Meta
Muse Spark 1.3
meta/muse-spark-1.3
Keeps track of long tasks. Reads text, images, audio, video and PDF.
MultimodalText, Images, Video, Files, Audio → TextReady on endue
- Agentic work
- Audio & video
- Long documents
Overview
Good for
Written by endue
- Agentic work
- Audio & video
- Long documents
Not ideal for
From the model’s specs
Nothing in the specs rules out common agent work.
Capabilities
| Tool use | Supported |
|---|---|
| Structured output | Supported |
| JSON mode | Supported |
| Reasoning | Supported |
| Vision | Supported |
| Audio input | Supported |
| Video input | Supported |
| File input | Supported |
| Long context | Supported |
Specifications
- Model ID
meta/muse-spark-1.3- Family
- Muse Spark
- Context window
- 1M tokens
- Input
- Text, Images, Video, Files, Audio
- Output
- Text
- Released
- 2026-09-02