Choose a model

Muse Wonder and Muse Spark 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 both in the same agent.

Compare the models

Muse WonderMuse Spark
Built forComplex software engineering and long-horizon agentic workAgentic and coding work at scale
Use it whenCapability matters more than cost per tokenVolume, latency, or cost per token matters most
Model IDsmuse-wonder-1.0muse-spark-1.3 (recommended), muse-spark-1.2, muse-spark-1.1
InputText, image, video, audio, and PDFText, image, video, audio, and PDF
Context window1,048,576 tokens1,048,576 tokens
Reasoning effort"minimal" to "max""minimal" to "max" on muse-spark-1.3
Contributor mode on Model APINot availablemuse-spark-1.3-contributor, muse-spark-1.2-contributor
PricingMuse Wonder pricingMuse Spark pricing
AvailabilityMuse Wonder availabilityMuse Spark availability

Choose by workload

WorkloadModel
Multi-file coding changes in a real repositoryMuse Wonder
Multi-hour agent runs and sub-agent orchestrationMuse Wonder
The main loop of a coding agent or agent frameworkMuse Wonder
Computer useMuse Wonder
Sub-agent tasks handed out by a main agentMuse Spark
Tight tool loops and latency-sensitive turnsMuse Spark
Classification and other high-volume requestsMuse Spark
Discounted prices on Model API in Contributor modeMuse Spark, through a Contributor-mode variant
Audio understandingMuse Spark 1.2
Speech to textMuse Voice Transcribe
Image generation and editingMuse Image
Image and video segmentationSegment Anything Model

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, and put Muse Spark on sub-agents and background tasks, which run many short, focused jobs where cost adds up.

The harnesses you already use support this split:

  • Claude Code and the Claude Agent SDK: map the opus alias to muse-wonder-1.0 and the sonnet, haiku, and sub-agent models to muse-spark-1.3. See Set up Claude Code and Build with the 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.
  • Your own agent loop: pass a different model on each request. Both models accept the same request body; Switch between models lists the few settings that differ.

Switch between models

Moving a workload from one model to the other is a model ID change. Keep these differences in mind:

  • Reasoning effort: muse-wonder-1.0 and muse-spark-1.3 accept "minimal" to "max". "max" isn't available on muse-spark-1.2, muse-spark-1.1, or muse-spark-1.3-contributor; see Reasoning.
  • Contributor mode: on Model API, only Muse Spark has Contributor-mode variants. Muse Wonder is Standard mode only; see Muse Wonder 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.
  • Audio input: response quality for audio on Muse Spark 1.3 may be degraded. Use Muse Spark 1.2 or Muse Voice Transcribe instead.

Next steps