Muse Spark 1.1
Muse Spark 1.1 is a large language model made by Meta, added to the catalog on 16 Jul 2026. It has a context window of 1,048,576 tokens and costs $1.25 per 1M input tokens and $4.25 per 1M output tokens. It accepts text, images, files and video and produces text. Typical uses: analysing PDF documents, answering questions about images and summarising video content.
Price checked · source: OpenRouter
What Muse Spark 1.1 is
Muse Spark 1.1 is a multimodal reasoning model from Meta, described as built for agentic tasks. It accepts text, images, video, and files, including PDF documents, and produces text. Its input types suit tasks involving written material alongside visual content or video. The model’s output is text, so results from those inputs are returned in a text form.
The model has a context window of 1,048,576 tokens, or about one million tokens. This provides room to supply substantial material in a single context, such as lengthy documents or collections of text and visual inputs. Its listed maximum output is 943,718 tokens. These figures describe the model’s context and output limits; they do not specify how much content a particular task should use.
Muse Spark 1.1 supports reasoning, tools, structured outputs, and response formats. These capabilities make it relevant to tasks where a response needs to follow a specified structure, or where tool support is part of a workflow. Its multimodal inputs also suit questions about provided images, video, or PDF content, with answers generated as text. The catalog identifies it as a reasoning model for agentic tasks, but does not provide further details about particular tools or task outcomes. Its combination of text output, multimodal input, and a large context window can support document analysis, visual-content questions, video summarisation, and structured text generation.
Key features
- Accepts text, images, video, and files including PDF documents
- Produces text
- Has a context window of 1,048,576 tokens
- Supports reasoning, tools, structured outputs, and response formats
Typical uses
- Analysing PDF documents
- Answering questions about images
- Summarising video content
- Processing long text inputs
- Generating structured text
Muse Spark 1.1 pricing
US dollars, list price through OpenRouter.
| Item | Standard |
|---|---|
| Input, per 1M tokens | $1.25 |
| Output, per 1M tokens | $4.25 |
| Cached input read, per 1M tokens | $0.15 |
| Web search, per search | $0.0025 |
No price change since it was added on 16 Jul 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0019 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.035 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.046 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.194 |
Muse Spark 1.1 specifications
| Model id | meta/muse-spark-1.1 |
|---|---|
| Version | muse-spark-1.1-20260709 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 16 Jul 2026 |
| Input types | text, image, video, file |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Muse Spark 1.1 yet.
Compare Muse Spark 1.1
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.