
Clef
Model ranking
Not matched to the current verified ranking snapshot.
| Provider | Price | Provider model ID | Status | Context / max output | Source |
|---|---|---|---|---|---|
Cloudflare Workers AIclef | Standard Tariff not listedInput $0.24USD / 1M tokens Updated 2026-11-22 · 15:43 UTCCloudflare Workers AI · StandardInput: $0.24 Published Workers AI USD list tariffs. Free daily Neuron allowance is separate, not a zero unit price. Image tile/step components must be evaluated together; no flat image price is inferred. Checked 2026-11-22T15:43:15.988Z Price source ↗ | @cf/cloudflare/clef | Catalog-listedConditionsPublic catalog listing; account eligibility and capacity can vary. Verified component tariffs are supplied by the existing pricing engine. | Context tokens 65536 | Official source ↗2026-10-20 |
Clef is Cloudflare’s 27B multimodal decision model. It receives a state and a schema of questions, then assigns probabilities to the allowed options instead of returning ordinary open-ended chat.
Clef: suitable applications
Use it for bounded routing and state assessment where candidate outcomes can be explicitly enumerated in a typed schema.
Capabilities and technical details
The documented interface accepts text, JSON and visual state, including images or video. Option-level outputs make the decision space explicit.
Clef accepts text, image, video and returns structured data. The recorded input reference is 262,144 tokens, with any lower Cloudflare cap recorded separately. The recorded terms are Apache 2.0; the linked source explains their scope.
Clef limitations and selection
Returned probabilities can be miscalibrated or wrong. Media are converted into billable input tokens, so a text-only token estimate does not cover every request.
Evaluate option definitions and confidence calibration with representative states, and compare the full Clef model with Clef Flash using the same schema.
Clef API pricing
Clef pricing is tied to the selected endpoint and its documented token components. Compare input, output and cached-input charges only where those components are actually quoted; an absent component is not an invented free rate.
Review the Cloudflare Clef endpoint reference and the Cloudflare model documentation. Compare the linked Cloudflare Workers AI provider profile with the xpu live model directory when selecting a deployment.
Specifications
- Catalog model ID
- cloudflare/clef
- Developer model ID / revision
- Not verified in cited sources
- Input modalities
- text, image, videoCloudflare Workers AI endpoint; route-specific capabilities ↗
- Output modalities
- structured dataCloudflare Workers AI endpoint; route-specific capabilities ↗
- Context / input token limit
- 262,144Developer model card / documentation ↗
- Maximum output tokens
- Not verified in cited sources
- Tool calling
- Not verified in cited sources
- Structured output
- SupportedCloudflare Workers AI endpoint; route-specific capabilities ↗
- API parameters (source-specific)
- Not verified in cited sources
- Weight access
- Open weightsDeveloper model card / documentation ↗
- Weight license / access terms
- Apache 2.0Developer weight license / hosted access terms ↗
- Total parameters (billions)
- 27Developer model card / documentation ↗
- Active parameters (billions)
- Not verified in cited sources
- Parameter-count details
- Developer-declared nominal model size; serialized tensor counts can differ. Active parameters, when supplied, are separate from total parameters.Developer model card ↗
- Download size (GB)
- Depends on checkpoint and precision; no verified file size
- Release date
- Not verified in cited sources
- Notes
- Cloudflare deployment limits and transport options are recorded on its offering. Weight license is separate from hosted-service conditions. Context shown here is the publisher configuration; provider caps can be lower. Parameter sizes are developer-declared nominal labels; serialized tensor counts may differ.
Catalog entries link to their specification and availability sources. This is a curated selection, not every model each provider offers. Best prices are the lowest collected USD tariffs, not a total-cost estimate. Token offers are selected by input price, with output from the same tariff; workload mix may change the cheapest provider. Listed variants may require batch processing, off-peak hours, or specific media settings. Price coverage varies by provider; collected tariffs include their source and observation time. Arena user-preference scores are checked automatically every six hours against the latest published Text / overall dataset. Source: Arena / LMArena; CC BY 4.0. Selection and catalog matching by XPU LIVE. They apply to the shown evaluation configuration; listed prices may use different settings. Models without verified scores are not assumed to be weaker.
