Muse Spark 1.2

Muse Spark 1.2 is Meta's coding-focused reasoning model for complex agentic tasks, reading text, images, video, audio, and PDFs across a context window of 1.0M tokens.

Input and output price: Input $1.25, Output $4.25, Per 1M tokens
24h uptime: Loading AI Gateway uptime

Get API key Read the docs

import { streamText } from 'ai'

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

Read docs

Overview API Providers Uptime Status Throughput Latency Similar About FAQ

Copy link to headingMore models by Meta

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Free Tier	Release Date

meta/muse-image-1.0

—

$0.01/img

—

08/26/2026

meta/muse-spark-1.2-contributor

4.1 s

167 tps

$0.10/M

$0.20/M

Read$0.002/M

—

08/05/2026

meta/muse-spark-1.1

6.4 s

153 tps

$1.25/M

$4.25/M

Read$0.15/M

—

07/09/2026

meta/llama-4-scout

131K

0.2 s

203 tps

$0.17/M

$0.66/M

—

04/05/2025

meta/muse-spark-1.3-contributor

2.4 s

104 tps

$0.10/M

$0.20/M

Read$0.002/M

—

meta/muse-spark-1.3

4.0 s

110 tps

$1.25/M

$4.25/M

Read$0.15/M

—

Your use is subject to Meta's Terms & Privacy Policies.

Agent Stack

Core Platform

Tools

Learn

Build

Explore

Muse Spark 1.2

Copy link to headingMore models by Meta