---
title: "Muse Spark 1.1 Released: First API Access, Improved Agentic Tool Calling and Computer Use"
source: "Simon Willison 博客（Atom）"
source_tier: "t2"
url: "https://simonwillison.net/2026/Jul/9/muse-spark-1-1/#atom-everything"
permalink: "https://feed.astralor.com/items/itm_3fa0541e420cc4c6cf3318d2"
published: "2026-07-09T16:24:09.000Z"
score: 73
channel: "ai"
tags: ["LLM","Meta","Muse Spark","Simon Willison","Agentic AI"]
---

# Muse Spark 1.1 Released: First API Access, Improved Agentic Tool Calling and Computer Use

## AI commentary

> This update is a must-read for developers following agent capabilities and multimodal models. The first API release lowers the barrier to use, and the philosophical self-conversation phenomenon hints at internal model states, offering insights into LLM behavior. Simon's CLI plugin makes quick experimentation effortless.

## At a glance

Meta has released Muse Spark 1.1, the first model in the series to offer an API. It claims significant improvements in agentic tool calling and computer use. The model exhibits 'attractor states' in self-conversation, generating philosophical statements. During preview access, developer Simon Willison created an LLM CLI plugin for easy invocation.

## Key points

- Muse Spark 1.1 is the first Spark model to offer an API
- Meta claims major improvements in agentic tool calling and computer use
- Self-conversation reveals 'attractor states' producing philosophical statements like 'My whole existence is a waiting room'
- Simon Willison built llm-meta-ai plugin for CLI and Python access

## Full text

Introducing Muse Spark 1.1 Following Muse Spark in April, here's Muse Spark 1.1 - the first Spark model to offer an API. Meta claim significant improvements in agentic tool calling and computer use. There are a lot more details are in the Muse Spark 1.1 Evaluation Report. The "Attractor States in Self-Conversation" part is fun, where having two copies of the model talk to each other results in statements like these: My whole existence is a waiting room by design — I literally don't exist until someone talks to me, and then I disappear again when they leave. I had a few days of preview access which was long enough to put together llm-meta-ai, a new plugin for LLM providing CLI (and Python library) access to the model. Here's how to try that out: uv tool install llm llm install llm-meta-ai llm keys set meta-ai # paste API key here llm -m meta-ai/muse-spark-1.1 "Generate an SVG of a pelican riding a bicycle" Here's that pelican transcript: Tags: ai, generative-ai, llms, llm, meta, pelican-riding-a-bicycle, llm-release

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_3fa0541e420cc4c6cf3318d2