# Muse Spark 1.2

Meta's coding-focused successor to Muse Spark 1.1. Muse Spark 1.2 plans and delegates as a main agent or executes in parallel as a subagent, across a context window of 1.0M tokens.

- **Model ID:** `meta/muse-spark-1.2`
- **Type:** chat
- **Providers:** meta
- **Context window:** 1,048,576
- **Maximum output tokens:** 1,048,576
- **Pricing:** $1.25/1M input tokens, $4.25/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/muse-spark-1.2

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'meta/muse-spark-1.2',
  prompt: 'Why is the sky blue?'
})
```

## About

Muse Spark 1.2 is Meta's reasoning model for complex agentic tasks, and the coding-focused successor to Muse Spark 1.1. It accepts text, images, video, audio, and PDF documents, returns text, and works within a context window of 1.0M tokens.

Multi-agent work is the design centre. Muse Spark 1.2 runs either as a main agent that plans and delegates, or as a subagent executing in parallel, and it was built around harness patterns like context compaction, whole-repository work, and long-running tasks. That shows up as durability across long sessions rather than as a single benchmark number.

Support covers structured output, parallel function calling, and configurable reasoning effort, and the model works across multiple coding harnesses rather than assuming one.

A second slug, `muse-spark-1.2-contributor`, serves these same weights at a much lower rate in exchange for Meta training on your inputs and outputs. Choose between them on data governance first and price second. See the comparison on that model's page.

You can integrate Muse Spark 1.2 through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

## What to consider

The cheaper `muse-spark-1.2-contributor` slug is not a different model. It is the same weights on a data-sharing arrangement, so if cost is pushing you toward it, read what that arrangement covers before switching.

A context window of 1.0M tokens invites large prompts, and cost follows what you actually send. In an agent loop most input becomes cache reads, so measure your cached-versus-fresh ratio against the pricing panel on this page rather than sizing from the headline input rate.

Muse Spark 1.2 is built for multi-step agentic work. On single-turn questions or short completions, a smaller model in the family will usually be the better economic fit.

## When to use

### Best For

- **Multi-agent workflows** running as a planning main agent or a parallel subagent
- **Whole-repository work** where long sessions and context compaction were design targets
- **Multimodal engineering input** spanning text, images, video, audio, and PDFs
- **Parallel function calling** across tools within a single reasoning pass
- **Harness portability** since it is not tied to one coding harness

### Consider Alternatives When

- **Cost is the deciding factor** and your data can be shared, where the contributor tier serves the same weights for far less
- **Single-turn prompts** carry the workload, where a smaller model fits the economics better
- **Data cannot leave your control** in any form, where you should confirm retention terms before either tier
- **Open weights** are required, where Muse Glimmer 30B is the Apache 2.0 option

## Best for

- **Multi-Agent Workflows:** Planning main agent or parallel subagent roles
- **Whole-Repository Work:** Long sessions with context compaction as a design target
- **Multimodal Engineering Input:** Text, images, video, audio, and PDFs
- **Parallel Function Calling:** Multiple tools within one reasoning pass
- **Harness Portability:** Not tied to a single coding harness

## Consider alternatives

- **Cost-Driven Workloads:** The contributor tier serves the same weights for far less, with data sharing
- **Single-Turn Prompts:** A smaller model in the family fits the economics better
- **Strict Data Control:** Confirm retention terms before choosing either tier
- **Open Weights Requirement:** Muse Glimmer 30B is the Apache 2.0 option

## Frequently asked questions

### What is Muse Spark 1.2 built for?

Complex agentic tasks with a coding focus. It runs as a main agent that plans and delegates, or as a subagent executing in parallel.

### What input types does Muse Spark 1.2 accept?

Text, images, video, audio, and PDF documents. It returns text.

### What is the context window for Muse Spark 1.2?

The context window is 1.0M tokens, with up to 1.0M tokens per response.

### How is Muse Spark 1.2 different from muse-spark-1.2-contributor?

Same weights and same capabilities. The contributor slug bills far less in exchange for Meta using your inputs and outputs to train its models. Decide on data governance first.

### How does Muse Spark 1.2 compare to Muse Spark 1.1?

It is the coding-focused successor, built around harness patterns including context compaction, subagents, whole-repository work, and long-running tasks.

### Does Muse Spark 1.2 support parallel tool calls?

Yes, along with structured output and configurable reasoning effort.

### Does Muse Spark 1.2 support Zero Data Retention?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/muse-spark-1.2)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://developer.meta.com/ai/models/muse-spark/)