Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic work, coding and computer-use workflows. The maker's original release emphasizes planning, orchestration, context management and combining visual evidence with actions supplied by tools. The documented output is text; the application around the model provides the actual execution and rendered artifacts.
Agent planning and long context
The release describes adapting to native tools, custom functions and agent environments. As a main agent, the model can gather context, form a plan and delegate defined work; in a delegated role, it follows the assigned task and can escalate an obstacle. These are capabilities used by an agent environment rather than a collection of subagents automatically created by a single text response.
The maker's model table gives a 1,048,576-token context. Its 1.1 release describes recalling earlier work and compacting the information needed for later steps. A useful task should identify the objective, source material and final artifact, with important decisions and tool results retained explicitly. A large context helps keep related information together but does not define which requirement the result must satisfy.
For a long project question, label the source documents and request the relevant requirement, its location and the unresolved condition. For a plan, ask for the actions in an order tied to the supplied constraints and specify what result would complete each step. Retain the visible findings and outcomes when following up rather than assuming an unspecified memory contains every earlier fact.
Computer use and coding
The maker describes computer workflows across changing applications, with the model choosing between direct interface interaction and scripted automation in a connected environment. A screenshot can supply the visible state and a text instruction can define the user's goal. Request the relevant control, proposed operation and evidence supporting it, then return the actual new state if the environment performs that operation.
For coding, the release describes diagnosing bugs, implementing features and handling code migrations. Its debugging demonstration combines code generation, screenshots, locating a failure and inspecting the correction. A practical request can provide the failing behavior, affected source and expected result, then ask for the proposed change with the public interface retained. Code execution and file modification remain operations provided by the application tools.
Give the model the code and declarations that determine the behavior. For an explanation, provide an input to trace; for a modification, specify the result and constraints; for a visual implementation, include the screenshot and the interactions the image does not show. Request the artifact separately from its assumptions and the feedback needed to inspect it.
Multimodal inputs
The model table documents text, images, video, audio and PDF input for 1.1, with text output. The release describes detailed image and video captioning, visual-to-code generation and using perceptual detail through a longer workflow. A document question can ask for source-linked fields or a comparison; a video question can identify the event or sequence to describe; an audio-visual question can specify which spoken and visible information matters.
The model's output remains a written explanation, structured result or proposed code. A generated image, synthesized speech or completed external action requires a separately provided component. Preserve source identifiers, labels, units and relevant segments so that the text result can be compared with the original material.
Reasoning, tools and structured output
The Muse Spark reasoning guide documents minimal, low, medium, high and xhigh for this edition. Max is a later Standard 1.3 setting, and none is unsupported. Reasoning occurs even without an explicit effort value, and the output budget covers both the private internal reasoning and the visible answer. Raw reasoning and log probabilities are not exposed as ordinary confidence or explanation fields.
Developer-defined tool calling follows a cycle: the application supplies operations, the model prepares arguments, the application executes each call and returns its result, and the next answer uses the outcome. A tool call can request information or an operation; it is not itself evidence that the operation completed. Keep the originating call and result associated through the conversation.
The maker also documents structured text constrained by a supplied JSON schema. Define the fields required by the application and their types, and keep source information separate from interpretation when they serve different purposes. Structured shape does not establish factual correctness; the original sources and actual tool results still determine the content of an inspectable answer.
Edition and continuity boundaries
Muse Spark 1.1 remains its own release. The specific coding changes of 1.2, long-horizon behavior updates of 1.3 and Standard 1.3's max setting should not be assigned to it merely because the family is shared. The maker's chat interface does not give external callers private reasoning to replay, so preserve visible history and use the continuity mechanisms offered by the connected interface.
The sources read do not state separate hard maximum input or output-token capacities beyond the documented context. Define the required text artifact and retain the evidence needed for each action or conclusion, keeping the model's planning and perception distinct from the environment that executes its proposed operations.
