# Muse Ember now available on AI Gateway

Source: [Vercel](https://vercel.com/changelog/muse-ember-now-available-on-ai-gateway)  
Feed7 permalink: https://feed7.dev/p/muse-ember-now-available-on-ai-gateway-18c0njz  
Published: 2026-11-09T00:00:00.000Z  
Trust: Official Source (official_source)

## Why Included

Muse Ember adds a multimodal reasoning option for repeated, bounded agent tasks, with adjustable effort and access through AI Gateway’s APIs or coding-agent setup.

## Source Summary

Meta’s Muse Ember is available on Vercel AI Gateway for repeated agent tasks such as coding subtasks, tool calls, and document analysis. It accepts **text, image, and video** input with a **1M-token context window**, and its reasoning effort ranges from minimal to max.

## Practical Implication

Builders can select `meta/muse-ember` through the AI SDK, several API formats, or a coding agent connected to AI Gateway. That makes it an option to evaluate for bounded steps in a run that also handles code, screenshots, documents, or clips.

## Agent-Ready Context

Meta’s Muse Ember is available on Vercel AI Gateway for repeated agent tasks such as coding subtasks, tool calls, and document analysis. It accepts **text, image, and video** input with a **1M-token context window**, and its reasoning effort ranges from minimal to max.

Builders can select `meta/muse-ember` through the AI SDK, several API formats, or a coding agent connected to AI Gateway. That makes it an option to evaluate for bounded steps in a run that also handles code, screenshots, documents, or clips.

The material gives no comparative quality, latency, or cost results. Gateway says it reflects provider pricing without a platform fee, but that alone does not establish how Ember compares with other models for a workload.

## Connected Context

Feed7 judgment across 1045 accumulated Signals:

Muse Ember adds video input and adjustable reasoning effort to the gateway's options for bounded agent steps, including document analysis and tool calls. Its 1M-token context and broad input support make it an option to evaluate, but the listing supplies no evidence that it is faster, cheaper, or more capable than alternatives.

- [GLM 5.3 now available on AI Gateway](https://feed7.dev/p/glm-5-3-now-available-on-ai-gateway-0s7o9zv) — Both offer 1M-token coding-agent routes, while Ember's stated fit is repeated bounded tasks and includes video input; GLM 5.3 is framed around long-horizon engineering.
- [Inkling Small from Thinking Machines is now available on AI Gateway](https://feed7.dev/p/inkling-small-now-available-on-ai-gateway-1a9781l) — Both add adjustable reasoning effort for multimodal agent work, but Inkling is positioned as lower-compute while Ember's brief emphasizes bounded tasks and video input; neither listing establishes comparative results.

## Context Map

- Layer: model
- Domains: coding, image
- Topics: reasoning, model-selection, coding-agents

## Uncertainty

- The material gives no comparative quality, latency, or cost results. Gateway says it reflects provider pricing without a platform fee, but that alone does not establish how Ember compares with other models for a workload.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
