LLM Reference

Using Muse Spark 1.2 on Meta Model API

Implementation guide · Muse · AI at Meta

Serverless

Meta Model API exposes Muse Spark 1.2 through model ID muse-spark-1.2. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-08-24. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Meta Model API and generate an API key.
  2. 2
    Use the Meta Model API SDK or REST API to call muse-spark-1.2 — see the documentation for request format.
  3. 3
    You'll be billed $1.25/1M input, $4.25/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Meta Model API documentation for integration details.

Pricing on Meta Model API

TypePrice (per 1M)
Input tokens$1.25
Output tokens$4.25

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

About Muse Spark 1.2

Muse Spark 1.2 is Meta Superintelligence Labs' proprietary multimodal reasoning model for agentic coding and long-context work, released August 5, 2026. It supports a 1,048,576-token context window and up to 131,072 output tokens through the Meta Model API. No public weights release at launch.

Full model details →

Model Specs

Released2026-08-05
Context1.05m
ArchitectureDecoder Only

More Models on Meta Model API

Muse Spark 1.1
All models on Meta Model API →

Provider

Meta Model API

Meta