Muse Spark 1.3 is Meta's reasoning model for sustained agentic and coding work. The maker emphasizes keeping context and earlier results across extended tasks, working through conflicting sources and producing a finished deliverable. This entry is the Standard 1.3 edition, whose documented reasoning settings include max; the separately named Contributor edition has its own setting boundaries.
Long-horizon agent work
The release describes a model trained across different agent environments to gather information, revise a plan when evidence changes and preserve detailed requirements through a multi-step task. It also describes improved handling of several workflows in one thread, with incoming requests mapped to the relevant task. A useful request should define the objective, sources, requirements and artifact that will count as completion.
For a professional document task, provide the source reports, identify which facts must survive and ask for a structured brief with source locations. If the sources conflict, request the conflicting statements separately and the information needed to resolve them. For a coding task, include the intended behavior, affected modules and relevant code; ask for the proposed implementation and the evidence that would distinguish the intended result.
The maker says 1.3 asks for clarification when a request is ambiguous and seeks user help when blocked. It also describes better judgment around consequential actions. These are model behavior improvements rather than a replacement for the application's execution controls. Give the agent the information needed to decide and make the required result explicit.
Coding and multimodal evidence
The release focuses on longer coding tasks, cleaner output and fewer unnecessary turns compared with 1.2. A coding-agent workflow can inspect a screenshot, locate the relevant code, propose a correction and use execution or rendered feedback returned by its tools. State the interface that must remain compatible and request the changed artifact separately from its assumptions and explanation.
The official model table lists text, image, video and PDF input with text output and a 1,048,576-token context. Images or clips can supply visible evidence alongside the written task. A chart question should retain axes, legends and units; a screenshot question should identify the behavior to reproduce or inspect. A PDF question can ask for a source-linked extraction or comparison rather than a general summary of every page.
The maker explicitly notes that audio understanding in 1.3 is not fully supported and responses containing audio may degrade. That is distinct from 1.2's documented audio-visual capability. The model's text result also does not itself generate an image, spoken recording or finished file without the surrounding application tools.
Reasoning effort and continuity
The documented levels are minimal, low, medium, high, xhigh and max. Max is specific to Standard 1.3. Muse Spark does not support disabling reasoning with none; omitting the setting leaves a model-determined reasoning level. Choose the effort for the actual problem and leave room for both the internal reasoning and the required written result.
Reasoning tokens and visible tokens share the output budget. Raw internal reasoning stays private and is not returned as ordinary readable text. The maker distinguishes visible conversation history from private reasoning continuity: its chat interface does not expose a trace external callers can replay, while its other documented conversation workflow supports managed or encrypted reasoning continuation. Preserve the sources, visible messages and actual tool results needed by a follow-up rather than assuming all interfaces retain private reasoning identically.
Tools and structured deliverables
The application supplies developer-defined function descriptions, the model creates the required call arguments, and the application executes each call and returns the associated result. The model may request several functions in a turn. Return the result for each originating operation before asking for the next conclusion, so the answer uses actual retrieved or computed information.
The maker separately documents built-in search tools that execute within its connected service. Developer functions and those built-in tools have different execution arrangements. The model can reason about what information it needs, but selecting the model alone does not provide repository access, a browser or a private information source.
Structured output can constrain the result to a supplied JSON schema. Define the fields and types needed by the next step and the treatment of missing source information. In the maker's strict schema mode, the root is a plain object, every property is required and extra properties are disallowed; recursive schemas are rejected. These are constraints on the maker's structured interface, not proof that the facts inside a correctly shaped record are true.
For a useful final artifact, request the source-backed findings, the proposed change or document and the unresolved conditions separately. The sources read do not give an independent hard maximum input or output-token capacity beyond the documented context. Keep the Standard 1.3 identity, reasoning choice and connected execution results explicit throughout the task.
