Muse Spark 1.3 Contributor is a separately named edition in Meta's Muse Spark family for prototyping and experimentation. The family is designed for agentic and coding work: multi-step tool loops, software assistants and reasoning over substantial source material. Keep the Contributor name when selecting the edition rather than treating it as the Standard 1.3 entry with every setting transferred unchanged.
Inputs and context
The official model table lists text, images, video and PDFs as inputs and text as output, with a context window of 1,048,576 tokens. A task can combine a written requirement, a screenshot, a relevant clip or document pages and request a written explanation, structured findings or proposed code. The model's text result can become an artifact in the surrounding application; rendering a page or executing code requires that application environment.
Identify each source and its role before asking for a result. A prototype interface task can pair a screenshot with the desired behavior and the existing code fragment. Ask for the visible differences, the proposed implementation change and the assumptions that still need clarification. A document task can define the fields to extract and request the supporting page or passage beside each finding.
The maker notes that audio understanding in the 1.3 version is not fully supported and may give degraded responses. Treat that as a version-specific limitation rather than copying the audio capabilities of Muse Spark 1.2 or a separately named transcription model into this description.
Reasoning levels and answer budget
Muse Spark generates internal reasoning before its visible answer. The documented effort levels applicable here are minimal, low, medium, high and xhigh. The max level belongs specifically to Standard Muse Spark 1.3 and is not available for Contributor models. Disabling reasoning with none is not supported; omitting the setting still leaves the model reasoning at a model-determined level.
The output-token budget covers both internal reasoning and visible text. A request for a long written result therefore needs space for both, especially at a higher reasoning effort. The raw internal reasoning stays private, and log probabilities are not supported as a confidence measure. Request the explanation, fields or final code needed by the task rather than assuming the underlying reasoning trace will be returned as readable text.
For a focused extraction or formatting experiment, define the exact record and source material. For a multi-step coding or visual problem, define the intermediate decisions and the final artifact. Higher reasoning effort changes the reasoning allocation; it does not by itself define what constitutes a completed, useful result.
Tools and structured findings
The maker's Muse Spark documentation describes developer-defined tool calling and structured output. The application supplies the tool definitions, the model decides which operation is needed and prepares its arguments, and the application executes each call and returns the corresponding result. The next answer can use those results to decide what to do next. A proposed call is distinct from a completed operation.
The same documentation distinguishes connected built-in search tools from developer-defined functions. Search or code execution is part of the tool environment, not an additional content modality of the text answer. In a prototype, supply only the operations relevant to the question and describe what each returns so the subsequent answer remains connected to actual retrieved or computed information.
For structured extraction, specify the field names, required information and representation for missing values. A practical record can contain the source identifier, observed fact, interpretation and question still needing clarification. Keep the record separate from optional prose when an application must process the fields reliably. The maker's schema interface rejects recursive schemas and limits nesting to ten levels. Its strict mode requires a plain-object root, every listed property required and extra properties disallowed. A matched structure does not establish factual correctness.
A useful prototype task
Choose one workflow that can produce an inspectable artifact. Supply the requirement, a visual example and the code determining the current behavior. Request a short comparison, a proposed revised fragment and examples that distinguish the expected behavior from the current one. Include any lookup or execution result returned by the application before asking for the final explanation.
For a document-oriented prototype, give the PDF and the question to answer, then ask for a source-linked summary or comparison table. For video, identify the event or visual relationship to inspect and request an ordered description with the observations supporting it. Define the length and sections of the final answer so the model's large context serves the actual question.
Edition and continuity boundaries
Contributor remains its own named 1.3 edition, with the documented context and input types. Meta's reasoning guide distinguishes ordinary conversation history from preservation of private reasoning across turns: the maker's chat interface does not return that private trace to external callers. Keep the visible messages, sources and tool outcomes needed for a follow-up rather than assuming every interface carries internal reasoning forward.
The sources read do not specify a separate hard maximum input or output-token capacity beyond the context window. Preserve the edition, input preparation and requested artifact, and keep tool execution and final text delivery connected to the results actually obtained in the prototype workflow.
