Muse Ember now available on Vercel AI Gateway
Vercel announced that Muse Ember, a lightweight reasoning model from Meta, is now available on AI Gateway under the model name meta/muse-ember. The model accepts text, image, and video input with a 1M-token context window, supports tool calling, and has adjustable reasoning effort from minimal to max.
Why it matters
Builders running agents with many repeated bounded sub-tasks (coding helpers, tool calls, document summaries) now have a high-volume model option callable through AI Gateway's Chat Completions, Responses, Anthropic Messages, and AI SDK interfaces, with usage tracking and failover. AI Gateway states it passes through provider pricing with no markup and no platform fee on inference.
Who should care
Developers building AI agents, coding agent users, teams running high-volume LLM workloads, and ecommerce or online business builders using agents for document analysis or automation.
What you can do
Call meta/muse-ember through AI Gateway with a tool-calling workflow, or test it in the Vercel model playground before routing a high-volume agent sub-task to it.