MiMo-V2.6-Pro is Xiaomi’s flagship model in its native omnimodal V2.6 series. It brings text, image, video and audio understanding into demanding software-engineering and extended agent tasks. The maker’s released Pro profile describes a sparse mixture-of-experts architecture with 1.02 trillion total parameters and 42 billion activated parameters. Its one-million-token context is intended for long repositories, tool traces and tasks carried across many interactions.
The series advances Xiaomi’s reinforcement-learning approach by scaling the variety of tasks and the quality of feedback alongside the training compute. Coding, general agents, visual tasks and cybersecurity work are mixed across different environments. Candidate trajectories are compared using task-specific criteria, with test results and graded quality contributing to the training signal. The Pro architecture combines a 70-layer hybrid attention backbone with dedicated vision and audio encoders and a five-layer multi-token prediction decoder.
For software work, state the behavior the program must deliver, provide the relevant implementation and explain how completion will be checked. Preserve the repository’s constraints and the exact failure or change request. The model can reason through a sequence of edits and tool results; the application supplies the tools and records their operations. Ask for a final account of the changed behavior, affected files and checks actually performed so that a long sequence ends in an inspectable result.
Xiaomi’s release then extends the task scope from coding to interactive worlds. It describes building games and 3D scenes from text, images or video references, implementing interaction logic and refining the work using rendered feedback. It also describes Blender-based objects and scenes and visual feedback in embodied simulation. Prepare a scene brief with dimensions, object relationships, controls and visible completion criteria. The resulting code, scene instructions or tool-produced assets should be inspected in the intended rendering or simulation environment.
For visual and design work, the maker shows frontend interfaces and slide decks with layout, components and animation, as well as workflows that use image and video tools. Provide the audience, required content, visual references and the interactions that must work. A useful request can produce a page implementation or a presentation outline with the details needed for the next production step. The underlying model returns text and tool directions; rendered visuals and generated media come from the tools used in the workflow.
The release also describes music and research applications. Its music example uses written scores and MIDI as editable composition artifacts. Its research examples combine literature and patent review, design hypotheses and computational simulations, as well as mathematical formalization checked with Lean. For a research task, distinguish source observations, assumptions, calculations and proposed hypotheses. Retain tool outputs and verification results, and label a computational candidate as a candidate rather than a laboratory-validated result.
Long-context work needs deliberate input organization. Keep document boundaries, file identifiers and prior decisions stable, and reserve room for the response and continuing tool history. Xiaomi’s local recipe recommends temperature 1.0 and top_p 0.95. The maker also documents tool-call repetition in the V2.6 training lineage and separate MOPD checkpoints intended to address it. Inspect whether each action advances the task and retain the exact edition with the result; repeated calls without new evidence are a reason to reassess the next step.
The final deliverable should match the task’s completion criterion: a checked code change, an inspected interactive scene, an editable design artifact or a research analysis tied to evidence. Pro, Flash and Pro-UltraSpeed have distinct roles in the V2.6 family. Preserve that distinction when comparing results, while keeping the material, tool observations and verification record available for review.
