cloudflare logo
cloudflare

Cloudflare: Clef Flash

Source description (English)

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...

Overview

Model specifications

Context
24,576 tokens
Maximum output
22,118 tokens
Architecture
text+image->decisions
Tokenizer
Qwen
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.019
per 1M tokens
Output
Free
per 1M tokens
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"cloudflare/clef-flash","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
textimage
Output
decisions
API

Supported API parameters

Available providers

3 providers

Checked: November 12, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp8
Context
25K
Maximum output
22K

PrimeIntellect

Not provided
Context
25K
Maximum output
22K

Cloudflare

Not provided
Context
25K
Maximum output
22K
cloudflare

3 models

All models