Clef is a 27B multimodal model created by Cloudflare that turns a state and a schema of typed questions into decisions.
ollama run clef:cloud
| Task | You define | You get back |
|---|---|---|
| Route a request | The destinations and when each applies | The chosen destination and each destination’s pr |
| Check a condition | A yes-or-no question and the evidence | The probability that the answer is yes |
| Apply a policy | The rules and the allowed outcomes | A typed decision based on the text or images you |
| Read a document | A photo of the page and the fields to decide | A field-by-field decision with probabilities |
| Moderate a tool call | The call an agent is about to make | The probability that it’s harmful, before it run |
| Field | Description |
|---|---|
| model | clef locally, or clef:cloud through a local Olla |
| state | The text to judge. Use a string, or a JSON objec |
| images | Optional. Base64-encoded PNG, JPEG, or WebP imag |
| questions | 1 to 64 named questions. Answers come back in th |
| keep_alive | Optional, local only. How long the model stays l |
| Benchmark | Clef | Clef-flash |
|---|---|---|
| BFCL (case exact accuracy) | 98.5 | 98.8 |
| API-Bank (accuracy) | 91.9 | 93.1 |
| BANKING77 (macro-F1) | 94.2 | 90.9 |
| CLINC150+OOS (macro-F1) | 97.4 | 66.8 |
| Home appliance simulator (case exact accuracy) | 83.0 | 97.7 |
| ANLI (macro-F1) | 69.8 | 59.1 |
| RouterBench (selected quality) | 79.7 | 79.9 |
| PhishNChips (accuracy) | 79.6 | 75.0 |