", "aboutText": "Muse Spark 1.3 is Meta's reasoning model for sustained agentic and coding work. The maker emphasizes keeping context and earlier results across extended tasks, working through conflicting sources and producing a finished deliverable. This entry is the Standard 1.3 edition, whose documented reasoning settings include max; the separately named Contributor edition has its own setting boundaries.\n\nLong-horizon agent work\n\nThe release describes a model trained across different agent environments to gather information, revise a plan when evidence changes and preserve detailed requirements through a multi-step task. It also describes improved handling of several workflows in one thread, with incoming requests mapped to the relevant task. A useful request should define the objective, sources, requirements and artifact that will count as completion.\n\nFor a professional document task, provide the source reports, identify which facts must survive and ask for a structured brief with source locations. If the sources conflict, request the conflicting statements separately and the information needed to resolve them. For a coding task, include the intended behavior, affected modules and relevant code; ask for the proposed implementation and the evidence that would distinguish the intended result.\n\nThe maker says 1.3 asks for clarification when a request is ambiguous and seeks user help when blocked. It also describes better judgment around consequential actions. These are model behavior improvements rather than a replacement for the application's execution controls. Give the agent the information needed to decide and make the required result explicit.\n\nCoding and multimodal evidence\n\nThe release focuses on longer coding tasks, cleaner output and fewer unnecessary turns compared with 1.2. A coding-agent workflow can inspect a screenshot, locate the relevant code, propose a correction and use execution or rendered feedback returned by its tools. State the interface that must remain compatible and request the changed artifact separately from its assumptions and explanation.\n\nThe official model table lists text, image, video and PDF input with text output and a 1,048,576-token context. Images or clips can supply visible evidence alongside the written task. A chart question should retain axes, legends and units; a screenshot question should identify the behavior to reproduce or inspect. A PDF question can ask for a source-linked extraction or comparison rather than a general summary of every page.\n\nThe maker explicitly notes that audio understanding in 1.3 is not fully supported and responses containing audio may degrade. That is distinct from 1.2's documented audio-visual capability. The model's text result also does not itself generate an image, spoken recording or finished file without the surrounding application tools.\n\nReasoning effort and continuity\n\nThe documented levels are minimal, low, medium, high, xhigh and max. Max is specific to Standard 1.3. Muse Spark does not support disabling reasoning with none; omitting the setting leaves a model-determined reasoning level. Choose the effort for the actual problem and leave room for both the internal reasoning and the required written result.\n\nReasoning tokens and visible tokens share the output budget. Raw internal reasoning stays private and is not returned as ordinary readable text. The maker distinguishes visible conversation history from private reasoning continuity: its chat interface does not expose a trace external callers can replay, while its other documented conversation workflow supports managed or encrypted reasoning continuation. Preserve the sources, visible messages and actual tool results needed by a follow-up rather than assuming all interfaces retain private reasoning identically.\n\nTools and structured deliverables\n\nThe application supplies developer-defined function descriptions, the model creates the required call arguments, and the application executes each call and returns the associated result. The model may request several functions in a turn. Return the result for each originating operation before asking for the next conclusion, so the answer uses actual retrieved or computed information.\n\nThe maker separately documents built-in search tools that execute within its connected service. Developer functions and those built-in tools have different execution arrangements. The model can reason about what information it needs, but selecting the model alone does not provide repository access, a browser or a private information source.\n\nStructured output can constrain the result to a supplied JSON schema. Define the fields and types needed by the next step and the treatment of missing source information. In the maker's strict schema mode, the root is a plain object, every property is required and extra properties are disallowed; recursive schemas are rejected. These are constraints on the maker's structured interface, not proof that the facts inside a correctly shaped record are true.\n\nFor a useful final artifact, request the source-backed findings, the proposed change or document and the unresolved conditions separately. The sources read do not give an independent hard maximum input or output-token capacity beyond the documented context. Keep the Standard 1.3 identity, reasoning choice and connected execution results explicit throughout the task.", "editorialOverlay": { "copy_fields": { "practical_html": "Technical example in English
Resolve conflicting project reports\n\nPrepare a decision brief from these reports. Engineering E: migration scripts passed staging checks. Operations O: production backup restoration has not been rehearsed. Release policy P: rehearsal must pass before migration approval. State what is established, what blocks approval and the next evidence needed. Keep staging success separate from production readiness and cite E, O or P beside each point.A source-linked brief with established facts, the blocking condition and one concrete evidence request.Staging checks alone never satisfy the policy's restoration-rehearsal requirement.meta/muse-spark-1.3Muse Spark 1.3 is Meta's multimodal reasoning model for long-running agents and coding workflows. It tracks sources and prior results, supports a 1,048,576-token maker context and reasoning levels through max on this Standard edition, returning text and proposed tool actions.
