Minaco

Muse Spark 1.3

Muse Spark 1.3 is Meta’s current Spark version for agentic coding and long-context work.

When to try it.

Use it for an implementation that needs both repository understanding and practical tool execution.

What to weigh

Spark 1.3 and Spark Open are different releases. This page describes the exact 1.3 route shown in the Minaco catalog.

A first task

Read the relevant modules and implement this change while preserving their public interfaces.

This is a suggested evaluation task. Check the result against your own requirements; it is not a benchmark or a guarantee of performance.

Know the rate.

Currently published for Muse Code. Rates below are Minaco Credits per one million tokens.

Input
2,500
Cached input
300
Output
8,500

Cache writes: 2,500 Credits per million tokens.

Estimate a model call

Example: 10,000 uncached input tokens and 1,000 output tokens cost approximately 33.5 Credits before per-request rounding.

An agent turn may make several model calls. Context, tool results and billable reasoning tokens affect the total; enter cache-write tokens separately when applicable. The prompt total determines the rate for the whole request. This estimate is not a charge cap or a checkout quote. How Credits work.

Exact route: meta/muse-spark-1.3

Catalog checked 2026-11-17. Model access depends on your plan and current service availability.

Use it in your workspace.

  1. Prepare Muse Code

    Install Minaco on your Apple silicon Mac, connect your account and prepare the native agent in Agent settings.

  2. Choose the exact model

    Select Muse Code and a Minaco-credit account mode. If your plan offers Muse Spark 1.3, choose it from the model selector. Desktop 0.13.14 or later reads the server’s model catalog.

  3. Give it a bounded task

    Open the project folder, provide the necessary context and review any approvals. Inspect the result and usage before expanding the scope.

When the next stage calls for a different agent, finish the turn and switch in the same conversation. Minaco prepares the visible working context for the next native session; hidden reasoning and credentials do not transfer.

How context handoff works →

Read the source.

Muse model documentation describes the upstream model.

Editorial review: 2026-11-11. Task suggestions and comparisons are Minaco’s guidance, not vendor benchmark results. Minaco is an independent workspace; model API features do not imply that every feature is exposed by the native agent.

Compare nearby choices.

  • Muse Wonder — Muse Wonder is Meta’s model for complex software work and long-horizon agent tasks. The upstream documentation identifies it as a preview.
  • Muse Ember — Muse Ember is Meta’s efficient execution model for repeated work such as tool calls, routing, extraction and coding subtasks.

Keep the work moving.

Your agents. Your workspace. One place to continue.

Download for Mac