MetaAPI Host BenchmarksEstimated
Muse Spark 1.1 — API Providers & Speed Matrix
Modelled throughput, TTFT latency and prompt-cache pricing estimates across cloud hosting endpoints, derived from official list prices and public benchmarks.
Muse Spark 1.1 is a proprietary model served through Meta's official API. Third-party hosting is not available — the matrix below covers the official endpoint only. See the Meta provider page for details.
Fastest provider
208 t/s
Lowest latency (TTFT)
2.47 s P50
Best price
$1.25 / $4.25
Blended Pricing Workload Calculator
Switch between standard conversational ratios, agentic caching loops, and heavy RAG workloads.
| Provider & Host | Hardware Stack | Output Speed (TPS) | Latency TTFT (P50) | Input Price ($/1M) | Output Price ($/1M) | Cache Read ($/1M) | Blended Price ($/1M) | SLA |
|---|---|---|---|---|---|---|---|---|
MetaOfficial | Official cloud API | 208 t/s | 2.47 s (3.46 s p90) | $1.25 | $4.25 | $0.125 | $2 | 99.99% |
Figures are modelled estimates based on published list prices and public throughput benchmarks — not measured on live endpoints. Verify current pricing and terms with each host before committing.