", "aboutText": "MiMo-V2.6-Pro is Xiaomi’s flagship model in its native omnimodal V2.6 series. It brings text, image, video and audio understanding into demanding software-engineering and extended agent tasks. The maker’s released Pro profile describes a sparse mixture-of-experts architecture with 1.02 trillion total parameters and 42 billion activated parameters. Its one-million-token context is intended for long repositories, tool traces and tasks carried across many interactions.\n\nThe series advances Xiaomi’s reinforcement-learning approach by scaling the variety of tasks and the quality of feedback alongside the training compute. Coding, general agents, visual tasks and cybersecurity work are mixed across different environments. Candidate trajectories are compared using task-specific criteria, with test results and graded quality contributing to the training signal. The Pro architecture combines a 70-layer hybrid attention backbone with dedicated vision and audio encoders and a five-layer multi-token prediction decoder.\n\nFor software work, state the behavior the program must deliver, provide the relevant implementation and explain how completion will be checked. Preserve the repository’s constraints and the exact failure or change request. The model can reason through a sequence of edits and tool results; the application supplies the tools and records their operations. Ask for a final account of the changed behavior, affected files and checks actually performed so that a long sequence ends in an inspectable result.\n\nXiaomi’s release then extends the task scope from coding to interactive worlds. It describes building games and 3D scenes from text, images or video references, implementing interaction logic and refining the work using rendered feedback. It also describes Blender-based objects and scenes and visual feedback in embodied simulation. Prepare a scene brief with dimensions, object relationships, controls and visible completion criteria. The resulting code, scene instructions or tool-produced assets should be inspected in the intended rendering or simulation environment.\n\nFor visual and design work, the maker shows frontend interfaces and slide decks with layout, components and animation, as well as workflows that use image and video tools. Provide the audience, required content, visual references and the interactions that must work. A useful request can produce a page implementation or a presentation outline with the details needed for the next production step. The underlying model returns text and tool directions; rendered visuals and generated media come from the tools used in the workflow.\n\nThe release also describes music and research applications. Its music example uses written scores and MIDI as editable composition artifacts. Its research examples combine literature and patent review, design hypotheses and computational simulations, as well as mathematical formalization checked with Lean. For a research task, distinguish source observations, assumptions, calculations and proposed hypotheses. Retain tool outputs and verification results, and label a computational candidate as a candidate rather than a laboratory-validated result.\n\nLong-context work needs deliberate input organization. Keep document boundaries, file identifiers and prior decisions stable, and reserve room for the response and continuing tool history. Xiaomi’s local recipe recommends temperature 1.0 and top_p 0.95. The maker also documents tool-call repetition in the V2.6 training lineage and separate MOPD checkpoints intended to address it. Inspect whether each action advances the task and retain the exact edition with the result; repeated calls without new evidence are a reason to reassess the next step.\n\nThe final deliverable should match the task’s completion criterion: a checked code change, an inspected interactive scene, an editable design artifact or a research analysis tied to evidence. Pro, Flash and Pro-UltraSpeed have distinct roles in the V2.6 family. Preserve that distinction when comparing results, while keeping the material, tool observations and verification record available for review.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Implement bounded grid movement\n\nWrite a JavaScript function move(player, direction, walls) for a 5-by-5 tile grid indexed 0–4. Directions are up, down, left and right. Return a new position; keep the current position when a move hits a wall or boundary. Walls are coordinate pairs. Provide tests for a free move, a wall and each outer boundary. No rendering is required.A pure movement function and test cases covering free movement, wall collision, boundaries and unchanged input state.Check every returned coordinate stays within 0–4 and neither the player object nor wall list is mutated.xiaomi/mimo-v2.6-proMiMo-V2.6-Pro is Xiaomi’s flagship omnimodal model for demanding coding, research and extended agent tasks. It understands text, images, video and audio; the released Pro profile documents a 1.02T-parameter MoE with 42B active parameters 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-Pro is Xiaomi’s flagship model in its native omnimodal V2.6 series. It brings text, image, video and audio understanding into demanding software-engineering and extended agent tasks. The maker’s released Pro profile describes a sparse mixture-of-experts architecture with 1.02 trillion total parameters and 42 billion activated parameters. Its one-million-token context is intended for long repositories, tool traces and tasks carried across many interactions.
The series advances Xiaomi’s reinforcement-learning approach by scaling the variety of tasks and the quality of feedback alongside the training compute. Coding, general agents, visual tasks and cybersecurity work are mixed across different environments. Candidate trajectories are compared using task-specific criteria, with test results and graded quality contributing to the training signal. The Pro architecture combines a 70-layer hybrid attention backbone with dedicated vision and audio encoders and a five-layer multi-token prediction decoder.
