{"slug": "new-model-available-cloudflare-clef-flash", "title": "New Model Available: Cloudflare: Clef Flash", "summary": "Cloudflare released Clef Flash, a 9B-parameter open-source decision model fine-tuned from Qwen3.5-9B and served on Workers AI, which returns a calibrated probability for every allowed option of every typed question in a single forward pass rather than generating tokens. The model accepts text or structured JSON state plus a schema of typed questions and is intended for low-latency classification, routing, scoring and guardrails through the Decisions API. Cloudflare notes that Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read, while images are counted separately.", "body_md": "Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of typed questions into decisions, returning a calibrated probability for every allowed option of every question in a single forward pass instead of generating tokens. Use it for low-latency classification, routing, scoring, and guardrails through the Decisions API. Note: Workers AI currently truncates long text state to roughly the first 2K tokens, so content beyond that is not read; images are counted separately.\n\n[Back to Models](https://zenmux.ai/models)\n\n## Providers\n\nRoute requests across multiple providers. Copy a provider slug to set your preference.\n\n## Uptime\n\n24hours\nDirect request success rate on AI Gateway and per-provider.\n\n## Latency\n\n24hours\nP50 whole response time on live AI Gateway traffic, in milliseconds.\n\n## Activity\n\nToken volume and request traffic to this model over time.\n\n## Benchmarks\n\nScores on standardized evaluations. Higher percentages are better — and rank percentile shows\n\nMetrics sourced from[Artificial Analysis](https://artificialanalysis.ai/)\n\n## Apps\n\nPublic apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for. [View All](https://zenmux.ai/analytics/apps)\n\n## Related Models\n\nMore models from [Cloudflare](https://zenmux.ai/cloudflare)", "url": "https://wpnews.pro/news/new-model-available-cloudflare-clef-flash", "canonical_source": "https://zenmux.ai/cloudflare/clef-flash", "published_at": "2026-10-28 10:58:33+00:00", "updated_at": "2026-10-31 00:18:09.817313+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-products", "ai-tools"], "entities": ["Cloudflare", "Clef Flash", "Qwen3.5-9B", "Workers AI", "Decisions API", "Artificial Analysis"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/new-model-available-cloudflare-clef-flash", "markdown": "https://wpnews.pro/news/new-model-available-cloudflare-clef-flash.md", "text": "https://wpnews.pro/news/new-model-available-cloudflare-clef-flash.txt", "jsonld": "https://wpnews.pro/news/new-model-available-cloudflare-clef-flash.jsonld"}}