clef-flash

Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions.

Context
25K
Input price
$0.04/1M tokens
Output price
$0/1M tokens

Capabilities

Infrastructure
Streaming

Details

Model IDCloudflare/clef-flash
Provider DeepInfra
Creator cloudflare
Family—
License—
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window25K tokens
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.deepinfra.com/v1/openai/v1/chat/completions

Pricing

Input
$0.04
Output
$0
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/deepinfra/Cloudflare/clef-flash

clef-flash

Cloudflare/clef-flash

Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions.

Changes · 4 entries
Cloudflare/clef-flashcreateca7a400Nov 2, 2026, 03:02 AM
Cloudflare/clef-flashupdateb2f45bfOct 29, 2026, 03:29 AM
quantizationbfloat16→fp8
Cloudflare/clef-flashupdate4e8b6afOct 21, 2026, 06:35 AM
descriptionClef-Flash is a 9B multimodal model that turns a state an...
taglineClef-Flash is a 9B multimodal model that turns a state an...
Cloudflare/clef-flashcreatebcf2693Oct 16, 2026, 06:36 AM