", "aboutText": "Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic work, coding and computer-use workflows. The maker's original release emphasizes planning, orchestration, context management and combining visual evidence with actions supplied by tools. The documented output is text; the application around the model provides the actual execution and rendered artifacts.\n\nAgent planning and long context\n\nThe release describes adapting to native tools, custom functions and agent environments. As a main agent, the model can gather context, form a plan and delegate defined work; in a delegated role, it follows the assigned task and can escalate an obstacle. These are capabilities used by an agent environment rather than a collection of subagents automatically created by a single text response.\n\nThe maker's model table gives a 1,048,576-token context. Its 1.1 release describes recalling earlier work and compacting the information needed for later steps. A useful task should identify the objective, source material and final artifact, with important decisions and tool results retained explicitly. A large context helps keep related information together but does not define which requirement the result must satisfy.\n\nFor a long project question, label the source documents and request the relevant requirement, its location and the unresolved condition. For a plan, ask for the actions in an order tied to the supplied constraints and specify what result would complete each step. Retain the visible findings and outcomes when following up rather than assuming an unspecified memory contains every earlier fact.\n\nComputer use and coding\n\nThe maker describes computer workflows across changing applications, with the model choosing between direct interface interaction and scripted automation in a connected environment. A screenshot can supply the visible state and a text instruction can define the user's goal. Request the relevant control, proposed operation and evidence supporting it, then return the actual new state if the environment performs that operation.\n\nFor coding, the release describes diagnosing bugs, implementing features and handling code migrations. Its debugging demonstration combines code generation, screenshots, locating a failure and inspecting the correction. A practical request can provide the failing behavior, affected source and expected result, then ask for the proposed change with the public interface retained. Code execution and file modification remain operations provided by the application tools.\n\nGive the model the code and declarations that determine the behavior. For an explanation, provide an input to trace; for a modification, specify the result and constraints; for a visual implementation, include the screenshot and the interactions the image does not show. Request the artifact separately from its assumptions and the feedback needed to inspect it.\n\nMultimodal inputs\n\nThe model table documents text, images, video, audio and PDF input for 1.1, with text output. The release describes detailed image and video captioning, visual-to-code generation and using perceptual detail through a longer workflow. A document question can ask for source-linked fields or a comparison; a video question can identify the event or sequence to describe; an audio-visual question can specify which spoken and visible information matters.\n\nThe model's output remains a written explanation, structured result or proposed code. A generated image, synthesized speech or completed external action requires a separately provided component. Preserve source identifiers, labels, units and relevant segments so that the text result can be compared with the original material.\n\nReasoning, tools and structured output\n\nThe Muse Spark reasoning guide documents minimal, low, medium, high and xhigh for this edition. Max is a later Standard 1.3 setting, and none is unsupported. Reasoning occurs even without an explicit effort value, and the output budget covers both the private internal reasoning and the visible answer. Raw reasoning and log probabilities are not exposed as ordinary confidence or explanation fields.\n\nDeveloper-defined tool calling follows a cycle: the application supplies operations, the model prepares arguments, the application executes each call and returns its result, and the next answer uses the outcome. A tool call can request information or an operation; it is not itself evidence that the operation completed. Keep the originating call and result associated through the conversation.\n\nThe maker also documents structured text constrained by a supplied JSON schema. Define the fields required by the application and their types, and keep source information separate from interpretation when they serve different purposes. Structured shape does not establish factual correctness; the original sources and actual tool results still determine the content of an inspectable answer.\n\nEdition and continuity boundaries\n\nMuse Spark 1.1 remains its own release. The specific coding changes of 1.2, long-horizon behavior updates of 1.3 and Standard 1.3's max setting should not be assigned to it merely because the family is shared. The maker's chat interface does not give external callers private reasoning to replay, so preserve visible history and use the continuity mechanisms offered by the connected interface.\n\nThe sources read do not state separate hard maximum input or output-token capacities beyond the documented context. Define the required text artifact and retain the evidence needed for each action or conclusion, keeping the model's planning and perception distinct from the environment that executes its proposed operations.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Plan an approval workflow\n\nPlan a document approval flow from these constraints: the author submits a draft; a reviewer must approve before the coordinator publishes; rejected drafts return to the author; publication needs a recorded approval ID. Give the ordered steps and evidence required at each transition. Mark any actor permission that the supplied rules do not define.A numbered workflow with approval evidence, rejection path and unresolved permission questions.Verify every publication path requires a recorded approval ID and rejection cannot skip review.meta/muse-spark-1.1Muse Spark 1.1 is Meta's multimodal reasoning model for agents, computer use and coding. It works with substantial text and visual context, produces text and proposed tool actions, and has a 1,048,576-token maker context with reasoning levels through xhigh.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic work, coding and computer-use workflows. The maker's original release emphasizes planning, orchestration, context management and combining visual evidence with actions supplied by tools. The documented output is text; the application around the model provides the actual execution and rendered artifacts.
