Muse Spark 1.1

Muse Spark 1.1 is a natively multimodal reasoning model from Meta. It supports tool-use, visual chain of thought, and multi-agent orchestration. It is the first version of the muse line in the registry. It has a context window of 1,048,576 tokens and a maximum output of 131,072 tokens. Pricing starts at $1.25 per million input tokens and $4.25 per million output tokens, with cached input from $0.15 per million tokens. The weights are not open. It accepts image, PDF, text, and video inputs, and returns text. It supports reasoning mode and tool calling.

First version of its line in the registry.

Range across the hosts that serve it: up to $1.38 per 1M input tokens.

• ·Natively multimodal: accepts image, PDF, text, video
• ·Supports tool-use and multi-agent orchestration
• ·Visual chain of thought for reasoning
• ·1M token context window
• ·131K token max output

• Reach for it for multimodal reasoning across images, PDFs, text, video
• Reach for it for tool-use and multi-agent orchestration
• Reach for it for long-context analysis with 1M token window

12 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window?

The context window is 1,048,576 tokens.

What is the pricing?

Pricing starts at $1.25 per million input tokens and $4.25 per million output tokens. Cached input costs from $0.15 per million tokens.

Are the weights open?

No, the weights are not open.