Meta: Muse Wonder
Muse Wonder is Meta’s multimodal reasoning model for long-running agents and complex engineering tasks. It reads text, images, video, audio and PDF documents within a 1,048,576-token context and returns text, with published tool-calling, structured-output and configurable reasoning-effort features.
- Ailoot Ultra · OpenAI Chat
POST /v1/chat/completionsmeta/muse-wonder - Ailoot Ultra · Anthropic Messages
POST /v1/messagesmeta/muse-wonder
About the model
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Muse Wonder is Meta’s reasoning model for tasks that need a sustained plan across a substantial evidence set. Its published inputs include text, images, video, audio and PDF documents, and its output is text. A single task can therefore combine a repository, a document collection and visual evidence while retaining a defined written deliverable.
Plan work around the required artifact
Describe what the work must produce and how the result will be checked. For a software task, identify the behaviour to preserve, the relevant files and the verification criteria. For document analysis, name the question, the sources and the information that the final report should retain.
The published agentic design includes planning, delegated subtasks, parallel tool use and recovery from errors. In an application, connect those model capabilities to a controlled execution workflow: tools perform the actions, returned observations provide evidence, and the next model step uses those observations. Retain completed findings so later steps do not lose the decisions already made.
Work across files and media
Muse Wonder’s documented engineering use spans multiple files in an existing repository. Give it a coherent set of relevant code and constraints rather than a disconnected excerpt when the change crosses component boundaries. Ask for the affected interfaces and verification steps along with the proposed edits.
For visual or audiovisual work, supply the material that carries the evidence. A screenshot can clarify a layout defect; a video can show an interaction sequence; a document can combine text, tables and figures. State what the model should extract or explain from that evidence and request a text result with the useful observations retained.
Reasoning and structured output
Muse Wonder’s published configuration includes mandatory reasoning with minimal, low, medium, high, xhigh and max effort levels, with medium as its default. Choose a setting around the depth of the task and specify what the answer should establish. Retain the same criteria when comparing results at different effort levels.
Tool calling and schema-guided structured output are published model features. A workflow can use them to request identified findings, evidence references, a change plan or a list of verification outcomes. Keep machine-consumed fields focused on the next step and retain the human-readable explanation where a reviewer needs to understand a decision.
Long-context continuity
The published context window is 1,048,576 tokens. Organise long inputs with clear source names and section boundaries, and distinguish confirmed observations from open assumptions. Use the context to preserve important decisions across a task rather than filling it with unrelated material.
A useful final artifact identifies what changed, the evidence used, the checks performed and the questions still needing attention. That can be a repository review, a multi-file change proposal or an analysis of a mixed document set. Muse Wonder’s text output describes and directs the work; the surrounding application supplies the execution, tools and storage that turn it into a completed workflow.
Capabilities
- Text, image, video, audio and PDF understanding with text output.
- Published 1,048,576-token context.
- Planning, delegated subtasks, parallel tool use and error recovery in agentic work.
- Multi-file software-engineering workflows.
- Mandatory reasoning with published effort levels and schema-guided output.
Use cases
- Multi-file engineering task — Relevant code, a desired outcome and verification criteria. Result: A coherent change plan or review across affected components.
- Long-running controlled agent — A goal, an execution harness and retained tool observations. Result: Successive decisions connected to a reviewable final artifact.
- Multimodal investigation — Documents and media carrying the evidence for a specific question. Result: A text analysis with source-linked observations.
- Large evidence-set synthesis — An organised collection with named sources and an output contract. Result: A report that retains conclusions, evidence and open assumptions.
Limits
- Context — Published context window: 1,048,576 tokens.
- Output — The published output family is text.
- Reasoning — Reasoning is mandatory; the source lists minimal, low, medium, high, xhigh and max efforts.
- Execution — Tools and the surrounding application execute actions and retain their outcomes.
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions meta/muse-wonder
meta/muse-wonderOverview
Muse Wonder is Meta’s multimodal reasoning model for long-running agents and complex engineering tasks. It reads text, images, video, audio and PDF documents within a 1,048,576-token context and returns text, with published tool-calling, structured-output and configurable reasoning-effort features.
