Muse Spark 1.2 (xhigh)
AI model by Meta. Real-time pricing and benchmark data.
Benchmarks
Editorial Analysis
Profile. Muse Spark 1.2 (xhigh) is positioned in the mid-tier at $4.25/M output tokens. The benchmark profile is balanced — strongest on Coding Index (72.2) — making it a default choice for teams that need general-purpose reasoning without paying frontier-model prices.
Latency. On latency, Muse Spark 1.2 (xhigh) reports 234 tok/s output speed and 15760ms time-to-first-token. Output speed is in the normal range — most chat and completion applications will be token-bound, not streaming-bound.
Cost model. For a workload of 1M input tokens + 100K output tokens, Muse Spark 1.2 (xhigh) costs $1.68 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.
Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-09-06.
Compare with similar models
| Model | Input | Output | Speed |
|---|---|---|---|
Muse Spark 1.2 (xhigh)Current | $1.25 | $4.25 | 234 tok/s |
| Qwen3 14B (Reasoning) | $0.35 | $4.20 | 61 tok/s |
| o3-mini (high) | $1.10 | $4.40 | 237 tok/s |
| o3-mini | $1.10 | $4.40 | 203 tok/s |
| o4-mini (high) | $1.10 | $4.40 | 145 tok/s |
| GLM-5.1 (Non-reasoning) | $1.38 | $4.40 | 50 tok/s |