ModelsPublished All news from that day
Ongoing case: Frontier model API prices Price change · 12 stories
Cloudflare released Clef-omni, which takes audio and video, and cut Clef-flash to $0.038 per million input tokens.
A week after releasing Clef and Clef-flash, Cloudflare released Clef-omni for audio, video, image and text input, and cut the price of Clef-flash while reducing its hosted context window.
Check our sources · 10 facts from 1 sourceCloudflare published a post on 9 October 2026 about its Clef models, a week after it released Clef and Clef-flash. The new model, Clef-omni, takes audio (wav or mp3) and video (mp4 or webm) alongside text and images. Cloudflare says it built Clef-omni on a Qwen3-Omni-30B-A3B-Instruct mixture-of-experts model and released the weights on Hugging Face.
Cloudflare lists these prices per million input tokens: Clef-flash $0.038, down from $0.09; Clef $0.24, unchanged; and Clef-omni $0.15. To make the Clef-flash price possible, Cloudflare cut the hosted model's context window to 24k from the 64k it had advertised.
It says the weights on Hugging Face are untouched and were trained to support 256k tokens for self-hosting. Cloudflare says only 0.24% of requests exceeded 24k input tokens.
Cloudflare also says the hosted Clef is faster, with median speedups of 1.7 to 2.0 times depending on input size, from changes to its serving infrastructure rather than the weights. For Clef-omni it reports median latency of about 130 ms for text-only decisions and about 150 ms for images, which are its own figures.
Your reaction
We count reactions per story and day, never who reacted. The counts help us choose what goes in the monthly issue. If you are signed in, your own page shows yours too.
We count reactions per story and day, never who reacted. They help choose what goes in the monthly issue.
Check our sources
Every sentence above is checked against this source.
1 Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
Open the source archived copy-
Cloudflare's blog post introducing Clef-omni carries the publication date 2026-10-09.
cite"datePublished":"2026-10-09T18:27:34.129Z"
-
Cloudflare says: "Today, we’re releasing Clef-omni, which takes in audio and video input alongside text and image." It names audio as wav or mp3 and video as mp4 or webm.
citeToday, we’re releasing Clef-omni, which takes in audio and video input alongside text and image. ... audio (wav or mp3) and video (mp4 or webm)
-
Cloudflare says it released the Clef-omni weights on Hugging Face, and that it built the model on a Qwen3-Omni-30B-A3B-Instruct mixture-of-experts (MoE) foundation.
citeWe also released the model open-weights on HuggingFace. ... We built this on a Qwen3-Omni-30B-A3B-Instruct mixture-of-experts (MoE) foundation
-
Cloudflare lists: "Clef-flash – originally $0.09 per M input tokens, now $0.038 per M input tokens", "Clef – remains at $0.24 per M input tokens" and "Clef-omni – launched today at $0.15 per M input tokens".
citeoriginally $0.09 per M input tokens, now $0.038 per M input tokens ... remains at $0.24 per M input tokens ... launched today at $0.15 per M input tokens
-
Cloudflare says: "The hosted version of Clef-flash now has a context window of 24k, instead of 64k as previously advertised."
citeThe hosted version of Clef-flash now has a context window of 24k, instead of 64k as previously advertised.
-
Cloudflare says the model weights on Hugging Face are untouched and "were trained to support a 256k context window should you choose to self-host it".
citewere trained to support a 256k context window should you choose to self-host it.
-
Cloudflare says: "From our usage data, we see that only 0.24% of requests exceed 24k input tokens."
citeonly 0.24% of requests exceed 24k input tokens
-
Cloudflare reports median speedups for the hosted Clef of 1.7x for about 800 tokens, 2.0x for about 3,400 tokens and 1.7x for about 16,000 tokens, and says "most of the optimizations we made are at the serving infrastructure layer".
citeMedian speedup 1.7× (~800 tokens), 2.0× (~3,400 tokens), 1.7× (~16,000 tokens) ... most of the optimizations we made are at the serving infrastructure layer
-
Cloudflare says: "Text-only decisions return in about 130 ms at the median, image inputs in about 150 ms, and audio clips in a few hundred milliseconds."
citeText-only decisions return in about 130 ms at the median, image inputs in about 150 ms, and audio clips in a few hundred milliseconds.
-
Cloudflare says the post follows last week’s release of Clef and Clef-flash.
Toned down to what the source says
citeFollowing last week’s release of Clef and Clef-flash
Every sentence above is checked against this source. Each fact has its own address you can cite.
Source 1 · Cloudflare · 9 Oct 2026
Introducing Clef-omni with full multimodality, plus a faster Clef and a cheaper Clef-flash
Cloudflare's blog post introducing Clef-omni carries the publication date 2026-10-09.
"datePublished":"2026-10-09T18:27:34.129Z"
Cloudflare says: "Today, we’re releasing Clef-omni, which takes in audio and video input alongside text and image." It names audio as wav or mp3 and video as mp4 or webm.
Today, we’re releasing Clef-omni, which takes in audio and video input alongside text and image. ... audio (wav or mp3) and video (mp4 or webm)
Cloudflare says it released the Clef-omni weights on Hugging Face, and that it built the model on a Qwen3-Omni-30B-A3B-Instruct mixture-of-experts (MoE) foundation.
We also released the model open-weights on HuggingFace. ... We built this on a Qwen3-Omni-30B-A3B-Instruct mixture-of-experts (MoE) foundation
Show all 10 factsShow fewer facts
Cloudflare lists: "Clef-flash – originally $0.09 per M input tokens, now $0.038 per M input tokens", "Clef – remains at $0.24 per M input tokens" and "Clef-omni – launched today at $0.15 per M input tokens".
originally $0.09 per M input tokens, now $0.038 per M input tokens ... remains at $0.24 per M input tokens ... launched today at $0.15 per M input tokens
Cloudflare says: "The hosted version of Clef-flash now has a context window of 24k, instead of 64k as previously advertised."
The hosted version of Clef-flash now has a context window of 24k, instead of 64k as previously advertised.
Cloudflare says the model weights on Hugging Face are untouched and "were trained to support a 256k context window should you choose to self-host it".
were trained to support a 256k context window should you choose to self-host it.
Cloudflare says: "From our usage data, we see that only 0.24% of requests exceed 24k input tokens."
only 0.24% of requests exceed 24k input tokens
Cloudflare reports median speedups for the hosted Clef of 1.7x for about 800 tokens, 2.0x for about 3,400 tokens and 1.7x for about 16,000 tokens, and says "most of the optimizations we made are at the serving infrastructure layer".
Median speedup 1.7× (~800 tokens), 2.0× (~3,400 tokens), 1.7× (~16,000 tokens) ... most of the optimizations we made are at the serving infrastructure layer
Cloudflare says: "Text-only decisions return in about 130 ms at the median, image inputs in about 150 ms, and audio clips in a few hundred milliseconds."
Text-only decisions return in about 130 ms at the median, image inputs in about 150 ms, and audio clips in a few hundred milliseconds.
Cloudflare says the post follows last week’s release of Clef and Clef-flash.
Toned down to what the source saysFollowing last week’s release of Clef and Clef-flash
Topics
The morning email
On the mornings we publish: the three top stories and up to four short ones. Free.
We email you a link to confirm. An issue may include one sponsor, always labelled Sponsored · Advertisement. Our emails count opens and clicks, not who made them. Unsubscribe in one click. What we keep