", "aboutText": "Muse Spark 1.3 Contributor is a separately named edition in Meta's Muse Spark family for prototyping and experimentation. The family is designed for agentic and coding work: multi-step tool loops, software assistants and reasoning over substantial source material. Keep the Contributor name when selecting the edition rather than treating it as the Standard 1.3 entry with every setting transferred unchanged.\n\nInputs and context\n\nThe official model table lists text, images, video and PDFs as inputs and text as output, with a context window of 1,048,576 tokens. A task can combine a written requirement, a screenshot, a relevant clip or document pages and request a written explanation, structured findings or proposed code. The model's text result can become an artifact in the surrounding application; rendering a page or executing code requires that application environment.\n\nIdentify each source and its role before asking for a result. A prototype interface task can pair a screenshot with the desired behavior and the existing code fragment. Ask for the visible differences, the proposed implementation change and the assumptions that still need clarification. A document task can define the fields to extract and request the supporting page or passage beside each finding.\n\nThe maker notes that audio understanding in the 1.3 version is not fully supported and may give degraded responses. Treat that as a version-specific limitation rather than copying the audio capabilities of Muse Spark 1.2 or a separately named transcription model into this description.\n\nReasoning levels and answer budget\n\nMuse Spark generates internal reasoning before its visible answer. The documented effort levels applicable here are minimal, low, medium, high and xhigh. The max level belongs specifically to Standard Muse Spark 1.3 and is not available for Contributor models. Disabling reasoning with none is not supported; omitting the setting still leaves the model reasoning at a model-determined level.\n\nThe output-token budget covers both internal reasoning and visible text. A request for a long written result therefore needs space for both, especially at a higher reasoning effort. The raw internal reasoning stays private, and log probabilities are not supported as a confidence measure. Request the explanation, fields or final code needed by the task rather than assuming the underlying reasoning trace will be returned as readable text.\n\nFor a focused extraction or formatting experiment, define the exact record and source material. For a multi-step coding or visual problem, define the intermediate decisions and the final artifact. Higher reasoning effort changes the reasoning allocation; it does not by itself define what constitutes a completed, useful result.\n\nTools and structured findings\n\nThe maker's Muse Spark documentation describes developer-defined tool calling and structured output. The application supplies the tool definitions, the model decides which operation is needed and prepares its arguments, and the application executes each call and returns the corresponding result. The next answer can use those results to decide what to do next. A proposed call is distinct from a completed operation.\n\nThe same documentation distinguishes connected built-in search tools from developer-defined functions. Search or code execution is part of the tool environment, not an additional content modality of the text answer. In a prototype, supply only the operations relevant to the question and describe what each returns so the subsequent answer remains connected to actual retrieved or computed information.\n\nFor structured extraction, specify the field names, required information and representation for missing values. A practical record can contain the source identifier, observed fact, interpretation and question still needing clarification. Keep the record separate from optional prose when an application must process the fields reliably. The maker's schema interface rejects recursive schemas and limits nesting to ten levels. Its strict mode requires a plain-object root, every listed property required and extra properties disallowed. A matched structure does not establish factual correctness.\n\nA useful prototype task\n\nChoose one workflow that can produce an inspectable artifact. Supply the requirement, a visual example and the code determining the current behavior. Request a short comparison, a proposed revised fragment and examples that distinguish the expected behavior from the current one. Include any lookup or execution result returned by the application before asking for the final explanation.\n\nFor a document-oriented prototype, give the PDF and the question to answer, then ask for a source-linked summary or comparison table. For video, identify the event or visual relationship to inspect and request an ordered description with the observations supporting it. Define the length and sections of the final answer so the model's large context serves the actual question.\n\nEdition and continuity boundaries\n\nContributor remains its own named 1.3 edition, with the documented context and input types. Meta's reasoning guide distinguishes ordinary conversation history from preservation of private reasoning across turns: the maker's chat interface does not return that private trace to external callers. Keep the visible messages, sources and tool outcomes needed for a follow-up rather than assuming every interface carries internal reasoning forward.\n\nThe sources read do not specify a separate hard maximum input or output-token capacity beyond the context window. Preserve the edition, input preparation and requested artifact, and keep tool execution and final text delivery connected to the results actually obtained in the prototype workflow.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Prototype and test a text-only helper\n\nDesign a small Python prototype for an appointment reminder. Input records contain id and minutes_until_start. Return IDs where 0 <= minutes_until_start <= 30, preserving input order. Supply the function and cases at -1, 0, 30 and 31 minutes. Include a short note on assumptions; no calendar connection or reminder sending is available.A self-contained function, boundary-case assertions and explicit assumptions about input fields.Exactly the 0- and 30-minute records qualify, and the function does not send messages or assume calendar access.meta/muse-spark-1.3-contributorMuse Spark 1.3 Contributor is a reasoning edition in Meta's agentic and coding family for prototype workflows. Its maker lists text, image, video and PDF inputs, text output and a 1,048,576-token context, with reasoning levels through xhigh rather than Standard 1.3'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 1.3 Contributor is a separately named edition in Meta's Muse Spark family for prototyping and experimentation. The family is designed for agentic and coding work: multi-step tool loops, software assistants and reasoning over substantial source material. Keep the Contributor name when selecting the edition rather than treating it as the Standard 1.3 entry with every setting transferred unchanged.
