Cloudflare's Clef decision models hit OpenRouter: calibrated probabilities in one forward pass
michellechen · x · 2026-10-10
Cloudflare's open-source Clef decision model family is now served on OpenRouter:
- Clef Omni: a MoE fine-tune of Qwen3-Omni-30B-A3B (30B total, 3B active) handling text, JSON and images at $0.15/M input tokens.
- Clef Flash: a fast 9B fine-tune of Qwen3.5-9B at $0.038/M input; note Workers AI truncates long text to 2K tokens.
- Clef: a 27B multimodal model fine-tuned from Qwen3.8-27B.
Instead of generating tokens, these models take a state plus a schema of typed questions and return calibrated probabilities for every allowed option in a single forward pass — aimed at classification, routing, scoring, and guardrails, all with 66K context.
More from Models
- Only 7% of training compute goes to pretraining? repligate probes what the figure means — repligate · 2026-10-10
- New GPT Memory Consolidation Model 'Memory4 Dream' Appears, Appears Built on GPT-6 Luna — lyraxana · 2026-10-10
- Grok Bot now acts as an autonomous X research analyst with daily briefings — FinanceYF5 · 2026-10-10
- Doctors Are Building Board-Style Exams for Medical AI, Starting with Radiology's Last Exam — DrDatta_AIIMS · 2026-10-10
- AI roundup: OpenAI tops 700 math papers, Mistral ships Le Chonk open model — FinanceYF5 · 2026-10-10
- Notes from an NYC AI dinner: agents find most inference perf wins, code review deemed unproductive — paulnovosad · 2026-10-10