Track errors free. Pay when they start fixing themselves.
The tracker is free forever, because a tracker is table stakes. The agent is the reason to pay, so the agent is never free.
Free
Free error tracking. Forever.
- events
- 5,000 events / month
- projects
- 1 project
- retention
- 30-day retention
- Sentry-compatible ingest
- Grouping, tags, breadcrumbs
- Regression detection
- Rate limits and quotas
This button exists on your issues. Upgrading unlocks it.
Developer
agentThe agent, credits included.
- events
- 100,000 events / month
- projects
- 5 projects
- retention
- 90-day retention
- Everything in Free
- Monthly AI credits included
- Bring your own agent, keys, or CLI
- Context bundles and confidence gating
- Draft PR post-back
Team
agentManaged runs, or your own.
- events
- 1,000,000 events / month
- projects
- Unlimited projects
- retention
- 90-day retention
- Everything in Developer
- A larger AI credit allowance
- Managed mode, running on plan credits
- GitHub App integration
- Editable change plans
A closer look at each plan
Every capability, one row each, with the tier it lands in. The last group is what Parsemend does not do, stated plainly, with a path to the roadmap.
| Capability | Free | Developer | Team |
|---|---|---|---|
| Error tracking | |||
| Events per month | 5,000 | 100,000 | 1,000,000 |
| Projects | 1 | 5 | Unlimited |
| Retention | 30 days | 90 days | 90 days |
| Sentry-compatible ingest (envelope + store) | Included | Included | Included |
| Works with unmodified Sentry SDKs (verified: PHP, Node) | Included | Included | Included |
| Grouping cascade + custom fingerprints | Included | Included | Included |
| Tags, breadcrumbs, environments | Included | Included | Included |
| Regression detection | Included | Included | Included |
| Rate limits and quotas (429 + Retry-After) | Included | Included | Included |
| Monitoring and observability | |||
| Tracing (transactions and spans) | Included | Included | Included |
| Structured logs | Included | Included | Included |
| Uptime monitoring | Included | Included | Included |
| Cron and scheduled-job monitoring | Included | Included | Included |
| Source maps and releases | Included | Included | Included |
| Alert rules (email, Slack, Discord, webhook) | Included | Included | Included |
| Metric and anomaly alerts (error rate, failure rate, p95) | Included | Included | Included |
| Per-project health aggregates (error rate, failure rate, p95) | Included | Included | Included |
| The fix agent | |||
| Fix runs (RootCause → Solution → Coding → ChangeDescription) | Not included | Included | Included |
| Monthly AI credits included | Not included | Included | Larger allowance |
| Credit top-ups when you need more | Not included | Included | Included |
| Fixability score and confidence gating | Not included | Included | Included |
| Context bundles | Not included | Included | Included |
| Draft PR post-back | Not included | Included | Included |
| Bring-your-own-agent, your-keys and CLI modes | Not included | Included | Included |
| Model providers: Anthropic, OpenAI, Gemini, Ollama | Not included | Included | Included |
| Managed mode (runs on plan credits) | Not included | Not included | Included |
| GitHub App integration | Not included | Not included | Included |
| Editable change plans | Not included | Not included | Included |
| Benchmark reports | Not included | Not included | Included |
| Code review and QA | |||
| Pull request review (explored, concluded, fact-checked) | Not included | Not included | Included |
| Production issue history as review context | Not included | Not included | Included |
| Dependency review (OSV + Packagist advisories) | Not included | Not included | Included |
| Secret scanning on pull requests (local rules only) | Not included | Not included | Included |
| Autonomous QA flows (deterministic browser replays) | Not included | Not included | Included |
| PR check runs (parsemend/qa) | Not included | Not included | Included |
| Fix verification by re-running the failing flow | Not included | Not included | Included |
| Not in ParsemendThese are on the roadmap, not in the product. The comparison with Sentry is at /vs/sentry; where each one stands is at /roadmap. | |||
| Session replay1 | Not included | Not included | Not included |
| Profiling1 | Not included | Not included | Not included |
| Crash-free-rate alerts (needs session ingestion) | Not included | Not included | Not included |
| Analytics dashboards and arbitrary-tag aggregation | Not included | Not included | Not included |
| Native symbolication (dSYM, PDB, ELF) | Not included | Not included | Not included |
1replay and profile envelope items are accepted and dropped as unknown, so an SDK that sends them never errors. That is tolerance, not support.
How billing works
- Flat.
- One subscription covers the whole platform, with a monthly allowance of AI credits built in. It does not move when your error volume spikes.
- Top-ups, only if you need them.
- The agent's runs draw from the allowance. Top up when a month outgrows it; nothing scales with headcount.
- Your own keys, optional.
- In bring-your-own-agent, your-keys and CLI modes, inference is billed to your provider at their public rates, or costs nothing on your own Ollama hardware. Credits are never touched on those paths.
Cost per fix, worked out
A calculator that turns your issue volume into a credit bill is only useful if its numbers come from real runs. It ships with the benchmark suite, together with the per-run token counts it is built on. Until then there is nothing here worth reading.
Credits are simpler than a second invoice, but they do put the metering on our side of the table. If you would rather see raw token prices on your own provider account, three of the four fix modes work exactly that way, and there is no judgement in either choice.
Frequently asked questions
Is the free tier a trial?
No. Error tracking is free forever, with 5,000 events a month on one project. It never expires. What it does not include is the fix agent.
Why is every AI feature paid?
Because the agent costs real money to run, and a free version of it would either be rate-limited into uselessness or fund itself by selling your data. The free tier is the full tracker; the agent is what the paid plans buy.
Who pays for the model tokens?
Parsemend does, out of the AI credits included in your plan. When a month outgrows the allowance you buy a top-up; when it does not, there is nothing extra to pay. In bring-your-own-agent, your-keys and CLI modes your provider bills you directly instead, and the credits are never touched.
What does a fix run actually cost in credits?
It depends on the size of the context bundle and the model behind the run, so any single number here would be misleading. The cost calculator ships alongside the benchmark suite, where the numbers come from real runs rather than estimates.
Do I need to give Parsemend access to my repository?
Only in managed mode. Bring-your-own-agent, your-keys and CLI modes all work without a GitHub App installation, and in the first and third your source never leaves your infrastructure.
Still deciding where the agent should run? Compare the four fix modes.