Source: vercel.com/changelog/muse-ember-now-available-on-ai-gateway
Muse Ember is aimed at the high-volume parts of an agent run, such as coding sub-tasks, tool calls and document analysis. Vercel says it handles bounded tasks that agents repeat many times in one run, like writing a helper function or summarizing a document. The model accepts text, image and video input with a 1M-token context window, and its reasoning effort can be set from minimal to max.
Developers can reach the model through the AI SDK, the Chat Completions, Responses and Anthropic Messages APIs, or a coding agent connected to AI Gateway. Tool calling lets an application feed each result into the next step. For Claude Code, Codex, Cursor and other agents, Vercel says to install the latest Vercel CLI, run the AI Gateway setup command, and then select meta/muse-ember in the agent.
AI Gateway offers a unified API for calling models and tracking usage and cost, with retries, failover, routing rules, budgets for API keys and Zero Data Retention support. Vercel says it reflects provider pricing with no markup and charges no platform fee on inference, including Bring Your Own Key requests.
Why it matters if you build agents
Agent builders can route the repetitive sub-tasks of a long run to a lightweight model with a 1M-token window and keep heavier calls on other models. Teams already using AI Gateway can call it through the AI SDK or the listed API formats without setting up a new provider.
Check the pricing, data-retention and budget settings against your own workload before sending production traffic to the model.
Get stories like this every weekday
One short email with the day's agent tooling news.