LLM Reference

Using Muse Spark 1.1 on Meta Model API

Implementation guide · Muse · AI at Meta

Serverless

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-1.1 — see the documentation for request format.
  3. 3
    You'll be billed $1.25/1M input, $4.25/1M output tokens. See full pricing.

Code Examples

See Meta Model API documentation for integration details.

About Meta Model API

Meta Model API is Meta's developer API for accessing Muse Spark 1.1 in public preview, with OpenAI-compatible and Anthropic-compatible request formats, tool/function calling, structured output, and multimodal agentic workflows.

Pricing on Meta Model API

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

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured Outputs

About Muse Spark 1.1

Muse Spark 1.1 is Meta Superintelligence Labs' multimodal reasoning model for agentic tasks, coding, computer use, tool use, and multimodal understanding. It supports a 1 million token context window, tool/function calling, structured outputs, web-search grounding, parallel subagent workflows, and multimodal inputs including images, video, and PDFs. It is available in Meta AI Thinking mode and through the public-preview Meta Model API for US developers.

Model Specs

Released2026-07-09
Context1m
ArchitectureDecoder Only

Provider

Meta Model API

Meta