Meta: Muse Spark 1.1
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context window....
Specification
- Model ID
- meta/muse-spark-1.1
- Weight license
- Not verified; consult the exact publisher model card
- Modality
- Text+image+file+video >text
- Context
- 1.0M tokens
- Input
- $1.25/1M
- Output
- $4.25/1M
- Web search
- $2500.00/1M
- Updated
- Nov 14, 2026
Scores
Capabilities
- Supports tool calling
- Supports vision inputs
- Supports long-context workflows
- Supports deeper reasoning tasks
Input and output
Accepts Text, Image, Video, File inputs. Returns Text outputs.
Supported parameters
include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p
Related models
Build with Meta: Muse Spark 1.1
Describe what you want to make and pick this model in the composer. A database and hosting are included.