Muse Spark 1.1
Meta· released 16 Jul 2026
meta/muse-spark-1.1- Input / 1M tokens
- $1.25
- Output / 1M tokens
- $4.25
Longest answer: 944K tokens
About
Muse Spark 1.1 is a multimodal reasoning model from Meta, released on 2026-07-16. It accepts text, images, video and files, including PDF documents, and returns text. The model supports tools and vision, and its context window is 1,048,576 tokens. It can produce up to 943,718 tokens of output. Its model ID is meta/muse-spark-1.1. Input costs USD 1.25 per 1M tokens and output costs USD 4.25 per 1M tokens. These details make the input formats, text-only output, context size and per-token rates central considerations for teams assessing it for multimodal agentic tasks. Meta is listed as both maker and lab, and the official page is hosted on OpenRouter. The listed facts do not specify open weights or a Hugging Face ID.
Who it is for
Muse Spark 1.1 suits teams building agentic tasks that need to process text, images, video or PDF documents and return text. It may interest builders who need tools, vision support and a large context window.
What is good
- Accepts text, images, video and files.
- Supports tools and vision.
- Context window is 1,048,576 tokens.
- Maximum output is 943,718 tokens.
- Supports reasoning.
What to know first
- Outputs text only.
- Input costs USD 1.25 per 1M tokens.
- Output costs USD 4.25 per 1M tokens.
Verdict
Muse Spark 1.1 offers several input formats, tool support and a large context window for reasoning tasks. Its text-only output and listed input and output rates are important fit considerations.
Details
- Lab
- Metaopenrouter.ai · 3 Oct 2026
- Context
- 1,049Kopenrouter.ai · 3 Oct 2026
- Input price
- $1.25 / 1Mopenrouter.ai · 3 Oct 2026
- Output price
- $4.25 / 1Mopenrouter.ai · 3 Oct 2026
- Max output
- 943,718 tokensopenrouter.ai · 3 Oct 2026
- Inputs
- text, image, video, fileopenrouter.ai · 3 Oct 2026
- Open weights
- Noopenrouter.ai · 3 Oct 2026
More newest models
See the list
Listed on Inferse
- Newest Models in 2026466 listed
- Longest-Context Models in 2026466 listed
- Cheapest Language Models in 2026437 listed
- Models with Tool Calling in 2026395 listed
- Reasoning Models in 2026332 listed
- Vision Language Models in 2026295 listed
- Meta Models: Pricing per 1M Tokens and Context (2026)14 listed
Sources
- openrouter.ai/meta/muse-spark-1.1· checked 3 Oct 2026