Skip to content

Muse Spark 1.3

Muse Spark 1.3 is trained for agentic workflows and optimized for competitive coding performance. Developers can expect higher first-attempt accuracy and reliable tool calling.

Meet Muse Spark 1.3

Trained for long-horizon, agentic workflows

Muse Spark 1.3 tracks context and prior results, works through messy or conflicting inputs, and asks for input when needed.

Competitive coding performance

Tuned for long-horizon coding workflows, with fewer unnecessary turns and cleaner output. Whether you’re building coding agents or using AI as a development partner, it performs competitively with frontier models across several coding evals.

Native multimodal perception

Muse Spark perceives video, images and documents, and its visual reasoning runs through a real execution environment instead of scripted steps. Feed it a screenshot or a clip and let it build.

Muse Spark

Introducing Muse Spark 1.3

Introducing Muse Spark 1.3, with max reasoning for challenging reasoning and agentic tasks and improved real-world usability.

Muse Spark 1.3 benchmarks

Category

Benchmark

Muse Spark 1.3 (max)

Meta

Muse Spark 1.2 (xhigh)

Meta

GPT 5.6 Sol (max)

OpenAI

Opus 5 (max)

Anthropic

Agent

Long Context

Coding

GDPVal-AA v2Knowledge work

JobBenchProfessional tool use

OSWorld 2.0Agentic computer use

DeepSearchQAAgentic browsing

Agentic IF Index (Internal)Instruction following

AutomationBenchE2E business workflows

MRCR 256K–512KLong context

MRCR 512K–1MLong context

DeepSWE v1.1Long-horizon agentic coding

SWEAtlas CodeBase QnACodebase understanding

Terminal-Bench 2.1Agentic terminal coding

1754

64.9

66.9(partial)32.0(binary)

90.3

57.8

49.6

98.5

98.1

75.4

59.4

88.8

1615

61.6

47.6(partial)17.9(binary)

85.9

46.2

38.2

66.3

55.5

55.0

46.2

82.9

1710

45.4

62.7(partial)27.3(binary)

93.1

60.5

46.7

91.5

73.8

73.0

53.5

88.8

1824

65.7

68.3(partial)31.4(binary)

90.4

59.1

50.3

-

-

74.0

52.7

86.7

GET STARTED

More ways to build

Muse Code Multi-agent coding in your terminal. Enabled by Muse Wonder and Muse Wonder Full.

Meta Model APIDirect, self-serve and affordable access to Muse Wonder.

OpenRouterSwap Muse Wonder into your existing tools and workflows.

Google CloudBuild for enterprise scale through Google Cloud.

Models and pricing

Model

Context window

Input (Mtok)

Cached input (Mtok)

Output (Mtok)

muse-spark-1.3-contributorUsed to improve our products.

1M

$0.10

$0.002

$0.20

muse-spark-1.3Not used to improve our products.

1M

$1.25

$0.15

$4.25

Cookbooks and quickstarts

Read documentation

Quick startYour first working request in under five minutes. Point your existing OpenAI SDK compatible client at Meta Model API.

Multi-agent orchestrationStand up a four profile agentic team that turns a one line product idea into a working SaaS app.

Agent fan-outSpin multiple subagents into isolated worktrees to tackle parallel work without mid-flight collisions.

Computer useGive Muse Spark eyes and a pair of hands and it can build software the way you do.

GitHub agentBuild an autonomous GitHub bot on Meta Model API with Muse Spark and OpenCode.

Search groundingGive your model live access to the web. Add a single tool to your request to get real time information.

Deploy Muse Spark

Model documentation