# Choose a model [Muse Wonder](https://dev.meta.ai/docs/muse-wonder), [Muse Spark](https://dev.meta.ai/docs/muse-spark), and [Muse Ember](https://dev.meta.ai/docs/muse-ember) are reasoning models that take the same requests on the same endpoints, so moving a workload between them is a model ID change. Pick one by what each part of your app needs — or run them together in the same agent. ## Compare the models | | [Muse Wonder](https://dev.meta.ai/docs/muse-wonder) | [Muse Spark](https://dev.meta.ai/docs/muse-spark) | [Muse Ember](https://dev.meta.ai/docs/muse-ember) | | :------------------------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------ | | **Built for** | Complex software engineering and long-horizon agentic work | Agentic and coding work at scale | Efficient execution of high-volume, repeated work | | **Use it when** | Capability matters more than cost per token | The main loop or a harder task needs strong reasoning at a lower cost than Muse Wonder | A larger model plans, and sub-agents run many bounded tasks | | **Model IDs** | `muse-wonder-1.0` | `muse-spark-1.3` (recommended), `muse-spark-1.2`, `muse-spark-1.1` | `muse-ember-1.0` | | **Input** | Text, image, video, audio, and PDF | Text, image, video, audio, and PDF | Text, image, video, audio, and PDF | | **Context window** | 1,048,576 tokens | 1,048,576 tokens | 1,048,576 tokens | | **[Reasoning effort](https://dev.meta.ai/docs/reasoning)** | `"minimal"` to `"max"`; default `"max"` | `"minimal"` to `"max"` on `muse-spark-1.3`; default `"high"` | `"minimal"` to `"max"`; default `"max"` | | **[Contributor mode](https://dev.meta.ai/docs/pricing-rate-limits#contributor-mode) on Model API** | Not available | `muse-spark-1.3-contributor`, `muse-spark-1.2-contributor` | Not available | | **Pricing** | [Muse Wonder pricing](https://dev.meta.ai/docs/pricing-rate-limits#muse-wonder-pricing) | [Muse Spark pricing](https://dev.meta.ai/docs/pricing-rate-limits#muse-spark-pricing) | [Muse Ember pricing](https://dev.meta.ai/docs/pricing-rate-limits#muse-ember-pricing), with long-context rates over 200K input tokens | | **Availability** | [Muse Wonder availability](https://dev.meta.ai/docs/muse-wonder#availability) | [Muse Spark availability](https://dev.meta.ai/docs/muse-spark#availability) | [Muse Ember availability](https://dev.meta.ai/docs/muse-ember#availability) | ## Choose by workload | Workload | Model | | :------------------------------------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------- | | Multi-file coding changes in a real repository | Muse Wonder | | Multi-hour agent runs and sub-agent orchestration | Muse Wonder | | The main loop of a coding agent or agent framework | Muse Wonder | | Computer use | Muse Wonder, or Muse Spark or Muse Ember at lower cost | | A lower-cost main loop for agents and assistants | Muse Spark | | Knowledge-heavy questions answered without retrieval | Muse Spark or Muse Wonder | | Sub-agent tasks handed out by a main agent, including coding subtasks | Muse Ember | | Tool calls, tight tool loops, and latency-sensitive turns | Muse Ember | | Classification, routing, and other high-volume requests | Muse Ember | | Running the same task over thousands of images, files, or records | Muse Ember | | Discounted prices on Model API in [Contributor mode](https://dev.meta.ai/docs/pricing-rate-limits#contributor-mode) | Muse Spark, through a Contributor-mode variant | | Audio understanding | Muse Spark 1.2 | | Speech to text | [Muse Voice Transcribe](https://dev.meta.ai/docs/models#muse-voice-transcribe) | | Image generation and editing | [Muse Image](https://dev.meta.ai/docs/models#muse-image) | | Image and video segmentation | [Segment Anything Model](https://dev.meta.ai/docs/models#sam-3) | ## Combine models in one agent Most agents don't need one model for everything. Put Muse Wonder on the main loop, where planning and multi-step reasoning decide the outcome, or Muse Spark when the main loop needs to cost less. Put Muse Ember on sub-agents and background tasks, which run many short, focused jobs where cost adds up: the larger model plans, and Muse Ember handles the volume. The harnesses you already use support this split: - **Claude Code and the Claude Agent SDK**: map the `opus` alias to `muse-wonder-1.0`, the `sonnet` alias to `muse-spark-1.3`, and the `haiku` alias and sub-agent model to `muse-ember-1.0`. See [Set up Claude Code](https://dev.meta.ai/docs/coding-agents#setup-claude-code) and [Build with the Claude Agent SDK](https://dev.meta.ai/docs/agent-frameworks#claude-agent-sdk). - **Codex**: set `muse-wonder-1.0` as the default model, and switch to `muse-spark-1.3` for faster, lower-cost sessions. See [Set up Codex](https://dev.meta.ai/docs/coding-agents#setup-codex). - **Your own agent loop**: pass a different `model` on each request. The reasoning models accept the same request body; [Switch between models](https://dev.meta.ai/docs/choose-a-model#switch-models) lists the few settings that differ. ## Switch between models Moving a workload from one model to another is a model ID change. Keep these differences in mind: - **Reasoning effort**: `muse-wonder-1.0`, `muse-spark-1.3`, and `muse-ember-1.0` accept `"minimal"` to `"max"`. `"max"` isn't available on `muse-spark-1.2`, `muse-spark-1.1`, or `muse-spark-1.3-contributor`. When a request sets no effort, Muse Wonder and Muse Ember use `"max"` and Muse Spark uses `"high"`; see [Reasoning](https://dev.meta.ai/docs/reasoning). - **Contributor mode**: on Model API, only Muse Spark has Contributor-mode variants. Muse Wonder and Muse Ember are Standard mode only; see [Muse Wonder availability](https://dev.meta.ai/docs/muse-wonder#availability) and [Muse Ember availability](https://dev.meta.ai/docs/muse-ember#availability). - **Muse Wonder Full**: the higher-capability variant of Muse Wonder is available only in Muse Code, so no model ID on Model API selects it; see [Muse Wonder availability](https://dev.meta.ai/docs/muse-wonder#availability). - **Audio input**: response quality for audio on Muse Spark 1.3 may be degraded. Use Muse Spark 1.2 or Muse Voice Transcribe instead. - **Long-context pricing**: Muse Wonder and Muse Spark charge the same rate at any context length. Muse Ember bills a request with more than 200K input tokens at long-context rates, so compare costs at your real input sizes; see [Muse Ember pricing](https://dev.meta.ai/docs/pricing-rate-limits#muse-ember-pricing). - **Harder work**: for hard single-shot coding problems, knowledge-heavy questions, or visual coding, use Muse Spark or Muse Wonder rather than Muse Ember. ## Next steps - Read the full specs and recommended settings on the [Muse Wonder](https://dev.meta.ai/docs/muse-wonder), [Muse Spark](https://dev.meta.ai/docs/muse-spark), and [Muse Ember](https://dev.meta.ai/docs/muse-ember) pages. - Wire the main-loop and sub-agent split into your own code with an [agent framework](https://dev.meta.ai/docs/agent-frameworks). - Check what each split costs in [Pricing and rate limits](https://dev.meta.ai/docs/pricing-rate-limits).