Meta's Muse Ember lightweight reasoning model arrives on Vercel AI Gateway

Vercel has added Meta's Muse Ember to AI Gateway, positioning it as a lighter reasoning model for the repetitive steps inside an agent run — writing a helper function, making a tool call, or summarizing a document. In its changelog, Vercel says the model accepts text, images and video with a 1M-token context window, supports tool calling, and lets callers adjust reasoning effort from minimal to max.

It is available now to developers through the AI SDK and the Chat Completions, Responses and Anthropic Messages APIs under the model name meta/muse-ember. It can also be picked in coding agents including Claude Code, Codex and Cursor after installing the latest Vercel CLI. Gateway inference is billed at provider rates with no platform fee, including bring-your-own-key requests.