Inputs and context
The official model table lists text, images, video and PDFs as inputs and text as output, with a context window of 1,048,576 tokens. A task can combine a written requirement, a screenshot, a relevant clip or document pages and request a written explanation, structured findings or proposed code. The model's text result can become an artifact in the surrounding application; rendering a page or executing code requires that application environment.
Identify each source and its role before asking for a result. A prototype interface task can pair a screenshot with the desired behavior and the existing code fragment. Ask for the visible differences, the proposed implementation change and the assumptions that still need clarification. A document task can define the fields to extract and request the supporting page or passage beside each finding.
The maker notes that audio understanding in the 1.3 version is not fully supported and may give degraded responses. Treat that as a version-specific limitation rather than copying the audio capabilities of Muse Spark 1.2 or a separately named transcription model into this description.
Reasoning levels and answer budget
Muse Spark generates internal reasoning before its visible answer. The documented effort levels applicable here are minimal, low, medium, high and xhigh. The max level belongs specifically to Standard Muse Spark 1.3 and is not available for Contributor models. Disabling reasoning with none is not supported; omitting the setting still leaves the model reasoning at a model-determined level.
The output-token budget covers both internal reasoning and visible text. A request for a long written result therefore needs space for both, especially at a higher reasoning effort. The raw internal reasoning stays private, and log probabilities are not supported as a confidence measure. Request the explanation, fields or final code needed by the task rather than assuming the underlying reasoning trace will be returned as readable text.
For a focused extraction or formatting experiment, define the exact record and source material. For a multi-step coding or visual problem, define the intermediate decisions and the final artifact. Higher reasoning effort changes the reasoning allocation; it does not by itself define what constitutes a completed, useful result.
Tools and structured findings
The maker's Muse Spark documentation describes developer-defined tool calling and structured output. The application supplies the tool definitions, the model decides which operation is needed and prepares its arguments, and the application executes each call and returns the corresponding result. The next answer can use those results to decide what to do next. A proposed call is distinct from a completed operation.
The same documentation distinguishes connected built-in search tools from developer-defined functions. Search or code execution is part of the tool environment, not an additional content modality of the text answer. In a prototype, supply only the operations relevant to the question and describe what each returns so the subsequent answer remains connected to actual retrieved or computed information.
For structured extraction, specify the field names, required information and representation for missing values. A practical record can contain the source identifier, observed fact, interpretation and question still needing clarification. Keep the record separate from optional prose when an application must process the fields reliably. The maker's schema interface rejects recursive schemas and limits nesting to ten levels. Its strict mode requires a plain-object root, every listed property required and extra properties disallowed. A matched structure does not establish factual correctness.
A useful prototype task
Choose one workflow that can produce an inspectable artifact. Supply the requirement, a visual example and the code determining the current behavior. Request a short comparison, a proposed revised fragment and examples that distinguish the expected behavior from the current one. Include any lookup or execution result returned by the application before asking for the final explanation.
For a document-oriented prototype, give the PDF and the question to answer, then ask for a source-linked summary or comparison table. For video, identify the event or visual relationship to inspect and request an ordered description with the observations supporting it. Define the length and sections of the final answer so the model's large context serves the actual question.
Edition and continuity boundaries
Contributor remains its own named 1.3 edition, with the documented context and input types. Meta's reasoning guide distinguishes ordinary conversation history from preservation of private reasoning across turns: the maker's chat interface does not return that private trace to external callers. Keep the visible messages, sources and tool outcomes needed for a follow-up rather than assuming every interface carries internal reasoning forward.
The sources read do not specify a separate hard maximum input or output-token capacity beyond the context window. Preserve the edition, input preparation and requested artifact, and keep tool execution and final text delivery connected to the results actually obtained in the prototype workflow.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.3-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-1.3-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-1.3-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-1.3-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-1.3-contributor
Use the method paths shown above.
meta/muse-spark-1.3-contributorMuse Spark 1.3 Contributor is a reasoning edition in Meta's agentic and coding family for prototype workflows. Its maker lists text, image, video and PDF inputs, text output and a 1,048,576-token context, with reasoning levels through xhigh rather than Standard 1.3'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 1.3 Contributor is a separately named edition in Meta's Muse Spark family for prototyping and experimentation. The family is designed for agentic and coding work: multi-step tool loops, software assistants and reasoning over substantial source material. Keep the Contributor name when selecting the edition rather than treating it as the Standard 1.3 entry with every setting transferred unchanged.
