Meta releases Muse Ember, a low-cost AI model for agents’ repeat tasks

Meta released Muse Ember on November 9, 2026, giving developers a smaller model for the repeated steps inside AI agents: calling tools, reading documents and handling coding subtasks. Available through Muse Code and the Meta Model API, it starts at $0.10 per million input tokens and $0.50 per million output tokens.

A smaller model for the steps between decisions

Meta’s starting point is the volume of small, structured jobs an agent performs. The company describes Ember as its smallest and most efficient model, designed for routing requests, extracting information and parsing long documents. For coding, its intended assignments include reading files, running tests and making targeted fixes.

The proposed division of labor leaves harder planning to Muse Wonder. Meta recommends pairing the two: Wonder plans, while Ember handles the volume. That positions the new release as a model for delegated work, rather than a replacement for every part of a demanding assignment.

Ember also natively understands text, images, audio and video, Meta says. Its examples include screenshots, charts, scanned documents, voice memos and meeting recordings. Those inputs can be handled without a separate model, making the release relevant to document-heavy workflows as well as software development.

Developer access at launch

• Model identifier: muse-ember-1.0, available in Muse Code and the Meta Model API.
• Context window: one million tokens, the units of content a model processes, with up to 512,000 output tokens.
• Interface: support for the Responses API.

$0.10Input

Meta’s listed rate for input tokens.

$0.004Cached input

Meta lists a separate, lower rate for cached input tokens.

$0.50Output

Meta’s listed rate for generated output tokens.

Workflow gains, but no coding sweep

Meta’s launch table shows a substantial lead on AutomationBench-AA, a test of end-to-end business workflows. At maximum reasoning, Ember scored 37.8%, against 20.2% for GPT-6 Luna and 13.9% for Claude Haiku 5.5. Meta attributes these results to Artificial Analysis and specifies a strict, single-attempt scoring method.

The coding picture is less uniform. On Terminal-Bench 4.0, Ember scored 40.9%, compared with Haiku’s 39.2% and Luna’s 16.4%. Each model used its best published agent setup. But on FrontierCode 2.0-AA, which judges real engineering tasks on whether changes can be merged, Haiku led at 34.9%; Ember scored 27.2% and Luna 25.2%.

Meta also makes a cost-efficiency case using Artificial Analysis results. Its chart puts one Ember setting at a 35.8 intelligence score and $0.136 per task, versus Haiku’s highest displayed score of 36.2 at $0.411. Ember’s task costs are estimates using its listed pricing, not a guarantee of what a developer’s workload will cost.

Early trials and the safety boundary

Early partners offer examples of the intended work. In a testimonial published by Meta, Box AI products chief Yashodha Bhavnani described scoring contracts against negotiation rules and screening candidates against detailed briefs. Cline founder Saoud Rizwan highlighted using Ember as a subagent—a model assigned part of a larger job—for coding and document analysis.

Before release, Meta says it evaluated chemical and biological risks, cybersecurity risks and loss-of-control risks under its Meta Superintelligence Scaling Framework. Ember remained below the framework’s high-risk thresholds in the categories assessed. That is Meta’s safety assessment, not a claim that agent use carries no risk.

Meta also tested behavior closer to everyday deployment: respecting user intent, handling sensitive information, resisting instructions hidden in documents or tool outputs, and seeking human input before high-impact actions. These are the boundaries the company evaluated for a model meant to act on users’ behalf; the launch describes those checks without publishing numerical results for them.