Muse Spark 1.3
Muse Spark 1.3 is a large language model made by Meta, added to the catalog on 2 Sep 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: reasoning across text and visual inputs, working with file-based material and coding workflows.
Price checked · source: OpenRouter
What Muse Spark 1.3 is
Meta: Muse Spark 1.3 is a multimodal reasoning model from Meta, described for long-running agentic, multi-agent, and coding workflows. It accepts text, images, video, and files, and produces text. Its supported capabilities include reasoning, tool use, structured outputs, and response-format controls. This combination suits workflows where prompts or source material arrive in more than one supported form and where the requested result is textual. The catalog description also says the model is designed to keep track of information across extended tasks.
It has a context length of 1,048,576 tokens and a maximum output of 943,718 tokens. The large context and extended-task focus may suit work involving substantial input or multiple stages. The provider’s description identifies agentic, multi-agent, and coding workflows as intended areas, but does not specify particular tools, programming languages, file formats, or video limits. Its output modality is text, including when the input includes images, video, or files.
Muse Spark 1.3 may be used for reasoning over mixed text and visual inputs, coding workflows, or tasks that involve tools. Structured-output and response-format support can be relevant when an application expects responses in a defined format. Its long context may also fit workflows that need to retain information across an extended task. The available facts identify supported modalities and capabilities, but do not give detailed performance claims or describe behavior for specific tasks.
Key features
- Accepts text, image, video, and file inputs
- Produces text
- Has a context length of 1,048,576 tokens
- Supports reasoning and tools
- Supports structured outputs and response formats
Typical uses
- Reasoning across text and visual inputs
- Working with file-based material
- Coding workflows
- Long-running agentic workflows
- Multi-agent workflows
Muse Spark 1.3 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 2 Sep 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 1.3 specifications
| Model id | meta/muse-spark-1.3 |
|---|---|
| Version | muse-spark-1.3-20260902 |
| Context window | 1,048,576 tokensAbout 786,432 English words |
| Max output | 943,718 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 2 Sep 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 1.3 yet.
Compare Muse Spark 1.3
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.