Meta’s Muse Wonder handles coding, computer use and sustained agent tasks through Meta Model API and Muse Code, with a 1M-token context.
Pricing conditions: Standard API rates are $4/M input, $0.20/M cached input and $20/M output. There is no long-context premium. Web search adds $2.50 per 1,000 queries. Muse Wonder has no Contributor mode on pay-as-you-go; Muse Wonder Full requires a Muse Code subscription and has no API token price.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Muse Wonder joins Meta’s catalog on 12 October 2026. It is aimed at coding and agent workflows that must keep going after an initial answer: inspect a workspace, use tools, revise an approach and deliver a finished result. Active Memory and Active Focus are the names attached to its context retrieval and sustained execution capabilities. Their usefulness depends on the surrounding agent and the information it can access.
Use muse-wonder-1.0 for the hosted API route. The service accepts text, images, video, audio and PDFs and returns text within a 1,048,576-token context window. The registry records a 131,072-token output allowance; request and account limits still need checking. Reasoning effort ranges from minimal through max. Selecting max does not switch the request to Muse Wonder Full.
The Standard route charges $4 per million input tokens and $20 per million output tokens, with cached input at $0.20. Search grounding adds a separate query charge. Long inputs do not carry a different token rate on this route. Compare finished runs with the same tools and account settings, especially when several attempts are needed to complete a repository change.
Give the agent a repository change with clear acceptance checks and a deliberate blocker, such as missing documentation or a failing existing check. Inspect whether the final patch meets the original constraints, whether tool failures were resolved, and whether unfinished work is reported accurately. Compare sustained task completion separately from the quality of a single generated answer.
Record the exact model identifier, deployment route and request settings with each result. Count complete runs, including rejected outputs, retries and tool calls. When the workflow creates files or code, open the files or execute the existing checks before accepting the result. A plausible first response can hide an incomplete final deliverable.
The specifications describe supported interfaces and request capacity. They do not establish a measured quality ranking or a latency guarantee for your account. SyncDev has not independently benchmarked this model. Choose a deployment after testing the languages, input formats and operating conditions that matter to your users.
Explore meta models, browse model tasks, or compare two models with the same acceptance criteria.
Compare the model on the work you need to complete.
Muse Wonder is listed for Audio-text-to-text, Image-text-to-text, Text generation, Video-text-to-text, Coding & Code Generation, Computer Use. It accepts text, image, video, audio, pdf and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 1.05M context and 131.07K maximum output. The listed route has starting rates of $4.00 input and $20.00 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Gemini 4 Argon handles coding, reasoning and multimodal work with a shared 1M-token window and background long decode.
Meta
Muse Wonder Full is Meta’s higher-capability Wonder variant for sustained coding and agent work, available through eligible Muse Code subscriptions.
Xiaomi
MiMo-V2.6-Distill-Qwen-9B is Xiaomi’s smaller downloadable checkpoint for agent research and reinforcement-learning experiments.
Sakana AI
Fugu Max from Sakana AI: Multi-agent model for routing expert agents across complex analytical tasks.
Sakana AI
Fugu Ultra v2 from Sakana AI: Quality-first multi-agent model for hard research, analysis, and competitions.
inclusionAI
Ling 3.0 Flash VL adds image and video understanding to the Ling reasoning architecture for visual analysis and agents.