflow from real-time perception in its research roadmap, so continuous live control should not be assumed from a recorded demonstration. Its examples also show sustained tasks through an agent environment, rather than establishing an unlimited planning horizon or a universal completion-time promise. Review scene interpretations, chart values, speaker associations and proposed actions against the original inputs. MiMo-V2-Omni’s useful role is to bring the modalities into one reasoned interpretation of the task, with a result whose evidence and action outcomes can be inspected.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits mimo-v2-omni | 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 $0.00088 / 1K tokens Output · Output tokens $0.0044 / 1K tokens Input · Cache read $0 / 1K tokens Input · Cache write $0 / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "mimo-v2-omni",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-omni', '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-omni', '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-omni
Use the method paths shown above.
Technical example in English
Summarize a supplied podcast transcript\n\nSummarize this podcast transcript by theme. Speaker A: Smaller batches reduced our queue, but we measured only one week. Speaker B: Returns rose that week; we have not linked them to batch size. Speaker A: We should compare another week before expanding. Return agreements, unresolved relationships and the proposed next step, preserving speaker attribution.A theme-based summary with speaker labels, the agreed next step and unresolved causal claims.Check that the summary does not attribute the rise in returns to batch size or report a multi-week measurement.