muse-spark-1.2 · Meta
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window.
muse-spark-1.2 has a 1,048,576 token context window.
On AIHubMix, muse-spark-1.2 costs $1.375 per million input tokens and $4.675 per million output tokens.
muse-spark-1.2 accepts text, image, video, audio and PDF input.
muse-spark-1.2 supports thinking and tool calling. Per-protocol parameter support is listed in the capability table on this page.
muse-spark-1.2 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to muse-spark-1.2 — no other code changes needed.
muse-spark-1.2 is developed by Meta. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Muse Glimmer 30B is a dense causal language model distilled from Muse Spark, designed for…
Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It…
Use muse-spark-1.2 via the AIHubMix unified API — one interface for every major LLM.