Muse Spark 1.2 Contributor is the experimental and prototyping edition of Meta's Muse Spark 1.2 reasoning family. Keep the Contributor identifier separate from Standard 1.2 and later 1.3 editions. The maker's family documentation describes agentic work, software assistants, multimodal reasoning, tool use and structured text results; it does not establish a separate Contributor performance guarantee from Standard demonstrations.
Documented inputs and context
The maker lists text, images, video, audio and PDFs as the 1.2 version's input modalities and text as output, with a 1,048,576-token context. That table defines the producer's documented model scope. The result can be a written explanation, structured findings or proposed code; rendering an interface, creating a recording or performing another external action needs an application component.
For a prototype, choose one defined task and supply the material needed to inspect its result. A screenshot can accompany a requirement for a particular interaction. A PDF can provide the statements to compare or extract. A video can show the visible sequence to describe, while an audio-visual question should identify which spoken or visible detail matters. Label each source and request the evidence supporting the answer.
The 1.2 release describes family strengths in turning visual material into code and reasoning about charts or scenes. Apply those as task domains rather than an assertion that this Contributor edition reproduces every Standard demo. A practical request can ask for the layout elements visible in a screenshot, a proposed implementation and the questions remaining about behavior not shown by the image.
Reasoning and result preparation
The Muse Spark reasoning guide provides minimal, low, medium, high and xhigh effort levels for this edition. Max is specific to Standard 1.3, and disabling reasoning with none is unsupported. Without an explicit setting, the model still uses a model-determined reasoning level. A small extraction and a multi-step visual or coding problem can therefore have different effort choices while retaining the same 1.2 Contributor identity.
The output budget covers internal reasoning and visible text together. Raw reasoning is private, so request the explanation or final artifact needed by the user rather than expecting the underlying trace. Set the task's answer length and fields according to what will be inspected afterwards.
For a document comparison, request the source statement, its page, the condition it establishes and any contradiction. For a code prototype, specify the accepted input, expected result and interface to preserve. Ask for the proposed fragment separately from its assumptions and example inputs. These requirements define a result that can be reviewed instead of an open-ended experiment with no completion criterion.
Tool-assisted experiments
Developer-defined tool use follows a model-and-application loop. The application describes functions, the model chooses an operation and prepares arguments, and the application executes it and returns the result. A lookup can supply reference information; an execution tool can supply what happened when proposed code ran. Keep the originating operation and returned result associated with one another before asking for the next answer.
The 1.2 family announcement emphasizes using tools to inspect visual inputs and generated artifacts more closely. That means the environment provides the inspection or rendering operation. A text proposal alone is not a rendered page or an executed interaction. Define what the tools return so the model can connect feedback to the actual requirement.
Structured output can organize the experiment's findings into a supplied schema. Define field names, required types and missing-value handling, retaining source identifiers beside extracted information. A syntactically valid record and a correct interpretation are different properties; keep the original material available for inspection of the latter.
Edition and continuity limits
The maker's ordinary chat workflow does not return private reasoning context for external callers to replay. Preserve visible history, source facts and tool outcomes when continuing an experiment, and use only the continuity mechanisms documented for the connected interface. Log probabilities are not supported for Muse Spark, so they should not be treated as a built-in confidence score for an extracted field.
The published context and modality table belongs to this named 1.2 edition; it should not inherit 1.3's max setting or its audio limitation. The sources read do not state a separate maximum input or output-token capacity beyond the context. Keep the prototype's goal, material and inspectable text result explicit, while preserving the Contributor identity and the actual results returned by its tools.
