Question 1

What is Muse Spark 1.1?

Accepted Answer

Muse Spark 1.1 is a model from Meta, released on Jul 9, 2026. Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window. The model is designed to orchestrate multi-agent workflows, acting as either a main agent that plans and delegates or as a subagent, and generalizes zero-shot to new tools, MCP servers, and custom skills. It supports structured output, parallel function calling, built-in search with citations, and configurable reasoning effort. Meta reports strong performance on real-world coding across large codebases, computer-use workflows, and visual-to-code generation.

Question 2

How much does Muse Spark 1.1 cost?

Accepted Answer

On the Respan gateway, input starts at $1.25 per 1M tokens on every provider, and output starts at $4.25 per 1M tokens on every provider, after gateway discounts.

Question 3

Which providers serve Muse Spark 1.1 on Respan?

Accepted Answer

2 providers serve Muse Spark 1.1: EmpirioLabs and OpenRouter.

Question 4

What is Muse Spark 1.1's context window?

Accepted Answer

Muse Spark 1.1 accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Muse Spark 1.1 with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "muse-spark-1.1". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Muse Spark 1.1?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 87 tokens per second, and the lowest response latency was 0.7 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

Where does Muse Spark 1.1 rank on the Respan Index?

Accepted Answer

Muse Spark 1.1 scores 45.1 out of 100 on the Respan Index v1.1, ranking #34 of 138 models. By category: Coding 26.1, Agents 57.7, Reasoning 42.4, Knowledge & language 54.4, and Human preference 53.9. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by llmmetric.com.

Question 8

How does Muse Spark 1.1 score on benchmarks?

Accepted Answer

Muse Spark 1.1 has 30 published benchmark scores, including Terminal-Bench 2.1 80%, MCP Atlas 88.1%, and LiveBench Reasoning 87.7%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output	Capabilities
EmpirioLabs`empiriolabs/muse-spark-1-1`	1.0M	$1.25/M	$4.25/M
OpenRouter`openrouter/meta/muse-spark-1.1`	1.0M	$1.25/M	$4.25/M

Muse Spark 1.1

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Respan Indexv1.1

Coding5

Apps

Muse Spark 1.1 FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.

Agents11

Reasoning3

Math1

Knowledge3

Multimodal2

Arena4

Other1