- Accepted inputs
- Text
- Results
- Text
Available in Ailoot · inputs & methods
Ailoot Ultra · OpenAI Chat POST /v1/chat/completions
- Input types
text- Output types
text- Output format
- json or SSE
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-wonder | Default— |
Fieldmessages | Typemessage[] | RequirementRequired | Values & limits Minimum items: 1 | Default— |
Fieldmessages[].role | Typestring | RequirementRequired | Values & limits Model-specific | Default— |
Fieldmessages[].content | Typestring | RequirementOptional | Values & limits Applies when: Text conversation | Default— |
Fieldstream | Typeboolean | RequirementOptional | Values & limits | Defaultfalse |
Input material combinations
Text · UTF8 text
messages[].content
Method parameters and lifecycle
| 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 |
Parametercontrol_scope | ContractText conversation; stream is a boolean and defaults to false. |
Parameteroutput_modalities | Contracttext |
Parameterhosted_operations | Contractfalse |
Parametermultimodal_input_binding | Contractnull |
Method aliases: /chat/completions
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.
Pricing
Tariff references do not add request options. Supported parameters are listed for the selected method.
- Fast mode
- Not specified When fast mode is selected
- Flex mode
- Not specified When flex mode is selected
- Maximum reasoning effort
- Not specified When maximum reasoning effort uses the default adjustment
Ailoot rates
Prices by configuration
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 $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 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 $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · OpenAI Chat
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
import json,os
from pathlib import Path
p=json.loads('{"model":"meta/muse-wonder","messages":[{"role":"user","content":"hello"}],"stream":false}')
Path("request.json").write_text(json.dumps(p,ensure_ascii=False))
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/chat/completions \
-H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path("result.json").read_text())
for x in r.get("choices",[]):
if x.get("message",{}).get("content"): print(x["message"]["content"])
PY_RESULT
from openai import OpenAI
import os
if not os.environ.get("AILOOT_API_KEY", "").strip(): raise SystemExit("Set AILOOT_API_KEY before making a request")
client=OpenAI(base_url="https://api.ailoot.ai/v1",api_key=os.environ["AILOOT_API_KEY"],max_retries=0)
result=client.chat.completions.create(model="meta/muse-wonder", messages=[{"role":"user","content":"hello"}], stream=False)
import base64, json
from pathlib import Path
def save_result(data, stem="result"):
# Keep every field, including usage, IDs, reasoning and tool requests.
Path(stem + ".json").write_text(json.dumps(data, ensure_ascii=False, indent=2), encoding="utf-8")
print(json.dumps(data, ensure_ascii=False, indent=2))
def save_blob(encoded, suffix, label):
raw = base64.b64decode(encoded, altchars=b"-_", validate=True)
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
file = Path(stem + "-" + label + "." + ext)
file.write_bytes(raw)
print("Saved", file)
for index, block in enumerate(data.get("content") or []):
print("Content", index, json.dumps(block, ensure_ascii=False))
for choice in data.get("choices") or []:
print("Choice", choice.get("index"), json.dumps(choice.get("message", choice.get("delta", {})), ensure_ascii=False))
for index, item in enumerate(data.get("output") or []):
print("Output", index, json.dumps(item, ensure_ascii=False))
if item.get("type") == "image_generation_call" and item.get("result"):
save_blob(item["result"], item.get("output_format") or "bin", "output-" + str(index))
for ci, candidate in enumerate(data.get("candidates") or []):
for pi, part in enumerate((candidate.get("content") or {}).get("parts") or []):
print("Candidate/part", ci, pi, json.dumps(part, ensure_ascii=False))
blob = part.get("inlineData") or part.get("inline_data")
if blob and blob.get("data"):
mime = blob.get("mimeType") or blob.get("mime_type")
suffix = {"image/png":"png", "image/jpeg":"jpg", "image/webp":"webp", "audio/wav":"wav", "audio/mpeg":"mp3", "video/mp4":"mp4"}.get(mime, "bin")
save_blob(blob["data"], suffix, "candidate-" + str(ci) + "-part-" + str(pi))
save_result(result.to_dict(mode="json"))
Receive and save results
Ailoot Ultra · OpenAI Chat
json or SSE
Keep all completed results
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.
If the original response needs checking
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
Response fields
| 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 |
Errors and next steps
| 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. |
Aliases
Model aliases
Ailoot Ultra meta/muse-wonder
Method path aliases
/chat/completions
Related caller IDs
Ailoot Ultra · Anthropic Messages POST /v1/messages meta/muse-wonder
meta/muse-wonderOverview
Muse Wonder is Meta’s multimodal reasoning model for long-running agents and complex engineering tasks. It reads text, images, video, audio and PDF documents within a 1,048,576-token context and returns text, with published tool-calling, structured-output and configurable reasoning-effort features.
