Last refreshed 2026-10-04. Next refresh: weekly.
Why use Clef-flash on Cloudflare Workers AI?
Cloudflare Workers AI offers Clef-flash with pay-as-you-go pricing at $0.09/1M input tokens. Cloudflare is a leading connectivity cloud company that provides a comprehensive suite of cloud-native products and developer tools to enhance web performance, security, and reliability.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: @cf/cloudflare/clef-flash@cf/cloudflare/clef-flashRequest example
@cf/cloudflare/clef-flash.Gotchas
- Use provider model ID "@cf/cloudflare/clef-flash", not the LLMReference slug "clef-flash".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.09 |
Capabilities
About Clef-flash
Clef-flash is Cloudflare's 9B open-weight multimodal decision model, the fast sibling of Clef, released 2026-10-01 by the Workers AI team. Post-trained from Qwen3.5-9B (not Qwen3.8): the backbone is frozen, and a joint schema head is trained alongside rank-256 LoRA adapters with label-smoothed cross-entropy, a Brier calibration loss, and RLCD. It reads a state (text, JSON, or images) and up to 64 typed questions (noul, choice, or score) and returns a probability for every allowed option in one non-autoregressive pass, with no free-form text generation.