- Cloudflare-hosted
- Vision
Clef-omni is a multimodal decision model built on a 30B-parameter mixture-of-experts (3B active) backbone. It turns a state and a schema of typed questions into decisions, reads the state as text, JSON, images, audio, or video, and returns a probability for every allowed option of every question.
| Model Info | |
|---|---|
| Context Window ↗ | 64,000 tokens |
| Terms and License | link ↗ |
| More information | link ↗ |
| Vision | Yes |
| Unit Pricing | $0.15 per M input tokens |
export interface Env {
AI: Ai;
}
export default {
async fetch(request, env): Promise<Response> {
const response = await env.AI.run("@cf/cloudflare/clef-omni", {
model: "clef-omni",
state: "Checkout has been failing for every customer for the last hour.",
questions: {
urgent: {
type: "noul",
instructions: "Is this support request urgent?",
},
team: {
type: "choice",
instructions: "Which team should handle this request?",
criteria: {
billing: "Payments, invoices, and refunds",
technical: "Outages, errors, and configuration",
sales: "Plans and upgrades",
},
},
severity: {
type: "score",
instructions: "How severe is the customer impact?",
criteria: ["No impact", "Minor", "Major", "Critical"],
},
},
});
// response.answers.urgent -> probability the request is urgent
// response.answers.team -> chosen team with per-option probabilities
// response.answers.severity -> probability-weighted score (0 = lowest level)
return Response.json(response);
},
} satisfies ExportedHandler<Env>;
import os
import requests
ACCOUNT_ID = "your-account-id"
AUTH_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")
response = requests.post(
f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/cloudflare/clef-omni",
headers={"Authorization": f"Bearer {AUTH_TOKEN}"},
json={
"model": "clef-omni",
"state": "Checkout has been failing for every customer for the last hour.",
"questions": {
"urgent": {
"type": "noul",
"instructions": "Is this support request urgent?",
},
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"billing": "Payments, invoices, and refunds",
"technical": "Outages, errors, and configuration",
"sales": "Plans and upgrades",
},
},
"severity": {
"type": "score",
"instructions": "How severe is the customer impact?",
"criteria": ["No impact", "Minor", "Major", "Critical"],
},
},
},
)
print(response.json())
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/cloudflare/clef-omni \
-X POST \
-H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN" \
-d '{
"model": "clef-omni",
"state": "Checkout has been failing for every customer for the last hour.",
"questions": {
"urgent": { "type": "noul", "instructions": "Is this support request urgent?" },
"team": {
"type": "choice",
"instructions": "Which team should handle this request?",
"criteria": {
"billing": "Payments, invoices, and refunds",
"technical": "Outages, errors, and configuration",
"sales": "Plans and upgrades"
}
},
"severity": {
"type": "score",
"instructions": "How severe is the customer impact?",
"criteria": ["No impact", "Minor", "Major", "Critical"]
}
}
}'model
stringrequireddefault: clef-omnipattern: ^\s*clef-omni\s*$Required. The model selector: "clef-omni" for @cf/cloudflare/clef-omni.state
▶questions{}
objectrequiredminProperties: 1maxProperties: 64Map of question id to a typed question (noul, choice, or score). 1 to 64 questions; ids may use letters, digits, '_', '.', '-' (max 100 chars). Answers are returned under the same ids.▶images[]
arraymaxItems: 4Clef extension to the System One API. Optional embedded PNG, JPEG, or WebP images placed before the state (max 4; 4 MiB and 16 megapixels each, 8 MiB total decoded). Each image costs 64 to 1,024 input tokens. Remote URLs are not accepted.▶audio[]
arraymaxItems: 4Clef-Omni extension. Optional embedded audio clips (max 4; 8 MiB and 300 seconds each). Audio and video clips together may total at most 16 MiB decoded. Remote URLs are not accepted.▶videos[]
arraymaxItems: 2Clef-Omni extension. Optional embedded videos (max 2; 16 MiB and 60 seconds each), sampled at 2 frames per second. A video's soundtrack is heard with its frames when every video in the request has one. Audio and video clips together may total at most 16 MiB decoded. Each second of video costs up to 256 input tokens. Remote URLs are not accepted.model
stringThe model that performed the evaluation.▶answers{}
objectOne answer per question, keyed by the question ids from the request.▶usage{}
object