Meta: Muse Spark Open
meta/muse-spark-openMuse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers
Providers
5 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $1.25 | $4.25 | Variable | 1.05s | 94 tps | 99.88% | |
 Basetenfp4 | $1.25 | $4.25 | $0.15 | 0.39s | 215 tps | 99.67% |
| $1.25 | $4.25 | $0.15 | 0.99s | 26 tps | 99.48% | |
| $1.25 | $4.25 | $0.15 | 5.78s | 42 tps | 98.56% | |
 Fireworks | $1.25 | $4.25 | $0.15 | 2.60s | 58 tps | 87.45% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Muse Spark Open in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Muse Spark Open costs pay-as-you-go elsewhere, not what you pay here.
Performance
Time to first token and output speed across every provider, over the last 3 days.
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Apps
Tools that most often run Muse Spark Open, by tokens this week.
Activity
75.3B tokens processed market-wide in the last month.
FAQ
Explore
Other models your pass can call.
