MiMo-V2.5 is Xiaomi’s native omnimodal model for understanding text, images, video and audio within one architecture. It combines multimodal perception with long-context reasoning and agent workflows. The manufacturer describes a sparse mixture-of-experts model with 310B total parameters and 15B activated parameters. Its response is a textual artifact or tool direction that a supporting application can use; understanding an audio or visual input is separate from generating new media.
The language backbone builds on the MiMo-V2-Flash architecture, combining sliding-window and global attention in a 5:1 pattern with a 128-token local window. Xiaomi adds a dedicated 729M-parameter vision transformer and a 261M-parameter audio encoder initialized from MiMo-Audio. Three multi-token prediction modules support speculative decoding. The local attention window is an architectural detail; the maker specifies a much larger context, up to one million tokens, for the combined task history.
For image analysis, provide a readable source and identify the relationship or detail that the answer must explain. A document task can ask for a table of observed fields with the corresponding page or region; a design task can connect a screenshot’s layout to an implementation requirement. Preserve the source image so small text, counts or spatial observations can be checked. Ask the model to leave unclear evidence visible instead of turning an indistinct mark into a confident value.
For video or audio, pair the supplied material with a focused question and the context needed to interpret it. A useful workflow is to explain a sequence of interface actions from a recording, identify where the observed behavior diverges from the intended steps, and prepare a diagnosis tied to the relevant interval. Preserve chronology and the original recording for review. The text output can become input to a later report, captioning or editing step without claiming that it is itself a newly generated video or voice track.
For an agent task, supply the goal, relevant source material and the input contracts of any tools provided by the application. Keep actual tool outputs in the history so the model can adapt its next step to what occurred. A repository task can combine code, a screenshot of the result and a check output to produce a focused change proposal. Record whether the resulting operation was executed and whether the observed artifact satisfies the requested behavior.
The manufacturer’s training sequence starts with text pre-training, warms up the visual and audio projectors, and continues with multimodal pre-training. Supervised agent training progressively extends the context from 32K through 256K to 1M; reinforcement learning and multi-teacher on-policy distillation then develop perception, reasoning and agent behavior. The maker reports roughly 48 trillion training tokens. This training history explains the combined input and task scope without making a guarantee about a particular recording or repository.
The model summary states support for up to 1M tokens, while the published serving example uses a 262,144-token context configuration. Keep the model’s capacity and a chosen implementation’s working window distinct, and leave room for the generated response and continuing tool results. Xiaomi recommends temperature 1.0 and top_p 0.95 for local inference. Media preprocessing and application controls should follow the specific interface used for the task.
MiMo-V2.5 is the omnimodal sibling of the larger, text-focused MiMo-V2.5-Pro. Retain that edition distinction in a result record. The useful final artifact is an explanation, extraction or change proposal connected to supplied text and media, with uncertain observations and unverified tool outcomes kept available for correction.
", "aboutText": "MiMo-V2.5 is Xiaomi’s native omnimodal model for understanding text, images, video and audio within one architecture. It combines multimodal perception with long-context reasoning and agent workflows. The manufacturer describes a sparse mixture-of-experts model with 310B total parameters and 15B activated parameters. Its response is a textual artifact or tool direction that a supporting application can use; understanding an audio or visual input is separate from generating new media.\n\nThe language backbone builds on the MiMo-V2-Flash architecture, combining sliding-window and global attention in a 5:1 pattern with a 128-token local window. Xiaomi adds a dedicated 729M-parameter vision transformer and a 261M-parameter audio encoder initialized from MiMo-Audio. Three multi-token prediction modules support speculative decoding. The local attention window is an architectural detail; the maker specifies a much larger context, up to one million tokens, for the combined task history.\n\nFor image analysis, provide a readable source and identify the relationship or detail that the answer must explain. A document task can ask for a table of observed fields with the corresponding page or region; a design task can connect a screenshot’s layout to an implementation requirement. Preserve the source image so small text, counts or spatial observations can be checked. Ask the model to leave unclear evidence visible instead of turning an indistinct mark into a confident value.\n\nFor video or audio, pair the supplied material with a focused question and the context needed to interpret it. A useful workflow is to explain a sequence of interface actions from a recording, identify where the observed behavior diverges from the intended steps, and prepare a diagnosis tied to the relevant interval. Preserve chronology and the original recording for review. The text output can become input to a later report, captioning or editing step without claiming that it is itself a newly generated video or voice track.\n\nFor an agent task, supply the goal, relevant source material and the input contracts of any tools provided by the application. Keep actual tool outputs in the history so the model can adapt its next step to what occurred. A repository task can combine code, a screenshot of the result and a check output to produce a focused change proposal. Record whether the resulting operation was executed and whether the observed artifact satisfies the requested behavior.