", "aboutText": "Muse Spark 1.2 Contributor is the experimental and prototyping edition of Meta's Muse Spark 1.2 reasoning family. Keep the Contributor identifier separate from Standard 1.2 and later 1.3 editions. The maker's family documentation describes agentic work, software assistants, multimodal reasoning, tool use and structured text results; it does not establish a separate Contributor performance guarantee from Standard demonstrations.\n\nDocumented inputs and context\n\nThe maker lists text, images, video, audio and PDFs as the 1.2 version's input modalities and text as output, with a 1,048,576-token context. That table defines the producer's documented model scope. The result can be a written explanation, structured findings or proposed code; rendering an interface, creating a recording or performing another external action needs an application component.\n\nFor a prototype, choose one defined task and supply the material needed to inspect its result. A screenshot can accompany a requirement for a particular interaction. A PDF can provide the statements to compare or extract. A video can show the visible sequence to describe, while an audio-visual question should identify which spoken or visible detail matters. Label each source and request the evidence supporting the answer.\n\nThe 1.2 release describes family strengths in turning visual material into code and reasoning about charts or scenes. Apply those as task domains rather than an assertion that this Contributor edition reproduces every Standard demo. A practical request can ask for the layout elements visible in a screenshot, a proposed implementation and the questions remaining about behavior not shown by the image.\n\nReasoning and result preparation\n\nThe Muse Spark reasoning guide provides minimal, low, medium, high and xhigh effort levels for this edition. Max is specific to Standard 1.3, and disabling reasoning with none is unsupported. Without an explicit setting, the model still uses a model-determined reasoning level. A small extraction and a multi-step visual or coding problem can therefore have different effort choices while retaining the same 1.2 Contributor identity.\n\nThe output budget covers internal reasoning and visible text together. Raw reasoning is private, so request the explanation or final artifact needed by the user rather than expecting the underlying trace. Set the task's answer length and fields according to what will be inspected afterwards.\n\nFor a document comparison, request the source statement, its page, the condition it establishes and any contradiction. For a code prototype, specify the accepted input, expected result and interface to preserve. Ask for the proposed fragment separately from its assumptions and example inputs. These requirements define a result that can be reviewed instead of an open-ended experiment with no completion criterion.\n\nTool-assisted experiments\n\nDeveloper-defined tool use follows a model-and-application loop. The application describes functions, the model chooses an operation and prepares arguments, and the application executes it and returns the result. A lookup can supply reference information; an execution tool can supply what happened when proposed code ran. Keep the originating operation and returned result associated with one another before asking for the next answer.\n\nThe 1.2 family announcement emphasizes using tools to inspect visual inputs and generated artifacts more closely. That means the environment provides the inspection or rendering operation. A text proposal alone is not a rendered page or an executed interaction. Define what the tools return so the model can connect feedback to the actual requirement.\n\nStructured output can organize the experiment's findings into a supplied schema. Define field names, required types and missing-value handling, retaining source identifiers beside extracted information. A syntactically valid record and a correct interpretation are different properties; keep the original material available for inspection of the latter.\n\nEdition and continuity limits\n\nThe maker's ordinary chat workflow does not return private reasoning context for external callers to replay. Preserve visible history, source facts and tool outcomes when continuing an experiment, and use only the continuity mechanisms documented for the connected interface. Log probabilities are not supported for Muse Spark, so they should not be treated as a built-in confidence score for an extracted field.\n\nThe published context and modality table belongs to this named 1.2 edition; it should not inherit 1.3's max setting or its audio limitation. The sources read do not state a separate maximum input or output-token capacity beyond the context. Keep the prototype's goal, material and inspectable text result explicit, while preserving the Contributor identity and the actual results returned by its tools.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Prototype a bounded state reducer\n\nPropose a JavaScript reducer for an upload widget with states idle, uploading, success and error. Events start, finish and fail are supplied as plain strings. Only uploading may transition to success or error; start resets any state to uploading. Include a transition table and tests for an invalid finish from idle.Reducer code, a transition table and tests covering valid and ignored transitions.Check that finish from idle is ignored and that the proposal does not claim a rendered or executed widget.meta/muse-spark-1.2-contributorMuse Spark 1.2 Contributor is a separately named Meta reasoning edition for prototype and experimental agent workflows. Meta documents a 1,048,576-token context and multimodal input with text output; the edition retains its own identity and reasoning levels without 1.3 Standard's max.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Muse Spark 1.2 Contributor is the experimental and prototyping edition of Meta's Muse Spark 1.2 reasoning family. Keep the Contributor identifier separate from Standard 1.2 and later 1.3 editions. The maker's family documentation describes agentic work, software assistants, multimodal reasoning, tool use and structured text results; it does not establish a separate Contributor performance guarantee from Standard demonstrations.
