meta/muse-spark-1.2
Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, audio, and PDF documents, returns text, and offers a 1M-token context...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Meta | $1.25 | $4.25 | 1.0M | 100% |
Muse Spark 1.2 costs $1.25 per million input tokens and $4.25 per million output tokens via OpenRouter, making it 222nd cheapest of 306 paid models.
Muse Spark 1.2 scores 54.1 on the Artificial Analysis Intelligence Index, ranking 8th of 158 benchmarked models, with a GPQA Diamond score of 90%.
Muse Spark 1.2 generates around 149 tokens per second with 3.7s time-to-first-token (p50), the 36th fastest tracked model.
Muse Spark 1.2 supports a 1.0M-token context window. It accepts text, image, video, file, audio input.