> ## Content Index
> Fetch the complete content index at: https://www.testingcatalog.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# Meta Muse Spark 1.4 surfaces in RocksDB pull request
- URL: https://www.testingcatalog.com/meta-muse-spark-1-4-surfaces-in-rocksdb-pull-request/
- Published: 2026-11-13T17:14:52.000Z
- Updated: 2026-11-13T17:16:44.000Z
- Description: Meta's unreleased Muse Spark 1.4 appeared in RocksDB live-tuning test notes, with one internal call logging 7,867 reasoning tokens.
- Author: Alexey Shabanov
- Tags: Meta, AI Rumours, Latest AI News

An unreleased Meta model called muse-spark-1.4-internal has appeared in a public GitHub pull request on Meta’s RocksDB repository. First spotted by [@LuminaBench](https://x.com/LuminaBench?ref=testingcatalog.com), the reference points to the next version of Meta’s Muse Spark line already running in internal production tooling.

> META 🔥: Muse-Spark-1.4-internal has been spotted in one of the PRs on Github.   
>  
> \> The PR is a small logging change to RocksDB's experimental "live tuning" feature.   
>  
> \> The mention appears to be in the PR notes, which seem to be auto-generated.   
>  
> It's expected that Muse Spark 1.4… [https://t.co/VhEpXRseC0](https://t.co/VhEpXRseC0?ref=testingcatalog.com) [pic.twitter.com/k8fjXYYnY7](https://t.co/k8fjXYYnY7?ref=testingcatalog.com)
> 
> — 🚨 AI News | TestingCatalog (@testingcatalog) [November 13, 2026](https://x.com/testingcatalog/status/2121273038607929694?ref%5Fsrc=twsrc%5Etfw&ref=testingcatalog.com)

The pull request makes a small logging change to [RocksDB’s experimental “live tuning” feature](https://github.com/meta/rocksdb/pull/15674?ref=testingcatalog.com). With live tuning, an AI advisor watches a running database and recommends configuration changes. At Meta, that advisor is an LLM accessed through an internal service called muse. The change adds two fields to every recommendation: the name of the model that answered and its usage, including tokens and seconds. The stated goal is to compare a frontier model with small on-host models across the same tuning cycles, measuring both cost and outcome.

The model name appears in the PR’s test notes, which seem to have been generated automatically. They describe a companion internal change that was run against a real model, with the tuner service reporting **muse-spark-1.4-internal** for that run. A single call used 33,535 input tokens, including 17,780 cached tokens, and produced 8,169 output tokens, including 7,867 reasoning tokens. The call took about 65 seconds. That makes 1.4 a model already being called inside Meta’s infrastructure tooling rather than merely tested in isolation. The PR was closed without merging a few hours after it opened, which is common for Meta changes that land through its internal systems.

![Side note - Meta API Platform got a UI redesign!](https://storage.ghost.io/c/2a/1b/2a1b1782-8506-4d7d-bf53-ad3fb52e2a0f/content/images/2026/11/Model-API-11-13-2026_06_13_PM.jpg)

Side note - Meta API Platform got a UI redesign recently

Meta released Muse Spark 1.3 on September 2, about a month after 1.2\. It is available in Muse Code and the Meta Model API with a 1M-token context, priced at $1.25 per million input tokens and $4.25 per million output tokens. Meta pitched it as a big step up in coding and long-horizon agentic work, while using about 25% fewer tokens than 1.2\. More than two months have passed since then, so a 1.4 model already in internal use suggests the next update may not be far off. Meta has not confirmed a name, timing, or feature set for Muse Spark 1.4.

## Sources and related context

- [RocksDB live tuning pull request](https://github.com/meta/rocksdb/pull/15674?ref=testingcatalog.com): Supports: The PR describes the logging change and records the muse-spark-1.4-internal model ID and call usage in its test notes.
- [Meta introduces Muse Spark 1.3](https://research.meta.ai/blog/introducing-muse-spark-1-3?ref=testingcatalog.com): Related context: Meta's September 2 announcement explains the preceding release, its coding and agentic focus, availability, and lower token use than 1.2.
- [Meta Model API Muse Spark pricing](https://dev.meta.ai/docs/pricing-rate-limits?ref=testingcatalog.com): Related context: Meta lists standard Muse Spark API pricing at $1.25 per million input tokens and $4.25 per million output tokens.