Vercel Adds Meta’s Muse Ember to AI Gateway for Agent Tasks
Vercel has made Meta’s Muse Ember available through AI Gateway, positioning the lightweight reasoning model for repeated, bounded tasks inside agent runs. The model supports text, image and video input, plus a 1M-token context window.
- Meta’s Muse Ember is now available on Vercel AI Gateway.
- The model targets repeated coding, tool calling and document tasks in agent runs.
- It accepts text, image and video input with a 1M-token context window.
- Reasoning effort can be adjusted from minimal to max.
- The model name is meta/muse-ember.
A model for repeated agent work
Muse Ember is designed for the high-volume parts of an agent run, according to Vercel. These include coding sub-tasks, tool calls and document analysis. Rather than handling an entire agent workflow, the model can take on smaller jobs that an agent repeats many times in a single run.
Vercel gives implementing a helper function, calling a tool and summarizing a document as examples. This focus could allow applications to route routine steps to a model intended for bounded tasks, while keeping those steps within the same agent workflow.
Multimodal input and adjustable reasoning
Muse Ember accepts text, image and video input and has a 1M-token context window. An agent can therefore pass code, screenshots, documents and video clips to the model in the same run, based on Vercel’s description.
Tool calling allows an application to feed each result into the next step. Developers can also adjust reasoning effort from minimal to max, giving them a setting for how much reasoning the model applies to a task.
Vercel says the model can be called through the AI SDK, the Chat Completions, Responses and Anthropic Messages APIs, or through a coding agent connected to AI Gateway. The model name is meta/muse-ember.
How developers can access Muse Ember
Developers can use Muse Ember in applications through the AI Gateway, or connect it to coding agents such as Claude Code, Codex and Cursor. To use it in those agents, Vercel instructs users to install the latest Vercel CLI and run npx vercel ai-gateway setup, then select meta/muse-ember in the agent.
Vercel also makes Muse Ember available in its model playground and provides a coding agents guide with further details. AI Gateway offers a unified API for calling models, tracking usage and cost, and configuring retries, failover and performance optimizations for higher-than-provider uptime.
The service includes custom reporting, Zero Data Retention support, budgets for API keys and routing rules. Vercel says AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including Bring Your Own Key requests. For users building agents, the addition gives them another model option for multimodal, repeated tasks while keeping access, routing and usage controls in one gateway.
Vercel: Muse Ember now available on AI Gateway
