Morph launches Reflex: first decision model with cached pricing, 10-20x cheaper than Jev
GabGarrett · x · 2026-11-05
morphllm launched Reflex, a 27B decision model built on Qwen 3.5, billed as the first decision model with cached pricing, available on their Model APIs and OpenRouter.
- Pricing: $0.042/M input tokens on the first request, $0.008/M for subsequent cached requests
- 10-20x cheaper than Jev, similar intelligence to leading decision models
- Example use case: support-ticket classification, where one ticket needs many questions answered (department? urgent? angry? refund? spam?) — caching means paying the premium once
The author argues cached pricing makes small specialized classification models obsolete and is the tipping point for decision-model economics.
More from Models
- New open-source American LLM pretrained from scratch teased, drawing AI community buzz — annadgoldie · 2026-11-05
- OpenAI October dev roundup: Decisions API, 12-hour caching, 8x faster Codex tokens — OpenAIDevs · 2026-11-05
- Researcher laments the enormous cost of RL used to squash models' quirky behaviors — generativist · 2026-11-05
- Gemini 4 C arbon one-shots 4,000-line demo, users say Google fixed model laziness — theREALmarvin · 2026-11-05
- DeepSeek alone handled 53% of OpenRouter's 27T daily tokens; open-weights labs top 75% — Comfortable-Rock-498 · 2026-11-05
- User screenshot shows ChatGPT desktop offering mystery models like 6 Luna and 5.6 Terra — flowersslop · 2026-11-05