For software work, state the behavior the program must deliver, provide the relevant implementation and explain how completion will be checked. Preserve the repository’s constraints and the exact failure or change request. The model can reason through a sequence of edits and tool results; the application supplies the tools and records their operations. Ask for a final account of the changed behavior, affected files and checks actually performed so that a long sequence ends in an inspectable result.
Xiaomi’s release then extends the task scope from coding to interactive worlds. It describes building games and 3D scenes from text, images or video references, implementing interaction logic and refining the work using rendered feedback. It also describes Blender-based objects and scenes and visual feedback in embodied simulation. Prepare a scene brief with dimensions, object relationships, controls and visible completion criteria. The resulting code, scene instructions or tool-produced assets should be inspected in the intended rendering or simulation environment.
For visual and design work, the maker shows frontend interfaces and slide decks with layout, components and animation, as well as workflows that use image and video tools. Provide the audience, required content, visual references and the interactions that must work. A useful request can produce a page implementation or a presentation outline with the details needed for the next production step. The underlying model returns text and tool directions; rendered visuals and generated media come from the tools used in the workflow.
The release also describes music and research applications. Its music example uses written scores and MIDI as editable composition artifacts. Its research examples combine literature and patent review, design hypotheses and computational simulations, as well as mathematical formalization checked with Lean. For a research task, distinguish source observations, assumptions, calculations and proposed hypotheses. Retain tool outputs and verification results, and label a computational candidate as a candidate rather than a laboratory-validated result.
Long-context work needs deliberate input organization. Keep document boundaries, file identifiers and prior decisions stable, and reserve room for the response and continuing tool history. Xiaomi’s local recipe recommends temperature 1.0 and top_p 0.95. The maker also documents tool-call repetition in the V2.6 training lineage and separate MOPD checkpoints intended to address it. Inspect whether each action advances the task and retain the exact edition with the result; repeated calls without new evidence are a reason to reassess the next step.
The final deliverable should match the task’s completion criterion: a checked code change, an inspected interactive scene, an editable design artifact or a research analysis tied to evidence. Pro, Flash and Pro-UltraSpeed have distinct roles in the V2.6 family. Preserve that distinction when comparing results, while keeping the material, tool observations and verification record available for review.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.6-pro | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Examples: system, user, assistant, tool, function Conditions: These roles are explicitly represented by Source compatibility types; the exact model role set remains model-specific. Model-specific | Default— |
Fieldmessages[].content | Typestring|content_part[]|null | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_calls | Typetool_call[] | RequirementOptional | Values & limits | Default— |
Fieldmessages[].tool_call_id | Typestring | RequirementOptional | Values & limits Applies when: role=tool; use actual returned ID | Default— |
Fieldmessages[].name | Typestring | RequirementOptional | Values & limits | Default— |
Fieldmessages[].reasoning_content | Typestring | RequirementOptional | Values & limits Applies when: Round-trip actual returned reasoning where this model uses it | Default— |
Fieldmessages[].reasoning_details | Typeobject|array | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmax_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldmax_completion_tokens | Typeinteger | RequirementOptional | Values & limits Minimum: 1 Model-specific | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Fieldstream_options.include_usage | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtemperature | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtop_p | Typenumber | RequirementOptional | Values & limits Model-specific | Default— |
Fieldstop | Typestring|string[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools | Typefunction_tool[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldtools[].type | Typestring | RequirementOptional | Values & limits function Model-specific | Default— |
Fieldtools[].function.name | Typestring | RequirementRequired | Values & limits Applies when: function tool supplied | Default— |
Fieldtools[].function.description | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtools[].function.parameters | TypeJSON_schema | RequirementOptional | Values & limits | Default— |
Fieldtool_choice | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldparallel_tool_calls | Typeboolean | RequirementOptional | Values & limits Model-specific | Default— |
