Meta Muse Wonder brings long-running agents to API, Muse and Vercel

What changed · following since Oct 13 Oct 14 — llm-meta-ai 0.2 adds Muse Wonder support to Simon Willison’s plugin for the Meta AI API.

Meta’s Muse Wonder release turns long-running agent capabilities into a product and distribution strategy spanning a direct model API, paid Muse subscriptions and third-party infrastructure. On October 12, Meta launched Muse Wonder and Muse Wonder Full with Active Memory and Active Focus; Vercel then made Muse Wonder callable through AI Gateway with tool use, multimodal inputs and a 1M-token context window. The growing integration surface makes it easier to evaluate the model through existing developer workflows before taking on Meta’s direct stack.

• Meta introduced Muse Wonder and Muse Wonder Full on October 12, describing them as models for personal and professional agents; Wonder is available through the Meta Model API, while Wonder Full is available to Muse Code subscribers.
• Meta says Active Memory and Active Focus help Muse Wonder retain what matters and work toward goals over extended periods; the models are also planned to power the Muse agent and artifact-generation workflows.
• Muse Wonder costs $4 per million input tokens and $20 per million output tokens through the Meta Model API. Muse app access is offered through monthly subscriptions priced at $20 or $100, while Wonder Full is not served through the API.
• Artificial Analysis reported Intelligence Index v4.3 scores of 52 for Muse Wonder and 56 for Muse Wonder Full at maximum reasoning effort, compared with 48 for Muse Spark 1.3 released six weeks earlier.
• Vercel’s AI Gateway exposes meta/muse-wonder-1.0 through one API key with usage and cost tracking, request traces, routing, retries and failover; the integration supports tool calling, structured output, text, images and PDFs within a 1M-token context window.

Bottom line If you are building long-running coding or computer-use agents, test Wonder through your existing gateway or API tooling and measure memory quality, tool recovery, latency and cost before committing to Meta’s direct stack.