On 9 October, a week after the first Clef models, Cloudflare released Clef-omni with open weights: text, image, audio and video in one call. Clef-flash falls from $0.09 to $0.038 per million input tokens, but its hosted version now takes up to 24k tokens instead of 64k.
- 9 October 2026: Cloudflare released Clef-omni, a decision model that takes audio (wav, mp3) and video (mp4, webm) together with text and images in a single request. The weights are open on Hugging Face, the price is $0.15 per million input tokens.
- Clef-flash gets cheaper, from $0.09 to $0.038 per million input tokens, which Cloudflare calls cheaper than Jev. The hosted version, however, now takes up to 24k input tokens instead of 64k; according to Cloudflare, only 0.24% of requests exceed 24k.
- Clef stays at $0.24 and 64k, but it is faster: median latency drops 1.7 to 2 times, and one of the optimisations is the move to SGLang. There are no new weights for it.
Decided on a Friday evening, trained over the weekend, launched on Thursday. That is how Cloudflare tells the story of how Clef, its first decision models, came together in its new post. A week after the launch come three changes, all in one post.
The two changes you will feel are in the input, and they go in opposite directions: Clef-omni takes more kinds of input, and Clef-flash takes shorter input.
Until now a decision on a call recording has gone through two models: one turns the sound into text, the other decides on the text. Clef-omni does both in one call, without transcribing the sound into text. Cloudflare's example is an installation check: a photo of the unit, a recording of it running and a video of the fan, plus three yes or no questions - whether the serial number label is visible, whether the unit sounds smooth and whether the fan is running.
Now the other direction. Clef-flash falls from $0.09 to $0.038 per million input tokens. Cloudflare calls it cheaper than Jev, and the arithmetic holds: $0.038 against $0.042, the price TypeSafe announced for Jev in September. The discount, however, is paid for in context. The hosted Clef-flash now reads up to 24k input tokens instead of the 64k Cloudflare advertised a week ago.
If you are among those 0.24% of requests over 24k, Cloudflare itself advises you to switch to Clef, which stays at 64k and at $0.24. The two 0.24s are at least easy to remember. There is a third way too: the Clef-flash weights on Hugging Face are untouched and hold up to 256k when self-hosted. The ceiling applies only to the hosted version.
If you send call recordings to a model that turns them into text only to decide something about them, Clef-omni deserves a test. If you send long contracts to Clef-flash, the new price is not for you: above 24k the hosted version is no longer enough.