MiMo-V2.6-Flash is Xiaomi’s efficiency-balanced model in the MiMo-V2.6 series. It combines text, image, video and audio understanding in one architecture, with a textual response that can guide a supporting application’s next step. Its task scope covers software engineering, general agent work, visual workflows and cybersecurity analysis. Flash is a separate smaller model from V2.6-Pro, with its own parameter scale rather than simply a shorter response setting.
The maker’s released Flash profile describes a sparse mixture-of-experts model with 309B total and 15B activated parameters. Its 48-layer backbone combines local sliding-window attention and global attention to work with long histories. Dedicated vision and audio encoders bring the different input types into that language backbone. Xiaomi specifies a context of one million tokens for repositories, accumulated tool results and extended task histories. Organize that space around the current goal, relevant evidence and decisions that must remain consistent.
The V2.6 training approach mixes coding, general agents, visual work and cybersecurity tasks in the same reinforcement-learning run. It also varies the agent environments rather than training each domain in isolation. The manufacturer describes comparing candidate trajectories with task-specific criteria so that a passing result can still be improved for quality and efficiency. This is a model-training approach; a useful task brief still needs a clear completion criterion and evidence showing whether the result satisfies it.
For a repository task, provide the observed failure, relevant files, expected behavior and constraints on the change. Ask the model to identify the cause, propose a focused patch and explain the checks needed. In an environment with execution tools, feed back their actual output so the model can refine the next step. Keep commands, errors and modifications connected to the relevant file. The final artifact should distinguish a proposed fix from a change that has been applied and checked.
For visual work, supply a readable screenshot or reference image and identify the layout, behavior or spatial relationship to reproduce. Xiaomi’s V2.6 release describes frontend interfaces, presentations, 3D scenes and interactive worlds built through coding and tool use. A practical deliverable can be a component implementation with a list of visible details to inspect in its rendered result. Image and video understanding supply evidence for that workflow; the model’s text output is separate from media produced by the surrounding tools.
Audio and video can provide context that is absent from a written brief. Ask a focused question about the supplied material and preserve its relation to the requested output. For example, pair an interface recording with the steps that failed and ask for a diagnosis tied to the observed sequence. Retain unclear passages or events for review. A fluent explanation should not silently become evidence that an indistinct sound, small label or fleeting frame was understood correctly.
Xiaomi’s model card recommends temperature 1.0 and top_p 0.95 for its inference recipe and describes a five-layer multi-token prediction decoder. Those settings and optimizations belong to the producer implementation. In extended tool workflows, check that each next call serves a new information need or responds to a changed result. The maker documents repeated tool calls as a V2.6 training issue and distinguishes its RL and later MOPD checkpoints. Keep the chosen edition and actual progress record explicit when reviewing a completed task.
", "aboutText": "MiMo-V2.6-Flash is Xiaomi’s efficiency-balanced model in the MiMo-V2.6 series. It combines text, image, video and audio understanding in one architecture, with a textual response that can guide a supporting application’s next step. Its task scope covers software engineering, general agent work, visual workflows and cybersecurity analysis. Flash is a separate smaller model from V2.6-Pro, with its own parameter scale rather than simply a shorter response setting.\n\nThe maker’s released Flash profile describes a sparse mixture-of-experts model with 309B total and 15B activated parameters. Its 48-layer backbone combines local sliding-window attention and global attention to work with long histories. Dedicated vision and audio encoders bring the different input types into that language backbone. Xiaomi specifies a context of one million tokens for repositories, accumulated tool results and extended task histories. Organize that space around the current goal, relevant evidence and decisions that must remain consistent.\n\nThe V2.6 training approach mixes coding, general agents, visual work and cybersecurity tasks in the same reinforcement-learning run. It also varies the agent environments rather than training each domain in isolation. The manufacturer describes comparing candidate trajectories with task-specific criteria so that a passing result can still be improved for quality and efficiency. This is a model-training approach; a useful task brief still needs a clear completion criterion and evidence showing whether the result satisfies it.\n\nFor a repository task, provide the observed failure, relevant files, expected behavior and constraints on the change. Ask the model to identify the cause, propose a focused patch and explain the checks needed. In an environment with execution tools, feed back their actual output so the model can refine the next step. Keep commands, errors and modifications connected to the relevant file. The final artifact should distinguish a proposed fix from a change that has been applied and checked.