- Accepted inputs
- Text
- Results
- json · sse
Available in Ailoot · inputs & methods
Ailoot Ultra · Anthropic Messages POST /v1/messages
- Input types
text- Output types
json,sse- Output format
- JSON or SSE
| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits meta/muse-wonder | 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 |
Input material combinations
Text · UTF-8 text
messages[].content string
Method parameters and lifecycle
| 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
Pricing
Tariff references do not add request options. Supported parameters are listed for the selected method.
- Fast mode
- Not specified When fast mode is selected
- Flex mode
- Not specified When flex mode is selected
- Maximum reasoning effort
- Not specified When maximum reasoning effort uses the default adjustment
Ailoot rates
Prices by configuration
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 $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 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 $0.008 / 1K tokens Output · Output tokens $0.04 / 1K tokens Input · Cache read $0.0004 / 1K tokens Input · Cache write — / 1K tokens Input · Cache write, 1 hour — / 1K tokens |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
Example requests
Ailoot Ultra · Anthropic Messages
{
"model": "meta/muse-wonder",
"max_tokens": 128,
"messages": [
{
"role": "user",
"content": "Summarize the incident report."
}
],
"stream": false
}set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
: "${AILOOT_TEXT_FILE:?Set your actual UTF-8 document}"
export AILOOT_TEXT_FILE
python3 - <<'PY_REQUEST'
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'meta/muse-wonder', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
Path('request.json').write_text(json.dumps(payload, ensure_ascii=False), encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/messages \
-H "x-api-key: $AILOOT_API_KEY" -H 'anthropic-version: 2023-06-01' -H 'Content-Type: application/json' \
--data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
PY_RESULT
import json, os
from pathlib import Path
source_file = Path(os.environ['AILOOT_TEXT_FILE'])
if not source_file.is_file():
raise SystemExit('Set AILOOT_TEXT_FILE to your actual UTF-8 document')
text = source_file.read_text(encoding='utf-8')
if not text.strip():
raise SystemExit('Choose a document containing text')
payload = {'model': 'meta/muse-wonder', 'max_tokens': 128, 'messages': [{'role': 'user', 'content': 'Summarize the incident report.'}]}
payload['messages'][0]['content'] = 'Summarize this material and quote supporting source passages.\n\n' + text
from urllib.request import Request, urlopen
from urllib.error import HTTPError
api_key = os.environ['AILOOT_API_KEY']
if not api_key.strip():
raise SystemExit('Set AILOOT_API_KEY before making a request')
headers = {'x-api-key': 'PLACEHOLDER_KEY', 'anthropic-version': '2023-06-01', 'Content-Type': 'application/json'}
headers['x-api-key'] = api_key
request = Request('https://api.ailoot.ai/v1/messages', data=json.dumps(payload, ensure_ascii=False).encode('utf-8'), headers=headers, method='POST')
try:
with urlopen(request, timeout=120) as response:
raw = response.read()
Path('response-headers.txt').write_text(str(response.headers), encoding='utf-8')
except HTTPError as error:
Path('result.json').write_bytes(error.read())
Path('response-headers.txt').write_text(str(error.headers), encoding='utf-8')
raise
Path('result.json').write_bytes(raw)
import json
from pathlib import Path
result = json.loads(Path('result.json').read_text(encoding='utf-8'))
print(json.dumps(result, ensure_ascii=False, indent=2))
Receive and save results
Ailoot Ultra · Anthropic Messages
JSON or SSE
Keep all completed results
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.
If the original response needs checking
Keep request/response IDs and headers. No generic text job retrieval URL is supplied.
Response fields
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldmodel | Typestring |
Fieldcontent[] | Typetext|thinking|tool_use|other content block |
Fieldstop_reason | Typestring|null |
Fieldusage | Typeobject |
Errors and next steps
| 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. |
Aliases
Model aliases
Ailoot Ultra meta/muse-wonder
Method path aliases
/chat/completions
Related caller IDs
FAQ · Meta: Muse Wonder
- What inputs and results are available?
POST /v1/chat/completions·meta/muse-wonder:text→textPOST /v1/messages·meta/muse-wonder:text→json,sse- Which fields does the request use?
POST /v1/chat/completions·meta/muse-wonder:model,messages,streamPOST /v1/messages·meta/muse-wonder:model,messages,max_tokens,stream- What limits apply?
POST /v1/chat/completions·meta/muse-wonder:messages.min_items:1