Documented inputs and context
The maker lists text, images, video, audio and PDFs as the 1.2 version's input modalities and text as output, with a 1,048,576-token context. That table defines the producer's documented model scope. The result can be a written explanation, structured findings or proposed code; rendering an interface, creating a recording or performing another external action needs an application component.
For a prototype, choose one defined task and supply the material needed to inspect its result. A screenshot can accompany a requirement for a particular interaction. A PDF can provide the statements to compare or extract. A video can show the visible sequence to describe, while an audio-visual question should identify which spoken or visible detail matters. Label each source and request the evidence supporting the answer.
The 1.2 release describes family strengths in turning visual material into code and reasoning about charts or scenes. Apply those as task domains rather than an assertion that this Contributor edition reproduces every Standard demo. A practical request can ask for the layout elements visible in a screenshot, a proposed implementation and the questions remaining about behavior not shown by the image.
Reasoning and result preparation
The Muse Spark reasoning guide provides minimal, low, medium, high and xhigh effort levels for this edition. Max is specific to Standard 1.3, and disabling reasoning with none is unsupported. Without an explicit setting, the model still uses a model-determined reasoning level. A small extraction and a multi-step visual or coding problem can therefore have different effort choices while retaining the same 1.2 Contributor identity.
The output budget covers internal reasoning and visible text together. Raw reasoning is private, so request the explanation or final artifact needed by the user rather than expecting the underlying trace. Set the task's answer length and fields according to what will be inspected afterwards.
For a document comparison, request the source statement, its page, the condition it establishes and any contradiction. For a code prototype, specify the accepted input, expected result and interface to preserve. Ask for the proposed fragment separately from its assumptions and example inputs. These requirements define a result that can be reviewed instead of an open-ended experiment with no completion criterion.
Tool-assisted experiments
Developer-defined tool use follows a model-and-application loop. The application describes functions, the model chooses an operation and prepares arguments, and the application executes it and returns the result. A lookup can supply reference information; an execution tool can supply what happened when proposed code ran. Keep the originating operation and returned result associated with one another before asking for the next answer.
The 1.2 family announcement emphasizes using tools to inspect visual inputs and generated artifacts more closely. That means the environment provides the inspection or rendering operation. A text proposal alone is not a rendered page or an executed interaction. Define what the tools return so the model can connect feedback to the actual requirement.
Structured output can organize the experiment's findings into a supplied schema. Define field names, required types and missing-value handling, retaining source identifiers beside extracted information. A syntactically valid record and a correct interpretation are different properties; keep the original material available for inspection of the latter.
Edition and continuity limits
The maker's ordinary chat workflow does not return private reasoning context for external callers to replay. Preserve visible history, source facts and tool outcomes when continuing an experiment, and use only the continuity mechanisms documented for the connected interface. Log probabilities are not supported for Muse Spark, so they should not be treated as a built-in confidence score for an extracted field.
The published context and modality table belongs to this named 1.2 edition; it should not inherit 1.3's max setting or its audio limitation. The sources read do not state a separate maximum input or output-token capacity beyond the context. Keep the prototype's goal, material and inspectable text result explicit, while preserving the Contributor identity and the actual results returned by its tools.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.2-contributor | 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.000004 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.000004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${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-1.2-contributor", "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-1.2-contributor',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-1.2-contributor',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-1.2-contributor
Use the method paths shown above.
meta/muse-spark-1.2-contributorMuse Spark 1.2 Contributor is a separately named Meta reasoning edition for prototype and experimental agent workflows. Meta documents a 1,048,576-token context and multimodal input with text output; the edition retains its own identity and reasoning levels without 1.3 Standard's max.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Muse Spark 1.2 Contributor is the experimental and prototyping edition of Meta's Muse Spark 1.2 reasoning family. Keep the Contributor identifier separate from Standard 1.2 and later 1.3 editions. The maker's family documentation describes agentic work, software assistants, multimodal reasoning, tool use and structured text results; it does not establish a separate Contributor performance guarantee from Standard demonstrations.
