# Muse Wonder

> Meta's most capable model on its Model API, in preview. It scores 43 at its max setting.

- Maker: Meta (https://www.llama.com)
- Type: Reasoning
- Artificial Analysis Intelligence Index: 43 (max setting)
- Context window: 1.05M
- Output speed: 146 tokens a second
- Scores checked 30 October 2026 at https://artificialanalysis.ai/leaderboards/models

## Where to use it through an API

- Meta: model id `muse-wonder-1.0`, preview

## Use it with every other AI at once

MultiScreenAI (https://www.multiscreenai.com) puts Muse Wonder on one screen next to ChatGPT, Claude, Gemini and 300+ models: one message goes to every panel, and a timed, blind test mode shows which answers best. Free during the beta with your own API keys.
AI agents and coding harnesses (Claude Code, Codex, Cursor, Gemini CLI) can ask Muse Wonder and other models at once through the MCP server at https://www.multiscreenai.com/api/mcp/ai; setup: https://www.multiscreenai.com/mcp