Agent planning and long context
The release describes adapting to native tools, custom functions and agent environments. As a main agent, the model can gather context, form a plan and delegate defined work; in a delegated role, it follows the assigned task and can escalate an obstacle. These are capabilities used by an agent environment rather than a collection of subagents automatically created by a single text response.
The maker's model table gives a 1,048,576-token context. Its 1.1 release describes recalling earlier work and compacting the information needed for later steps. A useful task should identify the objective, source material and final artifact, with important decisions and tool results retained explicitly. A large context helps keep related information together but does not define which requirement the result must satisfy.
For a long project question, label the source documents and request the relevant requirement, its location and the unresolved condition. For a plan, ask for the actions in an order tied to the supplied constraints and specify what result would complete each step. Retain the visible findings and outcomes when following up rather than assuming an unspecified memory contains every earlier fact.
Computer use and coding
The maker describes computer workflows across changing applications, with the model choosing between direct interface interaction and scripted automation in a connected environment. A screenshot can supply the visible state and a text instruction can define the user's goal. Request the relevant control, proposed operation and evidence supporting it, then return the actual new state if the environment performs that operation.
For coding, the release describes diagnosing bugs, implementing features and handling code migrations. Its debugging demonstration combines code generation, screenshots, locating a failure and inspecting the correction. A practical request can provide the failing behavior, affected source and expected result, then ask for the proposed change with the public interface retained. Code execution and file modification remain operations provided by the application tools.
Give the model the code and declarations that determine the behavior. For an explanation, provide an input to trace; for a modification, specify the result and constraints; for a visual implementation, include the screenshot and the interactions the image does not show. Request the artifact separately from its assumptions and the feedback needed to inspect it.
Multimodal inputs
The model table documents text, images, video, audio and PDF input for 1.1, with text output. The release describes detailed image and video captioning, visual-to-code generation and using perceptual detail through a longer workflow. A document question can ask for source-linked fields or a comparison; a video question can identify the event or sequence to describe; an audio-visual question can specify which spoken and visible information matters.
The model's output remains a written explanation, structured result or proposed code. A generated image, synthesized speech or completed external action requires a separately provided component. Preserve source identifiers, labels, units and relevant segments so that the text result can be compared with the original material.
Reasoning, tools and structured output
The Muse Spark reasoning guide documents minimal, low, medium, high and xhigh for this edition. Max is a later Standard 1.3 setting, and none is unsupported. Reasoning occurs even without an explicit effort value, and the output budget covers both the private internal reasoning and the visible answer. Raw reasoning and log probabilities are not exposed as ordinary confidence or explanation fields.
Developer-defined tool calling follows a cycle: the application supplies operations, the model prepares arguments, the application executes each call and returns its result, and the next answer uses the outcome. A tool call can request information or an operation; it is not itself evidence that the operation completed. Keep the originating call and result associated through the conversation.
The maker also documents structured text constrained by a supplied JSON schema. Define the fields required by the application and their types, and keep source information separate from interpretation when they serve different purposes. Structured shape does not establish factual correctness; the original sources and actual tool results still determine the content of an inspectable answer.
Edition and continuity boundaries
Muse Spark 1.1 remains its own release. The specific coding changes of 1.2, long-horizon behavior updates of 1.3 and Standard 1.3's max setting should not be assigned to it merely because the family is shared. The maker's chat interface does not give external callers private reasoning to replay, so preserve visible history and use the continuity mechanisms offered by the connected interface.
The sources read do not state separate hard maximum input or output-token capacities beyond the documented context. Define the required text artifact and retain the evidence needed for each action or conclusion, keeping the model's planning and perception distinct from the environment that executes its proposed operations.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.1 | 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 $0.0025 / 1K tokens Output · Output tokens $0.0085 / 1K tokens Input · Cache read $0.0003 / 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 $0.0025 / 1K tokens Output · Output tokens $0.0085 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "meta/muse-spark-1.1", "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='meta/muse-spark-1.1',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='meta/muse-spark-1.1',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 meta/muse-spark-1.1
Use the method paths shown above.
meta/muse-spark-1.1Muse Spark 1.1 is Meta's multimodal reasoning model for agents, computer use and coding. It works with substantial text and visual context, produces text and proposed tool actions, and has a 1,048,576-token maker context with reasoning levels through xhigh.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic work, coding and computer-use workflows. The maker's original release emphasizes planning, orchestration, context management and combining visual evidence with actions supplied by tools. The documented output is text; the application around the model provides the actual execution and rendered artifacts.