Fieldresponse_format | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning_effort | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldreasoning | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldservice_tier | Typestring | RequirementOptional | Values & limits Model-specific | Default— |
Fieldinstructions | Typestring | RequirementOptional | Values & limits Compatibility field | Default— |
Fieldfunctions | Typefunction[] | RequirementOptional | Values & limits Model-specific | Default— |
Fieldfunction_call | Typestring|object | RequirementOptional | Values & limits Model-specific | Default— |
Fieldprompt_cache_options | Typeobject | RequirementOptional | Values & limits Model-specific | Default— |
Fieldmodalities | Typestring[] | RequirementOptional | Values & limits text | Default— |
Fieldprovider | Typeobject | RequirementOptional | Values & limits Conditions: provider.options is rejected on this Ultra text route | Default— |
Fieldcache_control.ttl | Typestring | RequirementOptional | Values & limits Conditions: 1h is rejected in actual prompt-cache locations | Default— |
Text · UTF8 text
messages[].content
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages |
Parametermaterial_types | Contracttext |
Parametermessages | Contractmessage array with role/content shape |
Parameterfile_material | Contractactual UTF-8 document inserted as literal text; no file ID inferred |
Parameteroptional_controls | Contractstream, temperature, top_p, stop, max_tokens, max_completion_tokens, reasoning, response_format, tools, tool_choice |
Parametercontrol_scope | Contractmodel-specific; user function tools differ from hosted tools |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Lifecycle: synchronous_or_streamed
Send exact model ID with messages.
Context length is not an output cap.
A text file may supply literal text; image/audio/file-object inputs need exact binding.
Tariff references do not add request options. Supported parameters are listed for the selected method.
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 $0.00087 / 1K tokens Output · Output tokens $0.00174 / 1K tokens Input · Cache read $0.0000072 / 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 $0.00087 / 1K tokens Output · Output tokens $0.00174 / 1K tokens Input · Cache read $0.0000072 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-pro", "messages": [{"role": "user", "content": "Explain the difference between an observation and a hypothesis in three sentences."}]}')\n\nPath("request.json").write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path("result.json").read_text())\nfor x in r.get("choices",[]):\n if x.get("message",{}).get("content"): print(x["message"]["content"])\nPY_RESULT\nfrom openai import OpenAI\nimport os\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nresult=client.chat.completions.create(model='xiaomi/mimo-v2.6-pro',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}])\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nsave_result(result.to_dict(mode="json"))\nfrom openai import OpenAI\nimport os\nfrom pathlib import Path\n\nif not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")\nclient=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)\nimport base64, json\nfrom pathlib import Path\n\ndef save_result(data, stem="result"):\n # Keep every field, including usage, IDs, reasoning and tool requests.\n Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")\n print(json.dumps(data, ensure_ascii=False, indent=2))\n def save_blob(encoded, suffix, label):\n raw = base64.b64decode(encoded, altchars=b"-_", validate=True)\n ext = "png" if raw.startswith(b"\\x89PNG\\r\\n\\x1a\\n") else "jpg" if raw.startswith(b"\\xff\\xd8") else "webp" if raw[:4] == b"RIFF" and raw[8:12] == b"WEBP" else suffix\n file = Path(stem + "-" + label + "." + ext)\n file.write_bytes(raw)\n print("Saved", file)\n for index, block in enumerate(data.get("content") or []):\n print("Content", index, json.dumps(block, ensure_ascii=False))\n for choice in data.get("choices") or []:\n print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))\n for index, item in enumerate(data.get("output") or []):\n print("Output", index, json.dumps(item, ensure_ascii=False))\n if item.get("type") == "image_generation_call" and item.get("result"):\n save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))\n for ci, candidate in enumerate(data.get("candidates") or []):\n for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):\n print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))\n blob = part.get("inlineData") or part.get("inline_data")\n if blob and blob.get("data"):\n mime = blob.get("mimeType") or blob.get("mime_type")\n suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")\n save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))\n\nwith client.chat.completions.stream(model='xiaomi/mimo-v2.6-pro',messages=[{"role":"user","content":"Explain observations and hypotheses in three sentences."}]) as stream:\n with Path("stream-events.jsonl").open("w",encoding="utf-8") as log:\n for event in stream:\n payload=event.to_dict(mode="json")\n log.write(json.dumps(payload,ensure_ascii=False)+"\\n"); log.flush()\n print(json.dumps(payload,ensure_ascii=False))\n final=stream.get_final_completion()\n save_result(final.to_dict(mode="json"),"stream-result")\njson or SSE
Keep every complete returned response, file and content part.
