Muse Spark Open
Muse Spark Open is Meta's language model with a 1.0M context window and up to 944K output tokens, available from 5 providers, starting at $1.25 / 1M input and $4.25 / 1M output. An open-weights reasoning model from Meta for coding and agentic workflows, supporting tool calling and native image understanding via a sparse Mixture-of-Experts architecture.
| Benchmarks | |
|---|---|
| Intelligence Index | #37 |
| GPQA | #59 |
| HLE | #26 |
| Time to First Token | #377 |
| SciCode | #16 |
| LCR | #66 |
| Output TPS | #122 |
Capabilities
Input4/5
Text✓
Image✓
Audio✓
Video✓
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | ||
|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Cache Read $ / 1M | |
| $1.25 | $4.25 | $0.15 | |
| $1.25 | $4.25 | $0.15 | |
| $1.25 | $4.25 | N/A | |
| $1.25 | $4.25 | $0.15 | |
| $1.25 | $4.25 | $0.15 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Muse Spark Open, ranked by cheapest on-demand price. The model needs about 1973 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region |
|---|---|---|---|---|---|
| p6-b300.48xlarge |  AWS | 8× B300 | 2149 GB | $142.42/hr |
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Muse Spark Open | 1.0M | $1.25 | $4.25 | Current | |
| Muse Spark Open 816B-A42B NVFP4 | — | — | — | — | Available |