All models
Meta
Muse Spark 1.3
Meta's model for text, images, video and sound
This model is not in the catalog right now.
See available modelsAbout the model
Muse Spark 1.3 is a Meta model that accepts text, images, video and audio. It includes step-by-step reasoning for complex tasks and holds a context of up to a million tokens, so it is suited to long materials and mixed collections, for example a document with illustrations plus a meeting recording. It supports tool calling and works for agent scenarios and integrations. It follows instructions and keeps the output format. Russian at a medium level.
Strengths
- Text, images, video and audio
- Reasoning for complex tasks
- Context up to 1M tokens
- Tool calling (function-calling)
- Stable answer format
Where to use it
- Tasks with mixed data: text, images, sound
- Analyzing meetings and recordings
- Analyzing images and documents
- Agents with tools
- Analytics on long materials