Muse Spark 1.1
Routed in Coreby Meta
One-million-token multimodal reasoning for everyday agent work.
Intelligence51Artificial Analysis Index
Average task cost$0.26Observed benchmark task
Cost per million$1.25 in$4.25 out
Output speed124tokens per second
Evidence
Open source What we know
- Availability
- Available through Core's model router
- Core fit
- 54 / 100 · Efficient
- Public intelligence
- 51 · xhigh effort
- Benchmark snapshot
- Jul 2026
- Input price
- $1.25 per 1M tokens
- Output price
- $4.25 per 1M tokens
- Cache read
- $0.15 per 1M tokens