Pricing and Plans for Pydantic Logfire

One record-based meter covers AI observability, evals, application performance, and infrastructure. $20 of free usage a month (10M records) on every plan, then $2 per million on Team and Growth.
Perfect for solo devs, and the agents building with them.
Logfire plan highlights
Trace agent runs from prompt through tool calls with Pydantic AI, LangChain, OpenAI SDK, or anything OTel-instrumented.
Supports all OTel SDKs, so every service lands on one correlated timeline.
Kubernetes, hosts, databases, and more, with logs and host metrics with pre-built dashboards.
Bring up to 3 provider credentials (no markup). Access built-in providers with a 5% markup fee (requires adding a credit card).
Configure your OpenTelemetry Collectors and SDKs from Logfire over OpAMP. Up to 3 SDK applications, 3 Collector policies and 20 connected Collectors. Learn more
Covers 10 million logs, spans, and metrics every month. This is a lot of telemetry for a solo developer! Once you hit the limit, ingestion pauses, so you can't owe us anything on the personal tier. Upgrade to Team for additional records.
One admin seat (you).
A guest is a read-only user that can be invited directly to a Logfire project, but not to an organization. Guests are similar to outside collaborators in GitHub.
Query your traces, logs, and metrics for the last 30 days.
Support & compliance
Get help from the Pydantic community on Slack, GitHub Discussions, and Stack Overflow. No SLA; response times depend on the community.
For small teams shipping their first production workloads.
Logfire plan highlights
Everything in Personal, plus:
10 million logs, spans, and metrics are free every month. Additional records are $2 per million, or set a hard price cap to lock in your bill.
No per-agent fees. Trace every agent run and only pay for the telemetry (records) you send.
Supports all OTel SDKs, with every service on one correlated timeline with service inventory, service maps, and more. No per-service fees.
Kubernetes, hosts, databases, and more, with logs and host metrics with pre-built dashboards and alerts.
Evaluate your AI outputs for free, with no per-score charges.
Add human review to any trace or eval run, for RLHF training or manual quality checks.
Bring up to 5 provider credentials (no markup). Access built-in providers with a 5% markup fee.
Configure your OpenTelemetry Collectors and SDKs from Logfire over OpAMP. Up to 5 SDK applications, 5 Collector policies and 100 connected Collectors. Learn more
Admin or member seats for you & your core team. 5 seats included, $25/extra seat.
A guest is a read-only user that can be invited directly to a Logfire project, but not to an organization. Guests are similar to outside collaborators in GitHub.
Organize your apps. Scope access per project.
Support & compliance
Set a hard limit on your bill. Once you hit your cap, new telemetry is hidden from view, but we keep capturing it up to a generous threshold. To set a cap, email accounts@pydantic.dev. Learn more
Unsure after your first month? We'll refund you. And if you get hit with an unexpectedly large bill in your first month because of a spike in volume, we'll refund that too.
For teams running production AI services core to their business.
Logfire plan highlights
Everything in Team, plus:
Bring up to 20 provider credentials (no markup). Access built-in providers with a 3% markup fee.
Configure your OpenTelemetry Collectors and SDKs from Logfire over OpAMP. Up to 50 SDK applications, 50 Collector policies and 1,000 connected Collectors. Learn more
Try new Logfire capabilities before they ship broadly. Feedback shapes what lands and when.
No per-seat cost. Add your whole team.
No cap on read-only viewers. Bring in stakeholders, clients, or your CTO.
No limits on services, environments, or experiments.