Muse Spark Open
by Venice AI · family muse · listed Oct 2026RTVW
Multimodal reasoning model for visual analysis, planning, and tool use
Current rates USD per 1M tokens
Input$1.56
Output$5.31
Cache read$0.188
Cache write—
Against the market
On the record
- Model id
muse-spark-open- Context window
- 1.0M tokens
- Max output
- 131K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- Jan 2026
- Released
- 2026-10-15
- Last updated
- 2026-10-15
- Provider docs
- docs.venice.ai
Back of the envelope
≈
Also listed at
- Cloudflare AI Gateway$1.25 in · $4.25 out
- Prime Inference$1.25 in · $4.25 out
- Ollama Cloud$1.25 in · $4.25 out
- ai&$1.25 in · $4.25 out
- Fireworks AI$1.25 in · $4.25 out
- NanoGPT$1.25 in · $4.25 out
- Kilo Gateway$1.25 in · $4.25 out
- Eden AI$1.25 in · $4.25 out
- Requesty$1.25 in · $4.25 out
- Nebius Token Factory$1.25 in · $4.25 out
- Vercel AI Gateway$1.25 in · $4.25 out
- OpenRouter$1.25 in · $4.25 out
- Merge Gateway$1.25 in · $4.25 out
- Charm Hyper$1.40 in · $4.65 out