| What it does | Canary rollouts for prompts and models with automatic quality gates and rollback
| Self-hosted, on-premise load testing and performance testing platform
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| TR
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | 7-day free trial with 1,000 judged evaluations (no card required). Indie: $20/month or ₹1,699/month (3,000 judged evaluations/month). Starter: $49/month or ₹4,099/month (10,000 judged evaluations/month). Pro: $149/month or ₹12,499/month (100,000 judged evaluations/month). Enterprise: custom pricing.
| Free: $0 with a free key, no expiry. Starter: $83/mo (billed yearly: $990). Growth: $242/mo (billed yearly: $2,900). Enterprise: contact for pricing.
|
|---|
| Key features | - Canary deployments for prompts and models with progressive traffic steps
- LLM judge scoring responses on helpfulness, accuracy and clarity
- Automatic rollback when quality drops below threshold
- Drop-in replacement for OpenAI-compatible clients
- Support for OpenAI, Anthropic, Gemini, OpenRouter and Vercel AI Gateway
- Request log with prompts, responses, cost and judge verdict
- Failover and routing across providers
- Alerts via email, Slack and webhooks
- Dashboard and API for managing rollouts
- Controller makes routing decisions every 30 seconds
| - No-code test builder with web editor or JSON
- Multi-location load generation with percentage split
- Release comparison: A/B testing same test on two releases
- Protocol support: HTTP, gRPC, WebSocket, Kafka, SQL, MongoDB
- Server and database metrics collection with Collector and Tower
- Monitoring integrations: Datadog, New Relic, Dynatrace, Instana, Zabbix
- Import tests from OpenAPI, Postman, HAR, k6, or JMeter
- Scheduled runs with Slack, Teams, email and SMS alerts
- Production write guard: flags dangerous writes and data-changing requests
|
|---|
| What makes it different | - Automatically detects and rolls back silent quality failures that don't trigger errors or alerts
- Quality decisions based on real traffic and LLM judging, not health checks alone
- Minimal latency overhead of about 0.4ms median in request path
- Every decision audited with exact metrics that triggered routing changes
- Can run in the cloud or inside customer's own network for data privacy
| - Self-hosted: all data stays in your network, runs offline-verified license
- No per-VU or per-test-hour charges: fixed license price with unlimited load
- Always-on monitoring mode: runs tests at low load 24/7 on production
- Enterprise security: SSO, SAML, LDAP, audit log, encrypted secrets
- Version history and comparison: track every test change and compare releases
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | 14 ▼ −1 (down) since last check |
|---|
| Trust Flow (Majestic) | 0 | 3 |
|---|
| Citation Flow (Majestic) | 15 | 29 |
|---|
| Referring domains (Majestic) | 2 | 10 |
|---|
Repath
Spitfire