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 is Meta's reasoning model for sustained agentic and coding work. The maker emphasizes keeping context and earlier results across extended tasks, working through conflicting sources and producing a finished deliverable. This entry is the Standard 1.3 edition, whose documented reasoning settings include max; the separately named Contributor edition has its own setting boundaries.
Long-horizon agent work
The release describes a model trained across different agent environments to gather information, revise a plan when evidence changes and preserve detailed requirements through a multi-step task. It also describes improved handling of several workflows in one thread, with incoming requests mapped to the relevant task. A useful request should define the objective, sources, requirements and artifact that will count as completion.
For a professional document task, provide the source reports, identify which facts must survive and ask for a structured brief with source locations. If the sources conflict, request the conflicting statements separately and the information needed to resolve them. For a coding task, include the intended behavior, affected modules and relevant code; ask for the proposed implementation and the evidence that would distinguish the intended result.
The maker says 1.3 asks for clarification when a request is ambiguous and seeks user help when blocked. It also describes better judgment around consequential actions. These are model behavior improvements rather than a replacement for the application's execution controls. Give the agent the information needed to decide and make the required result explicit.
Coding and multimodal evidence
The release focuses on longer coding tasks, cleaner output and fewer unnecessary turns compared with 1.2. A coding-agent workflow can inspect a screenshot, locate the relevant code, propose a correction and use execution or rendered feedback returned by its tools. State the interface that must remain compatible and request the changed artifact separately from its assumptions and explanation.
The official model table lists text, image, video and PDF input with text output and a 1,048,576-token context. Images or clips can supply visible evidence alongside the written task. A chart question should retain axes, legends and units; a screenshot question should identify the behavior to reproduce or inspect. A PDF question can ask for a source-linked extraction or comparison rather than a general summary of every page.
The maker explicitly notes that audio understanding in 1.3 is not fully supported and responses containing audio may degrade. That is distinct from 1.2's documented audio-visual capability. The model's text result also does not itself generate an image, spoken recording or finished file without the surrounding application tools.
Reasoning effort and continuity
The documented levels are minimal, low, medium, high, xhigh and max. Max is specific to Standard 1.3. Muse Spark does not support disabling reasoning with none; omitting the setting leaves a model-determined reasoning level. Choose the effort for the actual problem and leave room for both the internal reasoning and the required written result.
Reasoning tokens and visible tokens share the output budget. Raw internal reasoning stays private and is not returned as ordinary readable text. The maker distinguishes visible conversation history from private reasoning continuity: its chat interface does not expose a trace external callers can replay, while its other documented conversation workflow supports managed or encrypted reasoning continuation. Preserve the sources, visible messages and actual tool results needed by a follow-up rather than assuming all interfaces retain private reasoning identically.
Tools and structured deliverables
The application supplies developer-defined function descriptions, the model creates the required call arguments, and the application executes each call and returns the associated result. The model may request several functions in a turn. Return the result for each originating operation before asking for the next conclusion, so the answer uses actual retrieved or computed information.
The maker separately documents built-in search tools that execute within its connected service. Developer functions and those built-in tools have different execution arrangements. The model can reason about what information it needs, but selecting the model alone does not provide repository access, a browser or a private information source.
Structured output can constrain the result to a supplied JSON schema. Define the fields and types needed by the next step and the treatment of missing source information. In the maker's strict schema mode, the root is a plain object, every property is required and extra properties are disallowed; recursive schemas are rejected. These are constraints on the maker's structured interface, not proof that the facts inside a correctly shaped record are true.
For a useful final artifact, request the source-backed findings, the proposed change or document and the unresolved conditions separately. The sources read do not give an independent hard maximum input or output-token capacity beyond the documented context. Keep the Standard 1.3 identity, reasoning choice and connected execution results explicit throughout the task.
POST /v1/chat/completionstexttext| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.3 | 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-1.3", "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',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',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
Use the method paths shown above.
meta/muse-spark-1.3Muse Spark 1.3 is Meta's multimodal reasoning model for long-running agents and coding workflows. It tracks sources and prior results, supports a 1,048,576-token maker context and reasoning levels through max on this Standard edition, returning text and proposed tool actions.
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 is Meta's reasoning model for sustained agentic and coding work. The maker emphasizes keeping context and earlier results across extended tasks, working through conflicting sources and producing a finished deliverable. This entry is the Standard 1.3 edition, whose documented reasoning settings include max; the separately named Contributor edition has its own setting boundaries.