Keep every choice and its content/tool calls/reasoning. In SSE assemble deltas by choice/tool index, retain the final finish reason and usage.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldchoices[].index | Typeinteger |
Fieldchoices[].message.content | Typestring|null |
Fieldchoices[].message.tool_calls | Typetool_call[] |
Fieldchoices[].message.reasoning_content | Typestring |
Fieldchoices[].message.reasoning_details | Typeobject|array |
Fieldchoices[].finish_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra xiaomi/mimo-v2.6-pro
Use the method paths shown above.
xiaomi/mimo-v2.6-proMiMo-V2.6-Pro is Xiaomi’s flagship omnimodal model for demanding coding, research and extended agent tasks. It understands text, images, video and audio; the released Pro profile documents a 1.02T-parameter MoE with 42B active parameters 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-Pro is Xiaomi’s flagship model in its native omnimodal V2.6 series. It brings text, image, video and audio understanding into demanding software-engineering and extended agent tasks. The maker’s released Pro profile describes a sparse mixture-of-experts architecture with 1.02 trillion total parameters and 42 billion activated parameters. Its one-million-token context is intended for long repositories, tool traces and tasks carried across many interactions.
The series advances Xiaomi’s reinforcement-learning approach by scaling the variety of tasks and the quality of feedback alongside the training compute. Coding, general agents, visual tasks and cybersecurity work are mixed across different environments. Candidate trajectories are compared using task-specific criteria, with test results and graded quality contributing to the training signal. The Pro architecture combines a 70-layer hybrid attention backbone with dedicated vision and audio encoders and a five-layer multi-token prediction decoder.
For software work, state the behavior the program must deliver, provide the relevant implementation and explain how completion will be checked. Preserve the repository’s constraints and the exact failure or change request. The model can reason through a sequence of edits and tool results; the application supplies the tools and records their operations. Ask for a final account of the changed behavior, affected files and checks actually performed so that a long sequence ends in an inspectable result.
Xiaomi’s release then extends the task scope from coding to interactive worlds. It describes building games and 3D scenes from text, images or video references, implementing interaction logic and refining the work using rendered feedback. It also describes Blender-based objects and scenes and visual feedback in embodied simulation. Prepare a scene brief with dimensions, object relationships, controls and visible completion criteria. The resulting code, scene instructions or tool-produced assets should be inspected in the intended rendering or simulation environment.
For visual and design work, the maker shows frontend interfaces and slide decks with layout, components and animation, as well as workflows that use image and video tools. Provide the audience, required content, visual references and the interactions that must work. A useful request can produce a page implementation or a presentation outline with the details needed for the next production step. The underlying model returns text and tool directions; rendered visuals and generated media come from the tools used in the workflow.
The release also describes music and research applications. Its music example uses written scores and MIDI as editable composition artifacts. Its research examples combine literature and patent review, design hypotheses and computational simulations, as well as mathematical formalization checked with Lean. For a research task, distinguish source observations, assumptions, calculations and proposed hypotheses. Retain tool outputs and verification results, and label a computational candidate as a candidate rather than a laboratory-validated result.