\n\nFor visual work, supply a readable screenshot or reference image and identify the layout, behavior or spatial relationship to reproduce. Xiaomi’s V2.6 release describes frontend interfaces, presentations, 3D scenes and interactive worlds built through coding and tool use. A practical deliverable can be a component implementation with a list of visible details to inspect in its rendered result. Image and video understanding supply evidence for that workflow; the model’s text output is separate from media produced by the surrounding tools.\n\nAudio and video can provide context that is absent from a written brief. Ask a focused question about the supplied material and preserve its relation to the requested output. For example, pair an interface recording with the steps that failed and ask for a diagnosis tied to the observed sequence. Retain unclear passages or events for review. A fluent explanation should not silently become evidence that an indistinct sound, small label or fleeting frame was understood correctly.\n\nXiaomi’s model card recommends temperature 1.0 and top_p 0.95 for its inference recipe and describes a five-layer multi-token prediction decoder. Those settings and optimizations belong to the producer implementation. In extended tool workflows, check that each next call serves a new information need or responds to a changed result. The maker documents repeated tool calls as a V2.6 training issue and distinguishes its RL and later MOPD checkpoints. Keep the chosen edition and actual progress record explicit when reviewing a completed task.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Repair a CSV field serializer\n\nBug report: serialize(['Ada, Inc','plain']) returns 'Ada, Inc,plain', creating three columns. Current function: fields.join(','). Required rules: quote fields containing commas, quotes or line breaks, and double embedded quotes. Propose a focused JavaScript serializer and regression cases for the reported row, an embedded quote and an empty field. Do not claim the code ran.A serializer implementation, explanation of escaping and three regression cases with expected CSV text.Check embedded quotes are doubled inside a quoted field and commas within one field do not create extra columns.xiaomi/mimo-v2.6-flashMiMo-V2.6-Flash combines text, image, video and audio understanding for coding and extended agent workflows. Its published model profile uses 309B total parameters, 15B active per token and a one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2.6-Flash is Xiaomi’s efficiency-balanced model in the MiMo-V2.6 series. It combines text, image, video and audio understanding in one architecture, with a textual response that can guide a supporting application’s next step. Its task scope covers software engineering, general agent work, visual workflows and cybersecurity analysis. Flash is a separate smaller model from V2.6-Pro, with its own parameter scale rather than simply a shorter response setting.
The maker’s released Flash profile describes a sparse mixture-of-experts model with 309B total and 15B activated parameters. Its 48-layer backbone combines local sliding-window attention and global attention to work with long histories. Dedicated vision and audio encoders bring the different input types into that language backbone. Xiaomi specifies a context of one million tokens for repositories, accumulated tool results and extended task histories. Organize that space around the current goal, relevant evidence and decisions that must remain consistent.
The V2.6 training approach mixes coding, general agents, visual work and cybersecurity tasks in the same reinforcement-learning run. It also varies the agent environments rather than training each domain in isolation. The manufacturer describes comparing candidate trajectories with task-specific criteria so that a passing result can still be improved for quality and efficiency. This is a model-training approach; a useful task brief still needs a clear completion criterion and evidence showing whether the result satisfies it.
For a repository task, provide the observed failure, relevant files, expected behavior and constraints on the change. Ask the model to identify the cause, propose a focused patch and explain the checks needed. In an environment with execution tools, feed back their actual output so the model can refine the next step. Keep commands, errors and modifications connected to the relevant file. The final artifact should distinguish a proposed fix from a change that has been applied and checked.
For visual work, supply a readable screenshot or reference image and identify the layout, behavior or spatial relationship to reproduce. Xiaomi’s V2.6 release describes frontend interfaces, presentations, 3D scenes and interactive worlds built through coding and tool use. A practical deliverable can be a component implementation with a list of visible details to inspect in its rendered result. Image and video understanding supply evidence for that workflow; the model’s text output is separate from media produced by the surrounding tools.
Audio and video can provide context that is absent from a written brief. Ask a focused question about the supplied material and preserve its relation to the requested output. For example, pair an interface recording with the steps that failed and ask for a diagnosis tied to the observed sequence. Retain unclear passages or events for review. A fluent explanation should not silently become evidence that an indistinct sound, small label or fleeting frame was understood correctly.