Long-horizon agent work
The release describes a model trained across different agent environments to gather information, revise a plan when evidence changes and preserve detailed requirements through a multi-step task. It also describes improved handling of several workflows in one thread, with incoming requests mapped to the relevant task. A useful request should define the objective, sources, requirements and artifact that will count as completion.
For a professional document task, provide the source reports, identify which facts must survive and ask for a structured brief with source locations. If the sources conflict, request the conflicting statements separately and the information needed to resolve them. For a coding task, include the intended behavior, affected modules and relevant code; ask for the proposed implementation and the evidence that would distinguish the intended result.
The maker says 1.3 asks for clarification when a request is ambiguous and seeks user help when blocked. It also describes better judgment around consequential actions. These are model behavior improvements rather than a replacement for the application's execution controls. Give the agent the information needed to decide and make the required result explicit.
Coding and multimodal evidence
The release focuses on longer coding tasks, cleaner output and fewer unnecessary turns compared with 1.2. A coding-agent workflow can inspect a screenshot, locate the relevant code, propose a correction and use execution or rendered feedback returned by its tools. State the interface that must remain compatible and request the changed artifact separately from its assumptions and explanation.
The official model table lists text, image, video and PDF input with text output and a 1,048,576-token context. Images or clips can supply visible evidence alongside the written task. A chart question should retain axes, legends and units; a screenshot question should identify the behavior to reproduce or inspect. A PDF question can ask for a source-linked extraction or comparison rather than a general summary of every page.
The maker explicitly notes that audio understanding in 1.3 is not fully supported and responses containing audio may degrade. That is distinct from 1.2's documented audio-visual capability. The model's text result also does not itself generate an image, spoken recording or finished file without the surrounding application tools.
Reasoning effort and continuity
The documented levels are minimal, low, medium, high, xhigh and max. Max is specific to Standard 1.3. Muse Spark does not support disabling reasoning with none; omitting the setting leaves a model-determined reasoning level. Choose the effort for the actual problem and leave room for both the internal reasoning and the required written result.
Reasoning tokens and visible tokens share the output budget. Raw internal reasoning stays private and is not returned as ordinary readable text. The maker distinguishes visible conversation history from private reasoning continuity: its chat interface does not expose a trace external callers can replay, while its other documented conversation workflow supports managed or encrypted reasoning continuation. Preserve the sources, visible messages and actual tool results needed by a follow-up rather than assuming all interfaces retain private reasoning identically.
Tools and structured deliverables
The application supplies developer-defined function descriptions, the model creates the required call arguments, and the application executes each call and returns the associated result. The model may request several functions in a turn. Return the result for each originating operation before asking for the next conclusion, so the answer uses actual retrieved or computed information.
The maker separately documents built-in search tools that execute within its connected service. Developer functions and those built-in tools have different execution arrangements. The model can reason about what information it needs, but selecting the model alone does not provide repository access, a browser or a private information source.
Structured output can constrain the result to a supplied JSON schema. Define the fields and types needed by the next step and the treatment of missing source information. In the maker's strict schema mode, the root is a plain object, every property is required and extra properties are disallowed; recursive schemas are rejected. These are constraints on the maker's structured interface, not proof that the facts inside a correctly shaped record are true.
For a useful final artifact, request the source-backed findings, the proposed change or document and the unresolved conditions separately. The sources read do not give an independent hard maximum input or output-token capacity beyond the documented context. Keep the Standard 1.3 identity, reasoning choice and connected execution results explicit throughout the task.
POST /v1/messagestextjson, sse| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-spark-1.3 | 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 $0.0003 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
{\n "model": "meta/muse-spark-1.3",\n "max_tokens": 128,\n "messages": [\n {\n "role": "user",\n "content": "Summarize the incident report."\n }\n ],\n "stream": false\n}set -eu\n: "${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', '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', '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
Use the method paths shown above.
Technical example in English
Resolve conflicting project reports\n\nPrepare a decision brief from these reports. Engineering E: migration scripts passed staging checks. Operations O: production backup restoration has not been rehearsed. Release policy P: rehearsal must pass before migration approval. State what is established, what blocks approval and the next evidence needed. Keep staging success separate from production readiness and cite E, O or P beside each point.A source-linked brief with established facts, the blocking condition and one concrete evidence request.Staging checks alone never satisfy the policy's restoration-rehearsal requirement.