Decision Model Tracker

Last updated 16 Nov 2026. Sources last checked 16 Nov 2026.

All models · First seen 1 Oct 2026

Clef-flash

Cloudflare · Released 1 Oct 2026

Get the APIDiscuss on X

Latency-focused sibling of Clef for faster, lower-cost decisions. Open-weight, Jev-API compatible, and hosted on Workers AI.

Maker
Cloudflare
Release date
1 Oct 2026
First seen
1 Oct 2026
Access
Workers AI; open weights on Hugging Face.
Pricing (as publicly stated)
As stated in Cloudflare's 9 Oct 2026 post: $0.038 per million input tokens, down from the earlier $0.09 rate. The hosted context window was reduced to 24k tokens as part of that price cut; Hugging Face weights were trained to support a larger window for self-hosting. See Cloudflare's developer docs for current rates.
Modalities
text
Question types
noul, choice, score
Latency (as stated)
In Cloudflare's 1 Oct 2026 launch benchmarks, Clef-flash's median latency was listed as 38.8 ms (p95 122.4 ms).
Official announcement
https://blog.cloudflare.com/clef-decision-models/

Benchmark claims

These are claims as published by the maker or in the linked official post. This catalog has not independently rerun every benchmark.

Cloudflare published launch scores for Clef-flash alongside Clef and Jev, and later said Clef-flash remains performant at the lower price.

Source: https://blog.cloudflare.com/clef-decision-models/

Pricing source: Cloudflare's 9 Oct 2026 post lists Clef-flash at $0.038 per million input tokens, originally $0.09, with the hosted context window reduced to 24k tokens.

Source: https://blog.cloudflare.com/clef-faster-cheaper-multimodal/

What enterprises should know

Cost and pricing

As stated in Cloudflare's 9 Oct 2026 post: $0.038 per million input tokens, down from the earlier $0.09 rate. The hosted context window was reduced to 24k tokens as part of that price cut; Hugging Face weights were trained to support a larger window for self-hosting. See Cloudflare's developer docs for current rates. Figures are what the maker stated in the linked source and may have changed.

Source: https://blog.cloudflare.com/clef-faster-cheaper-multimodal/

Lock-in

The official announcement describes distribution as follows: Workers AI; open weights on Hugging Face. That is the maker's description of how the product is obtained, not an assessment of switching costs.

Source: https://blog.cloudflare.com/clef-decision-models/

Security and privacy

The official announcement we sourced did not state a specific security certification or independent privacy audit for this product. If you use a hosted endpoint named in the announcement, inputs are sent to that host under the host's own terms.

Source: https://blog.cloudflare.com/clef-decision-models/

Maturity and availability

The maker's official announcement is dated 2026-10-01. Access was described as: Workers AI; open weights on Hugging Face. In Cloudflare's 1 Oct 2026 launch benchmarks, Clef-flash's median latency was listed as 38.8 ms (p95 122.4 ms).

Source: https://blog.cloudflare.com/clef-decision-models/

Compliance notes

The official announcement we sourced did not state a specific regulatory approval or compliance certification for this product.

Source: https://blog.cloudflare.com/clef-decision-models/

What consumers should know

Cost and pricing

The announcement describes a way to obtain or run the model (including, where stated, open weights or self-hosting). Hosted prices, if any, are as follows: As stated in Cloudflare's 9 Oct 2026 post: $0.038 per million input tokens, down from the earlier $0.09 rate. The hosted context window was reduced to 24k tokens as part of that price cut; Hugging Face weights were trained to support a larger window for self-hosting. See Cloudflare's developer docs for current rates.

Source: https://blog.cloudflare.com/clef-faster-cheaper-multimodal/

Lock-in

The announcement describes access as: Workers AI; open weights on Hugging Face. Self-hosting, where it is offered, means you are not limited to the maker's hosted endpoint, but you still depend on the published weights, license, and your own hardware.

Source: https://blog.cloudflare.com/clef-decision-models/

Security and privacy

The announcement describes both a hosted endpoint and a way to obtain weights for local use. Inputs sent to a hosted endpoint go to that host; inputs processed only on your own machine stay on that machine. The announcement we sourced did not state a product-specific consumer privacy audit.

Source: https://blog.cloudflare.com/clef-decision-models/

Maturity and availability

The official announcement is dated 2026-10-01. Availability was described as: Workers AI; open weights on Hugging Face. In Cloudflare's 1 Oct 2026 launch benchmarks, Clef-flash's median latency was listed as 38.8 ms (p95 122.4 ms). This summary does not say whether the product is suitable for a particular consumer task.

Source: https://blog.cloudflare.com/clef-decision-models/

Compliance notes

The official announcement we sourced did not state consumer-protection certifications specific to this product.

Source: https://blog.cloudflare.com/clef-decision-models/

Figures are as stated in the linked source on the date shown. Sources last checked 16 Nov 2026. Names and marks belong to their owners. This page is an independent summary, not a product page from Cloudflare.