Muse Ember now available on AI Gateway

Muse Ember, a lightweight reasoning model from Meta, is now available on Vercel’s AI Gateway, designed to manage high-volume, repetitive tasks within agent workflows such as coding sub-tasks, tool calls, and document analysis. The model supports text, image, and video inputs with a context window of up to 1 million tokens, allowing agents to process code, screenshots, documents, and video clips in a single run. Tool calling functionality enables applications to feed results from Muse Ember into subsequent steps of the workflow, while reasoning effort can be adjusted from minimal to maximum based on task requirements.

Muse Ember can be accessed through multiple interfaces including the AI SDK, Chat Completions, Responses, and Anthropic Messages APIs, as well as coding agents connected to AI Gateway. Integration with coding agents such as Claude Code, Codex, and Cursor is supported by installing the latest Vercel CLI and running the setup command, followed by selecting the meta/muse-ember model in the agent. Vercel provides a coding agents guide to assist with the integration process.

AI Gateway serves as a unified API for model calls, offering features such as usage and cost tracking, configurable retries, failover mechanisms, and performance optimizations to enhance uptime beyond provider guarantees. The platform includes built-in custom reporting, Zero Data Retention support, budget controls for API keys, and routing rules to manage traffic and performance. These capabilities are available without additional platform fees on inference, including for Bring Your Own Key requests.

AI Gateway mirrors provider pricing without markup and does not impose platform fees on inference costs. Users can view the full list of language models available on the platform, which now includes Meta’s Muse Ember. The service aims to simplify model integration while providing operational tools for managing AI workflows efficiently.