Cloudflare: Clef Flash - API in Egypt, billed in EGP

Live
cloudflareclef-flash

Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus

Modality

Decision

Context window

66K tokens

Max output

59K tokens

Region

US

Published

04 Oct 2026

Pricing

Input

5.18

EGP per 1M tokens

Output

Free

EGP per 1M tokens

Monthly cost example

258.99 EGP

Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.

Use it via the API

Cloudflare: Clef Flash is a System One decision model: send a state and named, typed questions (yes/no, multiple choice, or score) and get one typed answer per question back. The endpoint is TypeSafe-compatible, so the TypeSafe SDK works with base URL https://dev-backend.sovereigneg.com. Read the System One guide.

Run inference

OpenAI-compatible — POST /v1/systemone — drop-in for any OpenAI SDK.

import httpx

response = httpx.post(
    "https://dev-backend.sovereigneg.com/v1/systemone",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model": "clef-flash",
        "state": "I paid for my order twice and it still has not arrived after a week.",
        "questions": {
            "refund": {
                "type": "noul",
                "instructions": "Is the customer asking for money back?",
            },
            "team": {
                "type": "choice",
                "instructions": "Which team should handle this?",
                "criteria": {
                    "billing": "Charges, refunds, invoices",
                    "shipping": "Delivery and tracking",
                    "technical": "Bugs and outages",
                },
            },
            "urgency": {
                "type": "score",
                "instructions": "How urgent is this?",
                "criteria": ["Can wait", "Handle today", "Handle now"],
            },
        },
    },
    timeout=30,
)
answers = response.json()["answers"]
print(answers["refund"]["noul"])    # probability of yes, 0-1
print(answers["team"]["choice"])    # e.g. "billing"
print(answers["urgency"]["score"])  # 0-2, can land between levels

Frequently asked questions

How much does Cloudflare: Clef Flash cost?

5.18 EGP per 1M input tokens; Output tokens are free. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.

What is the context window of Cloudflare: Clef Flash?

Cloudflare: Clef Flash supports a context window of 65,536 tokens (66K), with up to 58,982 output tokens per response.

Where is Cloudflare: Clef Flash hosted?

Cloudflare: Clef Flash is served from US (US-hosted inference).

How do I use Cloudflare: Clef Flash via the API?

Cloudflare: Clef Flash is a System One decision model. Send a state and typed questions (yes/no, multiple choice, or score) to /v1/systemone with model "clef-flash" and your API key — the TypeSafe-compatible contract, so the TypeSafe SDK works with base URL https://dev-backend.sovereigneg.com.