Models/Meta

Meta

OpenRouter splits Meta and meta-llama. We collapse both onto this hub. meta-llama is 2.8% of text requests (44.1M). Muse Spark 1.2 is the closed flagship. Maverick and Scout are the open Llama 4 cards. No /models/meta-llama/ URL.

Not cited Week tokens
2.8% Request share 44.1M requests
10 Cards on this hub
10 Family entries

This lab was not on the This Week LLM Leaderboard or the named Top Weekly rows we cite. No week-token figure is invented. Fetched 2026-08-19. Text request share for meta-llama: 2.8% (44.1M requests) in the same window. That is request share, not tokens. OpenRouter This Week tokens are prompt plus completion. The percent next to a row is week-over-week change, not share of the week. Market share on this page is text request share by author, a different number.

01

Family map

current
Muse Spark 1.2

OpenRouter meta/muse-spark-1.2. In the Mac bundled catalog; not on the live public allowlist we fetched.

current
Llama 4 Maverick

Lives on this hub only. OpenRouter meta-llama/llama-4-maverick. Official HF meta-llama/Llama-4-Maverick-17B-128E-Instruct. AA Intelligence Index 14. No /models/meta-llama/ URL.

current
Llama 4 Scout

OpenRouter meta-llama/llama-4-scout. Official HF meta-llama/Llama-4-Scout-17B-16E-Instruct.

current
Llama 3.1 8B Instruct

Llama 3.1 8B Instruct: 2026-08-19 OpenRouter row.

current
Muse Glimmer 30B

Muse Glimmer 30B: 2026-08-19 OpenRouter row.

current
Muse Spark 1.1

Muse Spark 1.1: 2026-08-19 OpenRouter row.

current
Llama 3.3 70B Instruct

Llama 3.3 70B Instruct: 2026-08-19 OpenRouter row.

current
Llama 3.2 1B Instruct

Llama 3.2 1B Instruct: 2026-08-19 OpenRouter row.

current
Llama 3.2 3B Instruct

Llama 3.2 3B Instruct: 2026-08-19 OpenRouter row.

current
Llama 3.1 70B Instruct

Llama 3.1 70B Instruct: 2026-08-19 OpenRouter row.

02

Cards

This hub lists every published card. Start with Muse Spark 1.2.

Ranked view: Best coding models: the independent leaderboard puts every Meta card with an independent coding row next to every other lab on one board, with the confidence intervals left visible.

Hosted inference

Get Plus when you want Continuum to serve it.

The app is free with your own keys. Plus adds Continuum-hosted inference and the ids we actually list on each card.

Plus is $25/mo with $25 weekly hosted usage. The Mac app stays free with your own keys. Get Plus is not Download for Mac.