Skip to content
System One
All models

Clef Flash

Provided by: system-one.dev

The cheapest of the three Clef models. Use it for high-volume, cost-sensitive classification and routing.

Model info

  • Provided by: system-one.dev
  • 3 credits per question per 4KB
  • Up to 32 questions · 13MB per request
  • Inputs: text, JSON, and images (PNG, JPEG, WebP)
  • Images: up to 4 · 4MB each · 8MB total
  • Pick one: up to 255 options; Score: 2–10 levels
  • Released 2026-10-01

Uses

  • Ticket and screenshot routing: On a large volume of requests with screenshots, pick a team or a tool. See Agent tool routing.
  • Model routing: First judge how hard the request is, then send it to a small or large model. See Model routing.
  • Batch moderation: Read text and an image, then allow, block, or hand off from a yes/no probability. See Agent guardrails.
  • High-frequency checks in an agent loop: When every step must decide whether to stop or continue, use the lower-priced model to control cost. See When an agent should stop.

Official sources

Last updated 2026-10-12

Open GET /v1/models · Developer docs · Try live (sign in required)

Frequently asked questions

How is Clef different from Clef Flash?
Clef Flash, Clef, and Clef Omni share the same request format and all accept text and images. Clef Flash is the cheapest and fits high-volume, cost-sensitive work. Clef has the highest rate; when Jev or Clef Flash is not good enough, compare Clef on the same data. Compare the rates in each page’s Model info. See What is Clef.
What inputs does Clef Flash accept?
Text (including JSON) and images. Image formats, count, and request-size limits are in Model info on this page.
Does Clef Flash support Chinese?
Test Chinese results with your own data first.
Is there a free allowance?
Billing is in credits. See Model info on this page for the rate. Details: Pricing. New accounts get 100 free credits on sign-up.