Microsoft has released Decision-1, a decision model based on Qwen3.5-9B designed for classifications, evaluations, and routing decisions to guide agents through complex environments. According to the company, Decision-1 achieved top accuracy across 36 benchmarks covering nearly 150,000 questions and operated 2.5 times faster than runner-up H2O-Lightning-4B.

The model enters a crowded space initiated by startup Jev in mid-September, alongside competing models from OpenAI and Cloudflare. Decision-1 is available through Microsoft Foundry and OpenRouter at $0.042 per million input tokens, with free output tokens.

Why it matters

  • Specialized, small decision models built on open baselines are quickly commoditizing early startup concepts in agent routing.

  • Extremely low pricing lowers operational costs for enterprise teams deploying complex multi-agent orchestration architectures.

Source: the-decoder.com