Xiaomi’s model card recommends temperature 1.0 and top_p 0.95 for its inference recipe and describes a five-layer multi-token prediction decoder. Those settings and optimizations belong to the producer implementation. In extended tool workflows, check that each next call serves a new information need or responds to a changed result. The maker documents repeated tool calls as a V2.6 training issue and distinguishes its RL and later MOPD checkpoints. Keep the chosen edition and actual progress record explicit when reviewing a completed task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.6-flash | 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-v2.6-flash", "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-v2.6-flash',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-v2.6-flash',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-v2.6-flash
Use the method paths shown above.
xiaomi/mimo-v2.6-flashMiMo-V2.6-Flash combines text, image, video and audio understanding for coding and extended agent workflows. Its published model profile uses 309B total parameters, 15B active per token and a one-million-token context.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
MiMo-V2.6-Flash is Xiaomi’s efficiency-balanced model in the MiMo-V2.6 series. It combines text, image, video and audio understanding in one architecture, with a textual response that can guide a supporting application’s next step. Its task scope covers software engineering, general agent work, visual workflows and cybersecurity analysis. Flash is a separate smaller model from V2.6-Pro, with its own parameter scale rather than simply a shorter response setting.
The maker’s released Flash profile describes a sparse mixture-of-experts model with 309B total and 15B activated parameters. Its 48-layer backbone combines local sliding-window attention and global attention to work with long histories. Dedicated vision and audio encoders bring the different input types into that language backbone. Xiaomi specifies a context of one million tokens for repositories, accumulated tool results and extended task histories. Organize that space around the current goal, relevant evidence and decisions that must remain consistent.
The V2.6 training approach mixes coding, general agents, visual work and cybersecurity tasks in the same reinforcement-learning run. It also varies the agent environments rather than training each domain in isolation. The manufacturer describes comparing candidate trajectories with task-specific criteria so that a passing result can still be improved for quality and efficiency. This is a model-training approach; a useful task brief still needs a clear completion criterion and evidence showing whether the result satisfies it.
For a repository task, provide the observed failure, relevant files, expected behavior and constraints on the change. Ask the model to identify the cause, propose a focused patch and explain the checks needed. In an environment with execution tools, feed back their actual output so the model can refine the next step. Keep commands, errors and modifications connected to the relevant file. The final artifact should distinguish a proposed fix from a change that has been applied and checked.
For visual work, supply a readable screenshot or reference image and identify the layout, behavior or spatial relationship to reproduce. Xiaomi’s V2.6 release describes frontend interfaces, presentations, 3D scenes and interactive worlds built through coding and tool use. A practical deliverable can be a component implementation with a list of visible details to inspect in its rendered result. Image and video understanding supply evidence for that workflow; the model’s text output is separate from media produced by the surrounding tools.
Audio and video can provide context that is absent from a written brief. Ask a focused question about the supplied material and preserve its relation to the requested output. For example, pair an interface recording with the steps that failed and ask for a diagnosis tied to the observed sequence. Retain unclear passages or events for review. A fluent explanation should not silently become evidence that an indistinct sound, small label or fleeting frame was understood correctly.
Xiaomi’s model card recommends temperature 1.0 and top_p 0.95 for its inference recipe and describes a five-layer multi-token prediction decoder. Those settings and optimizations belong to the producer implementation. In extended tool workflows, check that each next call serves a new information need or responds to a changed result. The maker documents repeated tool calls as a V2.6 training issue and distinguishes its RL and later MOPD checkpoints. Keep the chosen edition and actual progress record explicit when reviewing a completed task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.6-flash | 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 $0.0000056 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "xiaomi/mimo-v2.6-flash",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-v2.6-flash', '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-v2.6-flash', '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-v2.6-flash
Use the method paths shown above.
Technical example in English
Repair a CSV field serializer\n\nBug report: serialize(['Ada, Inc','plain']) returns 'Ada, Inc,plain', creating three columns. Current function: fields.join(','). Required rules: quote fields containing commas, quotes or line breaks, and double embedded quotes. Propose a focused JavaScript serializer and regression cases for the reported row, an embedded quote and an empty field. Do not claim the code ran.A serializer implementation, explanation of escaping and three regression cases with expected CSV text.Check embedded quotes are doubled inside a quoted field and commas within one field do not create extra columns.