\n\nThe manufacturer’s training sequence starts with text pre-training, warms up the visual and audio projectors, and continues with multimodal pre-training. Supervised agent training progressively extends the context from 32K through 256K to 1M; reinforcement learning and multi-teacher on-policy distillation then develop perception, reasoning and agent behavior. The maker reports roughly 48 trillion training tokens. This training history explains the combined input and task scope without making a guarantee about a particular recording or repository.\n\nThe model summary states support for up to 1M tokens, while the published serving example uses a 262,144-token context configuration. Keep the model’s capacity and a chosen implementation’s working window distinct, and leave room for the generated response and continuing tool results. Xiaomi recommends temperature 1.0 and top_p 0.95 for local inference. Media preprocessing and application controls should follow the specific interface used for the task.\n\nMiMo-V2.5 is the omnimodal sibling of the larger, text-focused MiMo-V2.5-Pro. Retain that edition distinction in a result record. The useful final artifact is an explanation, extraction or change proposal connected to supplied text and media, with uncertain observations and unverified tool outcomes kept available for correction.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Diagnose a workflow from a text timeline\n\nAnalyze this supplied text timeline against the intended order 'select a file, validate it, then import'. Actual log: 00:01 selected sales.csv; 00:02 import started; 00:03 validation failed for missing column; 00:04 import marked complete. Identify the first divergence, explain the inconsistent final state and propose a focused correction with a regression scenario. No recording is attached.A timestamp-linked diagnosis, a correction to stage ordering/state handling and a regression scenario.The diagnosis identifies import before validation and prevents a failed validation from ending in complete status.xiaomi/mimo-v2.5MiMo-V2.5 understands text, images, video and audio in one model for multimodal analysis and agent tasks. Xiaomi documents 310B total parameters, 15B active parameters and up to one million tokens of context, with dedicated vision and audio encoders.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2.5 is Xiaomi’s native omnimodal model for understanding text, images, video and audio within one architecture. It combines multimodal perception with long-context reasoning and agent workflows. The manufacturer describes a sparse mixture-of-experts model with 310B total parameters and 15B activated parameters. Its response is a textual artifact or tool direction that a supporting application can use; understanding an audio or visual input is separate from generating new media.
The language backbone builds on the MiMo-V2-Flash architecture, combining sliding-window and global attention in a 5:1 pattern with a 128-token local window. Xiaomi adds a dedicated 729M-parameter vision transformer and a 261M-parameter audio encoder initialized from MiMo-Audio. Three multi-token prediction modules support speculative decoding. The local attention window is an architectural detail; the maker specifies a much larger context, up to one million tokens, for the combined task history.
For image analysis, provide a readable source and identify the relationship or detail that the answer must explain. A document task can ask for a table of observed fields with the corresponding page or region; a design task can connect a screenshot’s layout to an implementation requirement. Preserve the source image so small text, counts or spatial observations can be checked. Ask the model to leave unclear evidence visible instead of turning an indistinct mark into a confident value.
For video or audio, pair the supplied material with a focused question and the context needed to interpret it. A useful workflow is to explain a sequence of interface actions from a recording, identify where the observed behavior diverges from the intended steps, and prepare a diagnosis tied to the relevant interval. Preserve chronology and the original recording for review. The text output can become input to a later report, captioning or editing step without claiming that it is itself a newly generated video or voice track.
For an agent task, supply the goal, relevant source material and the input contracts of any tools provided by the application. Keep actual tool outputs in the history so the model can adapt its next step to what occurred. A repository task can combine code, a screenshot of the result and a check output to produce a focused change proposal. Record whether the resulting operation was executed and whether the observed artifact satisfies the requested behavior.
The manufacturer’s training sequence starts with text pre-training, warms up the visual and audio projectors, and continues with multimodal pre-training. Supervised agent training progressively extends the context from 32K through 256K to 1M; reinforcement learning and multi-teacher on-policy distillation then develop perception, reasoning and agent behavior. The maker reports roughly 48 trillion training tokens. This training history explains the combined input and task scope without making a guarantee about a particular recording or repository.
The model summary states support for up to 1M tokens, while the published serving example uses a 262,144-token context configuration. Keep the model’s capacity and a chosen implementation’s working window distinct, and leave room for the generated response and continuing tool results. Xiaomi recommends temperature 1.0 and top_p 0.95 for local inference. Media preprocessing and application controls should follow the specific interface used for the task.
