We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Cloudflare: Clef Omni
cloudflare/clef-omniTry Cloudflare: Clef Omni now
Runs on your balance at the prices above. New accounts start with free usage.
Results will appear here.
Settings
Cloudflare: Clef Omni at a glance
- Input price is 257% higher than the median of 25 Decisions models.
- Context window of 65,536 tokens, enough for long documents and multi-turn conversations.
- A typical request (1,000 input / 500 output tokens) costs about $0.000525.
About Cloudflare: Clef Omni
Cloudflare: Clef Omni is a decision model from Cloudflare, and it is the mixture-of-experts member of Cloudflare's open-source Clef decision model family. It is a fine-tune of Qwen3-Omni-30B-A3B, which means 30B total parameters with 3B active parameters, and it is served on Workers AI. Cloudflare released it on 2026-10-09.
The model accepts text and images as input, and its output modality is decisions. Its context window is 65,536 tokens, with a maximum output of 58,982 tokens. Because it is built on a mixture-of-experts architecture, only a fraction of the total parameters are active on each pass, which is the defining structural trait of this member of the Clef family.
The practical uses follow from that shape. If your application needs to take text, or text together with an image, and turn it into a decision rather than a free-form answer, this is the kind of model to evaluate. Routing, classification, gating, and similar decision steps are the natural fit, including cases where the input includes a screenshot or another image alongside the text. The 65,536 token context gives you room for substantial input before the decision is produced.
You call it through api14's OpenAI-compatible API using the model id "cloudflare/clef-omni". Because the API is OpenAI-compatible, you can point an existing OpenAI client at api14 and send the same style of request, with the model field set to that id. The model supports no request parameters beyond the basics, so keep your request simple and do not rely on optional knobs such as temperature, top_p, or similar controls being honored.
One thing to weigh before adopting it: the output is a decision, not prose. If you need generated text, a chat response, or another generative output, a model with a text output modality will fit better. The supported parameter list is empty, so if your workflow depends on tuning sampling behavior, this model will not accommodate that. Within those bounds, it is a focused option for text and image inputs that resolve to a decision.
How to call the Cloudflare: Clef Omni API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "cloudflare/clef-omni".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.post("/decisions", { body: {
"model": "cloudflare/clef-omni",
"state": "Customer: I was charged twice for my order and want my money back.",
"questions": {
"team": {
"type": "choice",
"instructions": "Which team should handle this message?",
"criteria": {
"billing": "Payments, refunds, invoices",
"support": "Product questions and bugs",
"sales": "Pricing and new purchases"
}
},
"urgent": {
"type": "noul",
"instructions": "Does this need a reply today?",
"criteria": {
"true": "Money, outage or legal risk",
"false": "Can wait"
}
}
}
} });
console.log(result.answers);
Specifications
- Context length
- 65,536
- Max output
- 58,982
- Input
- text, image, audio, video
- Output
- decisions
Requests on api14 · last 7 days
Cloudflare: Clef Omni: frequently asked questions
- How much does the Cloudflare: Clef Omni API cost?
- Cloudflare: Clef Omni costs Input $0.52 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Cloudflare: Clef Omni?
- Cloudflare: Clef Omni reads up to 65,536 tokens per request: prompt, history and documents together. It writes up to 58,982 output tokens per response.
- What can Cloudflare: Clef Omni do?
- Cloudflare: Clef Omni accepts text, image, audio, video and returns decisions.
- How do I call Cloudflare: Clef Omni from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "cloudflare/clef-omni". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Cloudflare: Clef Omni?
- Comparable Decisions models at a similar price: Upstage: Solar Decide Flash, OpenAI: GPT-6 Luna Decisions, Upstage: Solar Decide. Each runs through the same API key, so switching is one string.
Cloudflare: Clef Omni community
New topicThis community has no topics yet. Open the first one about Cloudflare: Clef Omni.