| What it does | A scheduling API for developers and their agents to make HTTP calls later, with automatic retries and full record-keeping
| Jev-compatible API for text classification and moderation, hosted in the EU
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| FI
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | $1 per 100,000 attempts. First project included in subscription. Additional projects cost $5/month. Trial credit of $1 valid for 14 days upon sign-up. Prepaid credit from $10, never expires.
| Free: $1 credit (66.7K decisions) on sign-up. Starter: $9/month for 1M decisions, then $10/million. Pro: $49/month for 10M decisions, then $5/million. Pay as you go: $15/million decisions from prepaid credit ($10 minimum). Clef-flash: $0.10/million tokens. Clef: $0.50/million tokens. Bonus credit: +
|
|---|
| Key features | - Schedule calls at a specified delay, at an exact time, on a cron expression, or at regular intervals
- Automatic retries with growing waits, up to 5 failures
- Full attempt records with status, timing, and response body up to 10 KiB
- Cryptographic signing of all calls verified over exact bytes
- Time zone support with daylight saving handling
- Respects HTTP Retry-After headers, waiting up to one hour
- Built-in MCP server for AI agents like Claude Code, Codex, and Cursor
- Bulk operations to manage many schedules together with dashboard, API, CLI, or SDK access
- REST API, JavaScript SDK, CLI, and dashboard interfaces
- 24-hour forecast for autoscalers
| - Decision flows: chain decisions on a canvas for multi-step classification
- Test sets: measure accuracy on your own labelled data before deployment
- Compare models side-by-side: test Laya, Clef-flash and Clef on the same data
- Custom models: fine-tune Laya on your own labelled examples
- Jev API compatibility: same endpoints, request and response formats as Jev
- Perspective API replacement: drop-in replacement for Google's deprecated moderation API
- Multiple model options: Laya (fast, cheap, EU-hosted), Clef-flash (9B model) and Clef (27B model)
|
|---|
| What makes it different | - Built from the start for AI agents through Model Context Protocol
- Pay only for attempts made; waiting costs nothing
- Automatic retry handling removes need to build job queue infrastructure
- Every attempt recorded with full context for debugging
- Cryptographically signed calls allow verification before trusting
| - EU-hosted Laya model: text never leaves the EU and is not used for training
- No lock-in: API compatible with Jev, uses open-weights models you can run yourself
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 2 ▲ +2 (up) since last check | 32 ● no change since last check |
|---|
| Trust Flow (Majestic) | 2 | 7 |
|---|
| Citation Flow (Majestic) | 23 | 27 |
|---|
| Referring domains (Majestic) | 10 | 90 |
|---|
GreatWait
layahost