Using Clef-omni on Cloudflare Workers AI

Implementation guide · Clef · Cloudflare

ServerlessOpen Source

Cloudflare Workers AI exposes Clef-omni through model ID @cf/cloudflare/clef-omni. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-10. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Cloudflare Workers AI and generate an API key.
  2. 2
    Use the Cloudflare Workers AI SDK or REST API to call @cf/cloudflare/clef-omni — see the documentation for request format.
  3. 3
    You'll be billed $0.15/1M input, Free/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Cloudflare Workers AI documentation for integration details.

Pricing on Cloudflare Workers AI

TypePrice (per 1M)
Input tokens$0.15
Output tokensFree

Capabilities

VisionMultimodalStructured OutputsAudio

About Clef-omni

Clef-omni is Cloudflare's open-weight omni-modal decision model, released 2026-10-09 as the third member of the Clef family. It is post-trained from Qwen3-Omni-30B-A3B-Instruct, a 30B-parameter mixture-of-experts backbone with 3B active parameters: Cloudflare keeps the thinker with its vision and audio encoders, does not use the speech-output components, freezes the backbone, and trains LoRA adapters plus a joint schema head with label-smoothed cross-entropy and Brier calibration.

Full model details →

Model Specs

Released2026-10-09
Parameters30B total / 3B active
Context64K
ArchitectureMixture of Experts

More Models on Cloudflare Workers AI

ClefClef-flash
All models on Cloudflare Workers AI →

Provider

Cloudflare Workers AI

Cloudflare

San Francisco, California, United States