Modaic launches decision-model training at $0.75/1M tokens with 2.69x vLLM throughput
code_star · x · 2026-11-18
Modaic launched as "Tinker for decision models": train decision models that hit the frontier for your task, then serve them fast.
Key specs:
- Prefill-optimized inference: 2.69x vLLM's throughput at 1/3 the latency
- Training from $0.75/1M tokens; serverless inference from $0.04/1M tokens
- API, MCP, and CLI interfaces for coding agents
Aimed at teams that need task-specific decision models with fast serving; the MCP/coding-agent integration is the notable hook.
More from coding & agent
- Preambient launches autonomous investment bank: 4x faster deals at half the fees — alifcoder · 2026-11-18
- Stanford's CS329Z Agentic AI Course Is Free on YouTube, Covers DSPy — stanfordnlp · 2026-11-18
- Tier your agents: Opus for planning, Sonnet for features, Haiku for simple tasks — Zachly · 2026-11-18
- Microsoft launches AI Transparency Initiative with 40+ orgs; Perception security platform goes GA — satyanadella · 2026-11-18
- Microsoft launches Agent 365 Business Analytics, an 'ERP for AI' spend — satyanadella · 2026-11-18
- Microsoft Perception goes GA: red, blue, and green security agents at machine speed — satyanadella · 2026-11-18