MiMo-V2.5 is the omnimodal sibling of the larger, text-focused MiMo-V2.5-Pro. Retain that edition distinction in a result record. The useful final artifact is an explanation, extraction or change proposal connected to supplied text and media, with uncertain observations and unverified tool outcomes kept available for correction.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.5 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00028 / 1K tokens Output · Output tokens $0.00056 / 1K tokens Input · Cache read $0.0000056 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00028 / 1K tokens Output · Output tokens $0.00056 / 1K tokens Input · Cache read $0.0000056 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "xiaomi/mimo-v2.5", "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='xiaomi/mimo-v2.5',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='xiaomi/mimo-v2.5',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 xiaomi/mimo-v2.5
Use the method paths shown above.
xiaomi/mimo-v2.5MiMo-V2.5 understands text, images, video and audio in one model for multimodal analysis and agent tasks. Xiaomi documents 310B total parameters, 15B active parameters and up to one million tokens of context, with dedicated vision and audio encoders.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2.5 is Xiaomi’s native omnimodal model for understanding text, images, video and audio within one architecture. It combines multimodal perception with long-context reasoning and agent workflows. The manufacturer describes a sparse mixture-of-experts model with 310B total parameters and 15B activated parameters. Its response is a textual artifact or tool direction that a supporting application can use; understanding an audio or visual input is separate from generating new media.
The language backbone builds on the MiMo-V2-Flash architecture, combining sliding-window and global attention in a 5:1 pattern with a 128-token local window. Xiaomi adds a dedicated 729M-parameter vision transformer and a 261M-parameter audio encoder initialized from MiMo-Audio. Three multi-token prediction modules support speculative decoding. The local attention window is an architectural detail; the maker specifies a much larger context, up to one million tokens, for the combined task history.
For image analysis, provide a readable source and identify the relationship or detail that the answer must explain. A document task can ask for a table of observed fields with the corresponding page or region; a design task can connect a screenshot’s layout to an implementation requirement. Preserve the source image so small text, counts or spatial observations can be checked. Ask the model to leave unclear evidence visible instead of turning an indistinct mark into a confident value.
For video or audio, pair the supplied material with a focused question and the context needed to interpret it. A useful workflow is to explain a sequence of interface actions from a recording, identify where the observed behavior diverges from the intended steps, and prepare a diagnosis tied to the relevant interval. Preserve chronology and the original recording for review. The text output can become input to a later report, captioning or editing step without claiming that it is itself a newly generated video or voice track.
For an agent task, supply the goal, relevant source material and the input contracts of any tools provided by the application. Keep actual tool outputs in the history so the model can adapt its next step to what occurred. A repository task can combine code, a screenshot of the result and a check output to produce a focused change proposal. Record whether the resulting operation was executed and whether the observed artifact satisfies the requested behavior.
The manufacturer’s training sequence starts with text pre-training, warms up the visual and audio projectors, and continues with multimodal pre-training. Supervised agent training progressively extends the context from 32K through 256K to 1M; reinforcement learning and multi-teacher on-policy distillation then develop perception, reasoning and agent behavior. The maker reports roughly 48 trillion training tokens. This training history explains the combined input and task scope without making a guarantee about a particular recording or repository.
The model summary states support for up to 1M tokens, while the published serving example uses a 262,144-token context configuration. Keep the model’s capacity and a chosen implementation’s working window distinct, and leave room for the generated response and continuing tool results. Xiaomi recommends temperature 1.0 and top_p 0.95 for local inference. Media preprocessing and application controls should follow the specific interface used for the task.
MiMo-V2.5 is the omnimodal sibling of the larger, text-focused MiMo-V2.5-Pro. Retain that edition distinction in a result record. The useful final artifact is an explanation, extraction or change proposal connected to supplied text and media, with uncertain observations and unverified tool outcomes kept available for correction.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.5 | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Context tokens, more than | Context tokens, up to and including | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Context tokens, more than— | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00028 / 1K tokens Output · Output tokens $0.00056 / 1K tokens Input · Cache read $0.0000056 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
| ConfigurationRequest-length tier 1 | Rate schedule— | Context tokens, more than0 | Context tokens, up to and includingNo upper bound | Charge Input · Input tokens $0.00028 / 1K tokens Output · Output tokens $0.00056 / 1K tokens Input · Cache read $0.0000056 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "xiaomi/mimo-v2.5",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'xiaomi/mimo-v2.5', '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': 'xiaomi/mimo-v2.5', '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 xiaomi/mimo-v2.5
Use the method paths shown above.
Technical example in English
Diagnose a workflow from a text timeline\n\nAnalyze this supplied text timeline against the intended order 'select a file, validate it, then import'. Actual log: 00:01 selected sales.csv; 00:02 import started; 00:03 validation failed for missing column; 00:04 import marked complete. Identify the first divergence, explain the inconsistent final state and propose a focused correction with a regression scenario. No recording is attached.A timestamp-linked diagnosis, a correction to stage ordering/state handling and a regression scenario.The diagnosis identifies import before validation and prevents a failed validation from ending in complete status.