Documented inputs and context
The maker lists text, images, video, audio and PDFs as the 1.2 version's input modalities and text as output, with a 1,048,576-token context. That table defines the producer's documented model scope. The result can be a written explanation, structured findings or proposed code; rendering an interface, creating a recording or performing another external action needs an application component.
For a prototype, choose one defined task and supply the material needed to inspect its result. A screenshot can accompany a requirement for a particular interaction. A PDF can provide the statements to compare or extract. A video can show the visible sequence to describe, while an audio-visual question should identify which spoken or visible detail matters. Label each source and request the evidence supporting the answer.
The 1.2 release describes family strengths in turning visual material into code and reasoning about charts or scenes. Apply those as task domains rather than an assertion that this Contributor edition reproduces every Standard demo. A practical request can ask for the layout elements visible in a screenshot, a proposed implementation and the questions remaining about behavior not shown by the image.
Reasoning and result preparation
The Muse Spark reasoning guide provides minimal, low, medium, high and xhigh effort levels for this edition. Max is specific to Standard 1.3, and disabling reasoning with none is unsupported. Without an explicit setting, the model still uses a model-determined reasoning level. A small extraction and a multi-step visual or coding problem can therefore have different effort choices while retaining the same 1.2 Contributor identity.
The output budget covers internal reasoning and visible text together. Raw reasoning is private, so request the explanation or final artifact needed by the user rather than expecting the underlying trace. Set the task's answer length and fields according to what will be inspected afterwards.
For a document comparison, request the source statement, its page, the condition it establishes and any contradiction. For a code prototype, specify the accepted input, expected result and interface to preserve. Ask for the proposed fragment separately from its assumptions and example inputs. These requirements define a result that can be reviewed instead of an open-ended experiment with no completion criterion.
Tool-assisted experiments
Developer-defined tool use follows a model-and-application loop. The application describes functions, the model chooses an operation and prepares arguments, and the application executes it and returns the result. A lookup can supply reference information; an execution tool can supply what happened when proposed code ran. Keep the originating operation and returned result associated with one another before asking for the next answer.
The 1.2 family announcement emphasizes using tools to inspect visual inputs and generated artifacts more closely. That means the environment provides the inspection or rendering operation. A text proposal alone is not a rendered page or an executed interaction. Define what the tools return so the model can connect feedback to the actual requirement.
Structured output can organize the experiment's findings into a supplied schema. Define field names, required types and missing-value handling, retaining source identifiers beside extracted information. A syntactically valid record and a correct interpretation are different properties; keep the original material available for inspection of the latter.
Edition and continuity limits
The maker's ordinary chat workflow does not return private reasoning context for external callers to replay. Preserve visible history, source facts and tool outcomes when continuing an experiment, and use only the continuity mechanisms documented for the connected interface. Log probabilities are not supported for Muse Spark, so they should not be treated as a built-in confidence score for an extracted field.
The published context and modality table belongs to this named 1.2 edition; it should not inherit 1.3's max setting or its audio limitation. The sources read do not state a separate maximum input or output-token capacity beyond the context. Keep the prototype's goal, material and inspectable text result explicit, while preserving the Contributor identity and the actual results returned by its tools.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.2-contributor | 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.000004 / 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 $0.0002 / 1K tokens Output · Output tokens $0.0004 / 1K tokens Input · Cache read $0.000004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta/muse-spark-1.2-contributor",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-1.2-contributor', '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-1.2-contributor', '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-1.2-contributor
Use the method paths shown above.
Technical example in English
Prototype a bounded state reducer\n\nPropose a JavaScript reducer for an upload widget with states idle, uploading, success and error. Events start, finish and fail are supplied as plain strings. Only uploading may transition to success or error; start resets any state to uploading. Include a transition table and tests for an invalid finish from idle.Reducer code, a transition table and tests covering valid and ignored transitions.Check that finish from idle is ignored and that the proposal does not claim a rendered or executed widget.