curatedai.net
Directory Categories Radar Models Leaderboard Guides Prompts Skills Briefing Newsletter
Light Dark
← Back
← All Muse models
LLMS • CURATED • UPDATED SEP 29, 2026

Muse Spark 1.3

Meta's agentic coding model, tuned to finish long jobs in fewer steps

Muse Spark 1.3 is Meta Superintelligence Labs' September 2, 2026 update to its closed-weights Muse Spark model, released through the Muse Code harness (macOS and Linux) and the Meta Model API. Meta says it sustains longer multi-step work in a single thread, asks clarifying questions when stuck, and uses about 20% fewer tool calls and 25% fewer tokens than Muse Spark 1.2. API pricing is unchanged at $1.25 per million input tokens and $4.25 output ($0.15 cached input), with a cheaper Contributor tier at $0.10/$0.20 that lets Meta train on your data. A max reasoning setting, which produced Meta's best published scores, is now available in Muse Code and the API.

QUICK FACTS

Pricing Paid
Platforms api, desktop
API Yes
Open Source No
Modalities LLMs, IDEs & Coding Tools
Best For Best Low-Cost Frontier Coding Model
Date Added 2026-09-29

WHY WE PICKED IT

On Artificial Analysis's Intelligence Index it scored 61, level with GPT-5.6 Sol and Claude Opus 5, according to VentureBeat, at a far lower per-token price than either. It is also the model behind Meta's Muse personal agent, so it is worth knowing even if you never call the API.

STRENGTHS

LIMITATIONS

GETTING STARTED

Install Muse Code on macOS or Linux, or call it through the Meta Model API at dev.meta.ai. Choose the Standard tier unless you are comfortable with Meta training on your prompts, which is the condition of the cheaper Contributor tier.

OFFICIAL LINKS

Website↗ Developer docs↗

SIMILAR TOOLS

Google Antigravity 2.0 Claude Fable 5 GPT-6 Astra NotebookLM Claude Opus 5

PRICING

Paid

Requires a paid subscription.

📚

FEATURED IN GUIDES

CLAUDE.md In Practice: What Actually Earns A Place In The File

The most-starred CLAUDE.md on GitHub has four rules, not twelve, and the error rates everyone quotes...

Open Models: What They Cannot Do

The benchmark gap has largely closed: open models now score within a point of the closed frontier on...

Hardware For Local AI Models: What The Memory Shortage Changed

Capacity decides whether a model runs. Bandwidth decides how fast it talks, and it is the number mos...

How To Run AI Models Locally: Hardware, Quantisation And Engines

Running a frontier open model locally is a memory problem before it is a speed problem, and a bandwi...

Uncensored AI Models: What Abliteration Actually Does To Them

Abliteration removes a model's ability to refuse by deleting one direction from its activations. It ...

EXPLORE ALTERNATIVES

View Muse Spark 1.3 Alternatives (2026) →

Compare Muse Spark 1.3 with 5+ similar llms AI tools.

❓

FREQUENTLY ASKED QUESTIONS

Q

Is Muse Spark 1.3 free?

A

No, Muse Spark 1.3 requires a paid subscription.

Q

Does Muse Spark 1.3 have an API?

A

Yes, Muse Spark 1.3 offers an API for programmatic integration.

Q

What is Muse Spark 1.3 best for?

A

Muse Spark 1.3 is best for Best Low-Cost Frontier Coding Model. Muse Spark 1. On Artificial Analysis's Intelligence Index it scored 61, level with GPT-5.6 Sol and Claude Opus 5, according to VentureBeat, at a far lower per-token price than either. It is also the model behind Meta's Muse personal agent, so it is worth knowing even if you never call the API.

Q

What platforms does Muse Spark 1.3 support?

A

Muse Spark 1.3 supports api, desktop.

Q

Is Muse Spark 1.3 open source?

A

No, Muse Spark 1.3 is not open source.

Q

How do I get started with Muse Spark 1.3?

A

Install Muse Code on macOS or Linux, or call it through the Meta Model API at dev.meta.ai. Choose the Standard tier unless you are comfortable with Meta training on your prompts, which is the condition of the cheaper Contributor tier.

Q

How do I use Muse Spark 1.3?

A

Muse Spark 1.3 is a large language model for text generation, analysis, and conversation. Use the API for programmatic access. Enter prompts or questions to get responses. It excels at about 20% fewer tool calls and 25% fewer tokens than muse spark 1.2, per meta.

🏷️

FEATURED ON CURATEDAI

Work on Muse Spark 1.3? You're hand-reviewed in our directory. Add this badge to your site — it links back to this profile.

Featured on CuratedAI