Decision Models launches P2P decision API returning option probabilities, 2.6x throughput
airesearch12 · x · 2026-10-15
Decision Models launched a "decision API" for routing tickets, approving actions, and scoring drafts — returning one answer per option with probabilities instead of free-form text. Key facts:
- One API covers s1-fast, s1-pro and s1-vision, with an EU tier built for GDPR/EU AI Act compliance.
- Self-measured Oct 11–12: s1-pro delivers 2.6x the throughput of its reference server on the same GPU; Quyet-1.0-Large hits 4.5x.
- s1-fast is priced under half of Jev's rate ("Jev-compatible"); the GLOBAL tier runs peer-to-peer inference on spare EU capacity first, then rented GPUs from independent providers who can see request content in clear text (opt-in only).
- The s1-pro model, vLLM-SR d3, tops the community Decision Index 0.3.2 board at 66.26.
The subnet was funded by @constreborn; the author comes from the Bittensor/chutes ecosystem, pitching decentralized, community-served inference.
More from coding & agent
- Grady Booch: Removing bottlenecks just yields more code, not more value — Grady_Booch · 2026-10-15
- Cloudflare's Clef decision models land on Merge Gateway with 39ms median latency — shensi · 2026-10-15
- AI agent generates full CNC machining plan and G-code, veteran technician says it matches manual CAM — IgorCarron · 2026-10-15
- Claude Code Desktop Gets Major Update for Running Parallel Sessions — lydiahallie · 2026-10-15
- Debugging 3 bugs reveals what engineers are really worth in the AI era — rseroter · 2026-10-15
- Epic's vibe-coded launcher gets Community Noted over security risks — mark_k · 2026-10-15