Meta

Muse Spark 1.3

by Metatext+image+file+audio+video->text1 endpoint
Neura Intelligence Index
96.0/ 100
Rank
#5
Confidence
low
Benchmarks
1(3% coverage)

Overview

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended tasks, work through conflicting inputs, and request clarification or confirmation when needed, with an emphasis on concise execution.

Capabilities

Text generation
Image understanding
Audio processing
Video understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
File input
Top-P sampling

Modalities

Input
TextImageVideoFileAudio
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
943.7K tokens
Tokenizer
Other
Content Moderation
Enabled
Uptime (24h)
9999.5%
Country
🇺🇸US
Release Date
September 2, 20262w

Supported Parameters

include_reasoningmax_tokensreasoningreasoning_effortrepetition_penaltyresponse_formatstructured_outputstemperaturetool_choicetoolstop_ktop_p

Benchmark Performance

general

BenchmarkScoreSource
MRCR v2
98.5
verified

Performance Over Time

Pricing

Per 1M tokens
Input$1.25
Output$4.25
Cache read$0.15
Added
September 2, 2026
Last synced 9/21/2026