Meta
Meta’s latest Muse Spark for coding and multi-step tool workflows, with a 1M-token context and max reasoning on the Standard tier.
At a glance
API model ID: muse-spark-1.3
Capabilities & boundaries
Tool support requires the appropriate API integration; a supported tool is not automatically active in every chat.
Meta supports minimal through max on Standard-tier Muse Spark 1.3. Max is unavailable on Contributor models. Omitting the effort parameter lets the model choose its reasoning depth; no named default is assumed here. More effort can increase latency and billed output tokens.
Unsupported settings: none.
Put it to work
Original examples from EZ Ai Assist. Adapt these to your task and the features available in your workspace.
Workflow 01
Give the model a bounded change and permission boundaries.
Using the repository context and acceptance criteria I provide, propose a minimal implementation plan. Identify the files likely to change, dependencies, tests, and rollback considerations. Do not modify code yet. Mark any step requiring network access, credentials, or production changes for explicit approval.
Workflow 02
Use screenshots and supplied observations without inventing interaction results.
Review this sequence of screenshots and recorded steps for a signup workflow. Identify inconsistent states, missing feedback, and likely failure paths. Distinguish visible evidence from behavior that needs an interactive test. Propose a prioritized test plan with expected results, without submitting forms or changing accounts.
Workflow 03
Keep tool execution and authorization explicit.
Design a bounded assistant workflow for the task below using only the listed tools. For each step specify its input, success check, timeout, and recovery path. Require approval before external writes or irreversible actions. Include how to stop safely when evidence is missing or a tool returns conflicting data.
Developer reference
These are Meta Standard API reference prices, not EZ Ai Assist subscription prices.
View EZ Ai Assist plans| Token type | Price |
|---|---|
| Input | $1.25 |
| Cached input | $0.15 |
| Output (including reasoning) | $4.25 |
| Usage | Rate and unit |
|---|---|
| Web-search grounding | $2.50per 1,000 search queries |
Common questions
Start with Muse Spark 1.3 when evaluating Meta for multi-step coding and tool-assisted work. Meta recommends it for new work, but use 1.2 for audio-heavy tasks while 1.3’s audio understanding remains limited.
Meta lists text, image, video, audio, and PDF inputs, with text output. However, audio understanding in 1.3 is not fully supported and can be degraded. Use 1.2 or a dedicated speech-to-text model when audio is central.
Reasoning tokens count toward the output budget and are billed at the output rate. Higher effort can take longer and leave less room for visible text within the same budget. Muse Spark does not support turning reasoning off with none.
Yes, on the Standard muse-spark-1.3 API model. The Contributor variant does not support max. Check whether your application exposes that control before building a workflow around it.
Contributor is a separate discounted API model ID that permits Meta to train on prompts and completions. Standard has different rates and data-use terms. This guide does not assume your EZ Ai Assist workspace uses either specific tier.
This guide covers Muse Spark hosted on Meta Model API. Meta’s model overview separately identifies its open-weight offerings; do not assume Muse Spark’s weights, deployment options, or licensing match Llama or another family.
No. It is a provider API reference with original workflow examples. Check the app for model access, input support, tools, reasoning controls, and applicable data terms. EZ Ai Assist plan prices are separate from Meta’s per-token charges.
Check the source
Specifications and API prices checked on . Example prompts and workflow advice are editorial guidance from EZ Ai Assist.
Same provider
Meta
Meta’s previous Muse Spark version supports text, image, video, audio, and PDF inputs for long-context reasoning and tool-assisted work.
Meta
Meta’s original Muse Spark version supports multimodal understanding and reasoning with a 1M-token context and Standard-tier API pricing.