Output tokens cost $4.68 per million on muse-spark-1.1 and $4.68 per million on muse-spark-1.2. Input tokens cost $1.38 per million on muse-spark-1.1 and $1.38 per million on muse-spark-1.2. Cached input tokens are billed at $1.38 per million on muse-spark-1.1 and $1.38 per million on muse-spark-1.2. Context lengths are 1,000,000 tokens on muse-spark-1.1 and 1,000,000 tokens on muse-spark-1.2. Time to first token (TTFT) measured on AIHubMix is 5.9s on muse-spark-1.1 and 5.4s on muse-spark-1.2. Measured output throughput is 183.7 tok/s on muse-spark-1.1 and 138.3 tok/s on muse-spark-1.2. On the LMArena coding leaderboard muse-spark-1.1 scores 1531 and muse-spark-1.2 scores 1533.
muse-spark-1.1muse-spark-1.2Muse 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.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
muse-spark-1.1: $4.68/M output tokens; muse-spark-1.2: $4.68/M. Use the cost calculator above to estimate your own workload.
muse-spark-1.2: 1533; muse-spark-1.1: 1531 (LMArena coding leaderboard).
muse-spark-1.2: 5.4s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
muse-spark-1.1 accepts 1,000,000 and muse-spark-1.2 accepts 1,000,000 input tokens.
muse-spark-1.1 at 183.7 tok/s and muse-spark-1.2 at 138.3 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
muse-spark-1.1 accepts text, image, audio and video input and supports thinking and tool calling; muse-spark-1.2 accepts text, image, audio and video input and supports thinking and tool calling.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix