Model
Muse Spark 1.1
Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.
8 providersreleased closed weights
$1.25
best input /M · NanoGPT
$4.25
best output /M
1M
context window
32K
max output
Compare providers (sorted by listed input price)
| Provider | Input /M | Output /M | Cache read /M | Cache write /M | Context | Capabilities | Status | Updated |
|---|---|---|---|---|---|---|---|---|
| NanoGPT meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1M | reasoningno toolsno structuredvision | Jul 9, 2026 | |
| Meta muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| OpenRouter meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| LLM Gateway meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Merge Gateway meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1.05M | reasoningtoolsno structuredvision | Jul 9, 2026 | |
| Vercel AI Gateway meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1.05M | reasoningtoolsstructuredno vision | Jul 9, 2026 | |
| Kilo Gateway meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | — | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 | |
| Pioneer meta/muse-spark-1.1 | $1.25 | $4.25 | $0.15 | $1.25 | 1.05M | reasoningtoolsstructuredvision | Jul 9, 2026 |
Price badge
https://models.sutraworks.ai/badge/meta/muse-spark-1.1.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Benchmarks
- SWE-Bench Pro ↗(resolve rate)report ↗61.5
- Terminal-Bench ↗(success rate)report ↗80
- DeepSWE(resolve rate)report ↗53.3
- MCP Atlas(success rate)report ↗88.1
- JobBench(success rate)report ↗54.7
- Toolathlon-Verified(success rate)report ↗75.6
- Humanity's Last Exam ↗(accuracy)report ↗62.1
- OSWorld-Verified ↗(success rate)report ↗80.8
- Finance Agent(accuracy)report ↗57.2
- CharXiv Reasoning(accuracy)report ↗88.4
- BabyVision(accuracy)report ↗76.3
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.