Long-context work needs deliberate input organization. Keep document boundaries, file identifiers and prior decisions stable, and reserve room for the response and continuing tool history. Xiaomi’s local recipe recommends temperature 1.0 and top_p 0.95. The maker also documents tool-call repetition in the V2.6 training lineage and separate MOPD checkpoints intended to address it. Inspect whether each action advances the task and retain the exact edition with the result; repeated calls without new evidence are a reason to reassess the next step.
The final deliverable should match the task’s completion criterion: a checked code change, an inspected interactive scene, an editable design artifact or a research analysis tied to evidence. Pro, Flash and Pro-UltraSpeed have distinct roles in the V2.6 family. Preserve that distinction when comparing results, while keeping the material, tool observations and verification record available for review.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits xiaomi/mimo-v2.6-pro | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits user, assistant | Default— |
Fieldmessages[].content | Typestring | RequirementRequired | Values & limits | Default— |
Fieldmax_tokens | Typeinteger | RequirementRequired | Values & limits | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Text · UTF-8 text
messages[].content string
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, messages, max_tokens |
Parameteroptional_controls | Contractstream |
Parametermaterial_types | Contracttext |
Parametertext_file_material | ContractRead the actual UTF-8 document and put its text in the indicated input or message content string. |
Lifecycle: synchronous_or_streamed
Tariff references do not add request options. Supported parameters are listed for the selected method.
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 $0.00087 / 1K tokens Output · Output tokens $0.00174 / 1K tokens Input · Cache read $0.0000072 / 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 $0.00087 / 1K tokens Output · Output tokens $0.00174 / 1K tokens Input · Cache read $0.0000072 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "xiaomi/mimo-v2.6-pro",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\n: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"\nexport AILOOT_TEXT_FILE\npython3 - <<'PY_REQUEST'\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'xiaomi/mimo-v2.6-pro', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nPath('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \\\n -H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nPY_RESULT\nimport json, os\nfrom pathlib import Path\n\nsource_file = Path(os.environ['AILOOT_TEXT_FILE'])\nif not source_file.is_file():\n raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')\ntext = source_file.read_text(encoding='utf-8')\nif not text.strip():\n raise SystemExit('Choose a document containing text')\npayload = {'model': 'xiaomi/mimo-v2.6-pro', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}\npayload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\\n\\n' + text\nfrom urllib.request import Request, urlopen\nfrom urllib.error import HTTPError\n\napi_key = os.environ['AILOOT_API_KEY']\nif not api_key.strip():\n raise SystemExit('Set AILOOT_API_KEY before making a request')\nheaders = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}\nheaders['x-api-key'] = api_key\nrequest = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')\ntry:\n with urlopen(request, timeout=120) as response:\n raw = response.read()\n Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')\nexcept HTTPError as error:\n Path('result.json').write_bytes(error.read())\n Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')\n raise\nPath('result.json').write_bytes(raw)\nimport json\nfrom pathlib import Path\n\nresult = json.loads(Path('result.json').read_text(encoding='utf-8'))\nprint(json.dumps(result, ensure_ascii=False, indent=2))\nJSON or SSE
Keep every complete returned response, file and content part.
Keep all content blocks, thinking signatures and actual tool-use IDs. Assemble all SSE block deltas; a first text block is not the complete output.
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionInvalid required fields, material representation or parameter value | Next stepCorrect the indicated fields before a new creation request. |
Ailoot Ultra xiaomi/mimo-v2.6-pro
Use the method paths shown above.
Technical example in English
Implement bounded grid movement\n\nWrite a JavaScript function move(player, direction, walls) for a 5-by-5 tile grid indexed 0–4. Directions are up, down, left and right. Return a new position; keep the current position when a move hits a wall or boundary. Walls are coordinate pairs. Provide tests for a free move, a wall and each outer boundary. No rendering is required.A pure movement function and test cases covering free movement, wall collision, boundaries and unchanged input state.Check every returned coordinate stays within 0–4 and neither the player object nor wall list is mutated.