# Muse Spark Muse Spark is Meta's model for agentic and coding work at scale, such as multi-step tool loops, software engineering assistants, sub-agent tasks, and long-context reasoning. It's the lower-cost option for high-volume, latency-sensitive work, and on Model API it also offers a discounted Contributor mode. ## At a glance | | | | :--------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | | **[Standard mode](https://dev.meta.ai/docs/pricing-rate-limits#standard-mode) model IDs** | `muse-spark-1.3`, `muse-spark-1.2`, `muse-spark-1.1` | | **[Contributor-mode](https://dev.meta.ai/docs/pricing-rate-limits#contributor-mode) variants** | `muse-spark-1.3-contributor`, `muse-spark-1.2-contributor` | | **Input** | Text, image, video, audio, and PDF | | **Output** | Text | | **Context window** | 1,048,576 tokens | | **[Reasoning effort](https://dev.meta.ai/docs/reasoning)** | `"minimal"` to `"max"` on `muse-spark-1.3`; see [Versions](https://dev.meta.ai/docs/muse-spark#versions) | | **Endpoints** | [Responses](https://dev.meta.ai/docs/protocols/responses), [Chat Completions](https://dev.meta.ai/docs/protocols/chat-completions), [Messages](https://dev.meta.ai/docs/protocols/messages) | | **Pricing** | Pay-as-you-go; see [Muse Spark pricing](https://dev.meta.ai/docs/pricing-rate-limits#muse-spark-pricing) | | **Rate limits** | See [rate limits](https://dev.meta.ai/docs/pricing-rate-limits#rate-limits) | ## Build with Muse Spark Use Muse Spark for high-volume, latency-sensitive, or cost-sensitive work: - **Sub-agent tasks**: run the many short, focused tasks that a main agent hands out. - **Tight tool loops**: drive multi-step tool calls where latency per turn adds up. - **Classification**: process large volumes of requests at a lower cost per token. - **Coding assistants**: connect the [coding agent](https://dev.meta.ai/docs/coding-agents) you already use, or run [Muse Code](https://dev.meta.ai/docs/muse-code). Muse Spark also handles [image understanding](https://dev.meta.ai/docs/media-understanding#images), [video](https://dev.meta.ai/docs/media-understanding#video) and [audio](https://dev.meta.ai/docs/media-understanding#audio) understanding, [tool calling](https://dev.meta.ai/docs/tool-calling), [structured output](https://dev.meta.ai/docs/structured-output), and [search grounding](https://dev.meta.ai/docs/search-grounding). For complex, long-running tasks where capability matters more than cost, see [Choose a model](https://dev.meta.ai/docs/choose-a-model). ## Versions Muse Spark comes in three versions. All take text, image, video, audio, and PDF input, return text, and have a 1,048,576-token context window. They differ by capability: - **Muse Spark 1.3** (`muse-spark-1.3`): the latest version, tuned for agentic workflows (multi-step tool, browser, and long-horizon tasks) with improved coding over 1.2. Supports all [reasoning effort](https://dev.meta.ai/docs/reasoning) levels, including the `"max"` level for extended reasoning (not available with `muse-spark-1.3-contributor`). **Recommended for new work.** - **Muse Spark 1.2** (`muse-spark-1.2`): the previous version. - **Muse Spark 1.1** (`muse-spark-1.1`): the original version. > **NOTE: Audio input on Muse Spark 1.3** > > Audio understanding in Muse Spark 1.3 is not fully supported, and response quality for requests that include audio may be degraded. For audio, use Muse Spark 1.2, or [Muse Voice Transcribe](https://dev.meta.ai/docs/models#muse-voice-transcribe) for dedicated speech-to-text. `muse-spark-1.3` is the default model in most code examples in these docs. The [coding agents](https://dev.meta.ai/docs/coding-agents), [agent frameworks](https://dev.meta.ai/docs/agent-frameworks), and [computer use](https://dev.meta.ai/docs/computer-use) guides use `muse-wonder-1.0` for long-running agentic work. ## Make your first call Follow the [quickstart](https://dev.meta.ai/docs/quickstart#first-call) to set your key and send your first request to `muse-spark-1.3`. ## Availability Every Muse Spark version is available on pay-as-you-go. All versions except Muse Spark 1.1 are also available in [Muse Code](https://dev.meta.ai/docs/muse-code), on pay-as-you-go and with any subscription. | Version | Model API (pay-as-you-go) | Muse Code | | :-------------------------------------------------------- | :------------------------ | :------------------------------------------------------------------------------------- | | Muse Spark 1.3 (`muse-spark-1.3`) | Standard mode | Pay-as-you-go and [every plan](https://dev.meta.ai/docs/muse-code/subscriptions#about) | | Muse Spark 1.3 Contributor (`muse-spark-1.3-contributor`) | Contributor mode | Pay-as-you-go and [every plan](https://dev.meta.ai/docs/muse-code/subscriptions#about) | | Muse Spark 1.2 (`muse-spark-1.2`) | Standard mode | Pay-as-you-go and [every plan](https://dev.meta.ai/docs/muse-code/subscriptions#about) | | Muse Spark 1.2 Contributor (`muse-spark-1.2-contributor`) | Contributor mode | Pay-as-you-go and [every plan](https://dev.meta.ai/docs/muse-code/subscriptions#about) | | Muse Spark 1.1 (`muse-spark-1.1`) | Standard mode | Not available | In [Standard mode](https://dev.meta.ai/docs/pricing-rate-limits#standard-mode), your content — the prompts, code, files, and context you send, plus the model responses you get back — is not used to train Meta models. In [Contributor mode](https://dev.meta.ai/docs/pricing-rate-limits#contributor-mode), your content may be used to train future Meta models, in exchange for a lower price. On pay-as-you-go, switch between the two by choosing the model ID: for example, `muse-spark-1.3` for Standard mode or `muse-spark-1.3-contributor` for Contributor mode. Muse Spark 1.1 is available in Standard mode only. See [Pricing and rate limits](https://dev.meta.ai/docs/pricing-rate-limits) for rates. ## Next steps - Weighing Muse Spark against Muse Wonder? [Choose a model](https://dev.meta.ai/docs/choose-a-model) compares them workload by workload. - Get schema-guaranteed JSON for your classification pipeline with [structured output](https://dev.meta.ai/docs/structured-output). - Run Muse Spark as the sub-agent model under a Muse Wonder main loop with an [agent framework](https://dev.meta.ai/docs/agent-frameworks).