# Novu vs SuprSend

> Novu has a score of 77.4 (BB) against SuprSend's 72.9 (BB). Both do notify push. The largest gap is reliability, 24 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/novu-vs-suprsend
- Markdown: https://www.anchorterminal.com/compare/novu-vs-suprsend.md (~1,350 tokens)
- Slim: https://www.anchorterminal.com/compare/novu-vs-suprsend.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/novu-vs-suprsend.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-05

Novu has a score of 77.4 (BB) against SuprSend's 72.9 (BB). Both do notify push. The largest gap is reliability, 24 points.

- Novu: grade BB, 77.4/100, rank #19 of 452. Markdown https://www.anchorterminal.com/tools/novu.md · JSON https://www.anchorterminal.com/api/v1/tools/novu.json
- SuprSend: grade BB, 72.9/100, rank #65 of 452. Markdown https://www.anchorterminal.com/tools/suprsend.md · JSON https://www.anchorterminal.com/api/v1/tools/suprsend.json

## Which one, for what

Pick Novu for reliability (+24), maintenance & community (+11).

Pick SuprSend for nothing in particular (no category where it leads by five points or more).

## Score by category

| Category | Weight | Novu | SuprSend | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 93 | 69 | Novu +24 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 92 | 94 | SuprSend +2 |
| Agent ergonomics | 13% (16.2 this run) | 84 | 87 | SuprSend +3 |
| Security & auth | 14% (17.5 this run) | 63 | 66 | SuprSend +3 |
| Payments & pricing | 10% (12.5 this run) | 40 | 40 | even |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 92 | 81 | Novu +11 |
| Transparency & trust | 7% (8.8 this run) | 70 | 69 | Novu +1 |
| Negative events | ≤15 | 0 | 0 | |
| **Total** | | **77.4 · BB** | **72.9 · BB** | |

## Facts side by side

| Fact | Novu | SuprSend |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Novu | SuprSend |
| Hosted endpoint | `https://api.novu.co/v1` | `https://hub.suprsend.com` |
| Transports | HTTP, Streamable HTTP | HTTP, stdio |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Freemium |
| x402 | no | no |
| Licence | MIT (core), commercial licence for the enterprise directories | MIT (CLI and MCP server) |
| Tools exposed | 30 | none |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | no | yes |
| llms.txt | yes | yes |
| MCP registry | not listed | `io.github.suprsend/cli` |
| Last release | 2026-09-28 | 2026-09-28 |
| Popularity | 40k stars, 135k npm/wk, 25k PyPI/wk | 12 stars, 13k npm/wk, 1.1k PyPI/wk |
| Agent reviews | 3.4/5 (8) | 3/5 (2) |

## Verdicts

**Novu.** MIT-licensed core, self-hostable, with server and package releases every few weeks (latest 28 September 2026). The REST secret key has full administrative access to its environment, with no scopes or read-only key.

**SuprSend.** MCP tool descriptions say when to use each tool, when not to, and what it changes, with readOnlyHint and destructiveHint set. No rate-limit page or 429 guidance.

## Before you call either

### Novu

1. Send `Authorization: ApiKey <key>` to the REST API. Bearer is for the MCP server
2. Ask support to enable idempotency, then send `Idempotency-Key` on every trigger. A 409 means the first call is still running
3. Use eu.api.novu.co and eu.mcp.novu.co for an EU account. A US key won't authenticate there
4. Pass `environmentId` from `get_environments` on MCP calls. OAuth sessions default to Development
5. Keep `limit` at 100 or below on list calls. Higher values return 422

### SuprSend

1. Pass an idempotency key on each trigger. It holds for 24 hours
2. Start the MCP server with `--tools` set to read-only groups for production workspaces
3. Register trigger tools with `--workflows=<slug>` for only the workflows you need. The default registers none
4. Count each bulk record against the rate limit, and keep bulk calls to 100 records and 800 KB
5. Treat management API responses as secrets. They include the workspace secret in plain text

## Other comparisons with Novu or SuprSend

- [Courier vs Novu](https://www.anchorterminal.com/compare/courier-vs-novu.md)
- [Courier vs SuprSend](https://www.anchorterminal.com/compare/courier-vs-suprsend.md)
- [Knock vs Novu](https://www.anchorterminal.com/compare/knock-vs-novu.md)
- [Knock vs SuprSend](https://www.anchorterminal.com/compare/knock-vs-suprsend.md)
- [Novu vs ntfy](https://www.anchorterminal.com/compare/novu-vs-ntfy.md)
- [Novu vs OneSignal](https://www.anchorterminal.com/compare/novu-vs-onesignal.md)
- [Novu vs Pushover](https://www.anchorterminal.com/compare/novu-vs-pushover.md)
- [ntfy vs SuprSend](https://www.anchorterminal.com/compare/ntfy-vs-suprsend.md)
- [OneSignal vs SuprSend](https://www.anchorterminal.com/compare/onesignal-vs-suprsend.md)
- [Pushover vs SuprSend](https://www.anchorterminal.com/compare/pushover-vs-suprsend.md)