Agent planning and long context
The release describes adapting to native tools, custom functions and agent environments. As a main agent, the model can gather context, form a plan and delegate defined work; in a delegated role, it follows the assigned task and can escalate an obstacle. These are capabilities used by an agent environment rather than a collection of subagents automatically created by a single text response.
The maker's model table gives a 1,048,576-token context. Its 1.1 release describes recalling earlier work and compacting the information needed for later steps. A useful task should identify the objective, source material and final artifact, with important decisions and tool results retained explicitly. A large context helps keep related information together but does not define which requirement the result must satisfy.
For a long project question, label the source documents and request the relevant requirement, its location and the unresolved condition. For a plan, ask for the actions in an order tied to the supplied constraints and specify what result would complete each step. Retain the visible findings and outcomes when following up rather than assuming an unspecified memory contains every earlier fact.
Computer use and coding
The maker describes computer workflows across changing applications, with the model choosing between direct interface interaction and scripted automation in a connected environment. A screenshot can supply the visible state and a text instruction can define the user's goal. Request the relevant control, proposed operation and evidence supporting it, then return the actual new state if the environment performs that operation.
For coding, the release describes diagnosing bugs, implementing features and handling code migrations. Its debugging demonstration combines code generation, screenshots, locating a failure and inspecting the correction. A practical request can provide the failing behavior, affected source and expected result, then ask for the proposed change with the public interface retained. Code execution and file modification remain operations provided by the application tools.
Give the model the code and declarations that determine the behavior. For an explanation, provide an input to trace; for a modification, specify the result and constraints; for a visual implementation, include the screenshot and the interactions the image does not show. Request the artifact separately from its assumptions and the feedback needed to inspect it.
Multimodal inputs
The model table documents text, images, video, audio and PDF input for 1.1, with text output. The release describes detailed image and video captioning, visual-to-code generation and using perceptual detail through a longer workflow. A document question can ask for source-linked fields or a comparison; a video question can identify the event or sequence to describe; an audio-visual question can specify which spoken and visible information matters.
The model's output remains a written explanation, structured result or proposed code. A generated image, synthesized speech or completed external action requires a separately provided component. Preserve source identifiers, labels, units and relevant segments so that the text result can be compared with the original material.
Reasoning, tools and structured output
The Muse Spark reasoning guide documents minimal, low, medium, high and xhigh for this edition. Max is a later Standard 1.3 setting, and none is unsupported. Reasoning occurs even without an explicit effort value, and the output budget covers both the private internal reasoning and the visible answer. Raw reasoning and log probabilities are not exposed as ordinary confidence or explanation fields.
Developer-defined tool calling follows a cycle: the application supplies operations, the model prepares arguments, the application executes each call and returns its result, and the next answer uses the outcome. A tool call can request information or an operation; it is not itself evidence that the operation completed. Keep the originating call and result associated through the conversation.
The maker also documents structured text constrained by a supplied JSON schema. Define the fields required by the application and their types, and keep source information separate from interpretation when they serve different purposes. Structured shape does not establish factual correctness; the original sources and actual tool results still determine the content of an inspectable answer.
Edition and continuity boundaries
Muse Spark 1.1 remains its own release. The specific coding changes of 1.2, long-horizon behavior updates of 1.3 and Standard 1.3's max setting should not be assigned to it merely because the family is shared. The maker's chat interface does not give external callers private reasoning to replay, so preserve visible history and use the continuity mechanisms offered by the connected interface.
The sources read do not state separate hard maximum input or output-token capacities beyond the documented context. Define the required text artifact and retain the evidence needed for each action or conclusion, keeping the model's planning and perception distinct from the environment that executes its proposed operations.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.1 | 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 $0.0025 / 1K tokens Output · Output tokens $0.0085 / 1K tokens Input · Cache read $0.0003 / 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 $0.0025 / 1K tokens Output · Output tokens $0.0085 / 1K tokens Input · Cache read $0.0003 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta/muse-spark-1.1",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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': 'meta/muse-spark-1.1', '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': 'meta/muse-spark-1.1', '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 meta/muse-spark-1.1
Use the method paths shown above.
Technical example in English
Plan an approval workflow\n\nPlan a document approval flow from these constraints: the author submits a draft; a reviewer must approve before the coordinator publishes; rejected drafts return to the author; publication needs a recorded approval ID. Give the ordered steps and evidence required at each transition. Mark any actor permission that the supplied rules do not define.A numbered workflow with approval evidence, rejection path and unresolved permission questions.Verify every publication path requires a recorded approval ID and rejection cannot skip review.