QuickSilver Pro system status
Services
Model availability
deepseek-v4-flashdeepseek-v4-proqwen3.8-maxqwen3.7-maxqwen3.7-plusqwen3.7-flashqwen3.6-plusqwen3.6-35bkimi-k2.6kimi-k2.7-codekimi-k3muse-spark-1.2muse-glimmer-30bglm-5.3glm-5.2nemotron-3.5-lightninggpt-5.6-lunagpt-5.6-terragpt-5.6-solgrok-4.5grok-4.6minimax-m3mimo-v2.5hy3claude-opus-5claude-fable-5claude-opus-4-8claude-opus-4-6claude-sonnet-4-6claude-sonnet-5claude-haiku-4-5gemini-3.7-flashgemini-3.6-flashgemini-3.5-flash-litegemini-3.5-flashgemini-3.1-pro-previewgemini-3-pro-imagegemini-3-flash-previewgemini-3.1-flash-liteflux.2-proRoadmap - how we become a real inference company
Now - launched on a curated catalog
LiveCustomers save 20% today on a curated catalog at low list prices. The narrow operational surface is what keeps the gap honest, and the same surface scales straight into Phase 2.
Q2 2026 - our own inference stack on H100/H200
PlannedSelf-hosted serving on dedicated GPUs using SGLang + continuous batching, EAGLE-3 speculative decoding, FP8 quantization via DeepGEMM, and SageAttention / ThunderMLA custom kernels. At that point system_fingerprint becomes stable (it changes only when we rev the stack), and repeatable-seed workflows start working properly. Target: 30-50% below current prices on the DeepSeek V4 wave.
H2 2026 - colocated data center + AIDC partnerships
FutureMove from rented (Vast.ai) to self-owned or colocated racks. Partner with AI-datacenter operators where that makes sense. The goal is the lowest-cost reliable inference for open-source models on the planet - full stack, our engineering.
About this page
Service rows run client-side probes from your browser. Model rows reflect a real 1-token probe sent server-side every 3 minutes from our backend. Historical bars show the results of recent probes stored in this browser's localStorage; cleared if you switch devices.
Public uptime tracking began 2026-04-16. For a contractual SLA and third-party-monitored history, contact us.