Langfuse vs Knock
Open-source LLM engineering platform — observability, prompts, evals
vs. Notifications-as-a-service: in-app feeds, email, push, SMS, chat via one API
Pricing tiers
Langfuse
Hobby (Cloud Free)
Free. 50k units/month included. 30 days data access. 2 users. Community support.
Free
Self-Hosted (OSS)
MIT-licensed. Docker Compose or Kubernetes deployment. Unlimited.
$0 base (usage-based)
Core
$29/month. 100k units included ($8 per 100k overage). 90 days retention. Unlimited users. In-app support.
$29/mo
Pro
$199/month. 100k units included + same overage. 3 YEARS retention. Unlimited annotation queues. High rate limits.
$199/mo
Teams Add-on
+$300/month. Adds Enterprise SSO + fine-grained RBAC + dedicated Slack support to Pro.
$300/mo
Enterprise
$2,499/month. Everything + custom rate limits, uptime SLA, dedicated support engineer. Yearly options.
$2499/mo
Knock
Developer
Free forever. 10K messages, 500 guide users, 500 AI credits/month.
$0 base (usage-based)
Starter
$250/mo. 50K messages, 2.5K guide users, 2K AI credits. Remove branding.
$250/mo
Enterprise
Custom pricing. White-label, i18n, data warehouse, Datadog, SCIM, SAML, HIPAA/BAA.
Custom
Free-tier quotas head-to-head
Comparing hobby on Langfuse vs starter on Knock.
| Metric | Langfuse | Knock |
|---|---|---|
| guide users | — | 2500 users |
| guide users overage | — | $0.05/user USD/user |
| messages monthly | — | 50000 messages/mo |
| messages overage | — | $0.005/message USD/message |
Features
Langfuse · 16 features
- Annotation Queues — Human reviewers rate traces. Unlimited on Pro+.
- Dashboards — Aggregate metrics, cost, quality across projects.
- Datasets — Curate test sets from production traces. Run experiments.
- EU Cloud Region — GDPR-compliant hosting in EU.
- Evaluations — LLM-as-judge, manual scores, custom model-graded evaluators.
- LLM Cost Tracking — Automatic cost calculation per provider/model.
- OpenTelemetry Native — OTel SDK → Langfuse endpoint works out of box.
- Playground — Test prompts + models + variables live.
- Prompt Management — Version, tag, label prompts. Reference from code by label.
- Public API — Full REST API for ingest, query, prompt management.
- Python @observe decorator — One-line decorator to trace any function.
- Self-Hosting — Docker Compose + k8s Helm chart.
- Sessions — Group related traces (conversations, agent runs).
- Tracing — Capture every LLM call, tool call, nested span with inputs/outputs/cost.
- Users Tracking — Segment traces by user ID, track per-user cost.
- Webhooks — Subscribe to trace completion events.
Knock · 13 features
- AI Agents — Autonomous notification drafting & workflow generation.
- Batch + Digest — Group notifications into digests on schedule or window.
- Chat — Slack, Microsoft Teams, Discord.
- Email — Send via SendGrid/Postmark/Resend/Mailgun/AWS SES as relays.
- Guides — In-product messaging, announcements, modals, banners.
- i18n / Localization — Translate templates by user locale.
- In-App Feed — Notification inbox with React/Vue/iOS/Android drop-in components.
- Multi-tenancy — Per-tenant branding, preferences, quiet hours.
- Outbound Webhooks — Subscribe to delivery events.
- Preferences — User + tenant preference center with granular controls.
- Push — iOS (APNs), Android (FCM), Expo, Web Push.
- SMS — Twilio, MessageBird, Telnyx, Vonage as providers.
- Workflows — Visual notification orchestration (branch, batch, delay, throttle).
Developer interfaces
| Kind | Langfuse | Knock |
|---|---|---|
| CLI | — | Knock CLI |
| SDK | langfuse-js, langfuse-python | knockapi (Python), knockapi (Ruby), knock-elixir, knock-go, knock-java, @knocklabs/node, @knocklabs/react |
| REST | Langfuse REST API | Knock REST API |
| MCP | Langfuse MCP Server | Knock MCP Server |
| OTHER | Langfuse Dashboard, OpenTelemetry endpoint | Outbound Webhooks |
Staxly is an independent catalog of developer platforms. Some links to Langfuse and Knock may be affiliate links — Staxly may earn a commission if you sign up through them, at no extra cost to you. Pricing is verified against vendor pages at publication time — reconfirm before buying.
Want this comparison in your AI agent's context? Install the free Staxly MCP server.