Inputs and context
The official model table lists text, images, video and PDFs as inputs and text as output, with a context window of 1,048,576 tokens. A task can combine a written requirement, a screenshot, a relevant clip or document pages and request a written explanation, structured findings or proposed code. The model's text result can become an artifact in the surrounding application; rendering a page or executing code requires that application environment.
Identify each source and its role before asking for a result. A prototype interface task can pair a screenshot with the desired behavior and the existing code fragment. Ask for the visible differences, the proposed implementation change and the assumptions that still need clarification. A document task can define the fields to extract and request the supporting page or passage beside each finding.
The maker notes that audio understanding in the 1.3 version is not fully supported and may give degraded responses. Treat that as a version-specific limitation rather than copying the audio capabilities of Muse Spark 1.2 or a separately named transcription model into this description.
Reasoning levels and answer budget
Muse Spark generates internal reasoning before its visible answer. The documented effort levels applicable here are minimal, low, medium, high and xhigh. The max level belongs specifically to Standard Muse Spark 1.3 and is not available for Contributor models. Disabling reasoning with none is not supported; omitting the setting still leaves the model reasoning at a model-determined level.
The output-token budget covers both internal reasoning and visible text. A request for a long written result therefore needs space for both, especially at a higher reasoning effort. The raw internal reasoning stays private, and log probabilities are not supported as a confidence measure. Request the explanation, fields or final code needed by the task rather than assuming the underlying reasoning trace will be returned as readable text.
For a focused extraction or formatting experiment, define the exact record and source material. For a multi-step coding or visual problem, define the intermediate decisions and the final artifact. Higher reasoning effort changes the reasoning allocation; it does not by itself define what constitutes a completed, useful result.
Tools and structured findings
The maker's Muse Spark documentation describes developer-defined tool calling and structured output. The application supplies the tool definitions, the model decides which operation is needed and prepares its arguments, and the application executes each call and returns the corresponding result. The next answer can use those results to decide what to do next. A proposed call is distinct from a completed operation.
The same documentation distinguishes connected built-in search tools from developer-defined functions. Search or code execution is part of the tool environment, not an additional content modality of the text answer. In a prototype, supply only the operations relevant to the question and describe what each returns so the subsequent answer remains connected to actual retrieved or computed information.
For structured extraction, specify the field names, required information and representation for missing values. A practical record can contain the source identifier, observed fact, interpretation and question still needing clarification. Keep the record separate from optional prose when an application must process the fields reliably. The maker's schema interface rejects recursive schemas and limits nesting to ten levels. Its strict mode requires a plain-object root, every listed property required and extra properties disallowed. A matched structure does not establish factual correctness.
A useful prototype task
Choose one workflow that can produce an inspectable artifact. Supply the requirement, a visual example and the code determining the current behavior. Request a short comparison, a proposed revised fragment and examples that distinguish the expected behavior from the current one. Include any lookup or execution result returned by the application before asking for the final explanation.
For a document-oriented prototype, give the PDF and the question to answer, then ask for a source-linked summary or comparison table. For video, identify the event or visual relationship to inspect and request an ordered description with the observations supporting it. Define the length and sections of the final answer so the model's large context serves the actual question.
Edition and continuity boundaries
Contributor remains its own named 1.3 edition, with the documented context and input types. Meta's reasoning guide distinguishes ordinary conversation history from preservation of private reasoning across turns: the maker's chat interface does not return that private trace to external callers. Keep the visible messages, sources and tool outcomes needed for a follow-up rather than assuming every interface carries internal reasoning forward.
The sources read do not specify a separate hard maximum input or output-token capacity beyond the context window. Preserve the edition, input preparation and requested artifact, and keep tool execution and final text delivery connected to the results actually obtained in the prototype workflow.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.3-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 $0.000004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta/muse-spark-1.3-contributor",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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-1.3-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-1.3-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-1.3-contributor
Use the method paths shown above.
Technical example in English
Prototype and test a text-only helper\n\nDesign a small Python prototype for an appointment reminder. Input records contain id and minutes_until_start. Return IDs where 0 <= minutes_until_start <= 30, preserving input order. Supply the function and cases at -1, 0, 30 and 31 minutes. Include a short note on assumptions; no calendar connection or reminder sending is available.A self-contained function, boundary-case assertions and explicit assumptions about input fields.Exactly the 0- and 30-minute records qualify, and the function does not send messages or assume calendar access.