ImprovementModels ·
Muse Spark 1.3
What it does
Muse Spark 1.3 is available for agents that combine text, images, reasoning, and Actions.
Before this
New. Muse Spark 1.3 was not previously in the public model selector.
Why it matters
Try another model for workflows that need image understanding and tool use in the same conversation.
The specs
The model supports a 1,048,576-token context window, a 943,718-token output ceiling, text and image input, and Actions; your agent’s configured limits still apply.
The picker offers six reasoning levels, from On ($) through Maximum ($$$$$$), with reasoning always enabled.