---
title: 'Logfire vs Braintrust: Production AI Improvement, Not Just Evaluation'
description: >-
  Compare Logfire and Braintrust for evals, pricing, and observability. Send
  your existing Braintrust evals to Logfire without rewriting the suite.
canonical: 'https://pydantic.dev/logfire/vs-braintrust'
last-reviewed: '2026-08-20'
---

> Markdown version of [Logfire vs Braintrust](https://pydantic.dev/logfire/vs-braintrust) — the canonical HTML page.
>
> Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

# Logfire vs Braintrust

Braintrust centers on evals. Logfire combines production traces, annotations, evals, prompt optimization, and managed agent configuration with the application and infrastructure around each run. There is no separate per-score meter.

[Try Logfire free](https://logfire.pydantic.dev/login?intent=signup)

## Keep your eval suite

Already use Braintrust’s `Eval` API? Change two environment variables and send your next runs to Logfire’s Evals workspace. Your inline data, local tasks, and scorers can stay where they are.

```bash
export BRAINTRUST_APP_URL="https://logfire-us.pydantic.dev/v1/braintrust"
export BRAINTRUST_API_KEY="<your-logfire-write-token>"
```

Use `https://logfire-eu.pydantic.dev/v1/braintrust` for an EU project. The endpoint does not import existing history or provide Braintrust-hosted datasets, prompts, functions, a model proxy, server-side scoring, or public sharing.

[See compatibility details](https://pydantic.dev/articles/switching-from-braintrust) · [Talk to us about hosted workflows](https://pydantic.dev/contact)

## From a production run to a better agent

_Logfire and Braintrust compared feature by feature_

| Feature | Logfire | Braintrust |
| --- | --- | --- |
| Production context | Browser, agents, services, databases, logs, metrics, and infrastructure | AI and application traces, logs, and OpenTelemetry spans |
| Full-stack observability suite | Infrastructure monitoring, service maps, logs, metrics, traces, and AI | ✗ |
| Browser session replay | Browser tracing and session replay alongside the agent trace | ✗ |
| First-class feature flags | OpenFeature/OFREP flags, targeting, and controlled rollout | ✗ |
| Evaluation workflow | Pydantic Evals: the same evaluators online and offline | Experiments, playgrounds, CI/CD, and online scoring |
| Score pricing | No separate score meter; normal record pricing applies | $1.50 per 1,000 scores after 50K/month on Pro |
| Human review | Annotation queues on production runs and evals | Human-review scores and assigned trace review |
| From failure to change | Trace-backed optimizer and managed agent configuration | Prompt, scorer, dataset, and environment workflows |
| Managed agent configuration | Prompts, agent specs, tools, skills, versioning, targeting, and rollout | ✗ |
| Controlled rollout | Immutable versions, labels, targeting, weighted rollout, and feature flags | Prompt, dataset, and parameter environments |
| Investigation workflow | Agent trace investigator, PostgreSQL-compatible SQL, and MCP across full telemetry | Logs, trace views, SQL, and MCP for Braintrust data |
| Deployment options | Cloud, Dedicated, or the same product self-hosted on Kubernetes | Cloud or an Enterprise self-hosted data plane |

## The full production improvement loop

### Investigate the system, not only the output

An agent failure is often a browser, API, database, retrieval, tool, or infrastructure failure wearing an LLM-shaped mask. Logfire keeps those signals in one nested trace, with service maps, logs, metrics, SQL, and an agent trace investigator built for the production incident behind the score.

### Evaluate online and offline without rationing coverage

Use the same Pydantic Evals evaluators for fast offline feedback and online production monitoring. Cheap heuristics can run on every run; LLM judges can sample the traffic that deserves them. Scores use Logfire's normal record pricing instead of adding a new billing meter.

### Turn a human judgment into the next improvement

Annotation queues let reviewers work through the production runs that matter, with verdicts, failure categories, expected outputs, comments, and tags. That judgment stays linked to the trace, becomes a reusable evaluation case, and gives the optimizer grounded evidence for the next change.

### Change the agent safely, without a second control plane

Logfire manages prompts, agent specs, tools, and skills as versioned configuration. Review a trace-backed proposal, then target a cohort, canary a weighted rollout, watch the live result, and roll back by moving a label. The version that served every run is part of that run's trace.

## Which should you choose?

### Choose Logfire if...

- You already have Braintrust evals and want to try Logfire without rewriting the suite
- You need to diagnose agents in the context of the browser, service map, database, API, logs, metrics, and infrastructure
- You want online and offline evaluation without a separate per-score billing meter
- You want reviewers to work from annotation queues, then export an annotated failure into a reusable evaluation case
- You want a trace-backed prompt optimizer to propose a production-grounded change
- You want to version, target, canary, and roll back managed prompts, agent specs, tools, and skills
- You want your coding agent to investigate the same telemetry with MCP and PostgreSQL-compatible SQL

### Choose Braintrust if...

- You depend on Braintrust-hosted datasets, prompts, functions, the model proxy, server-side scoring, or public sharing

## See Logfire on your own telemetry

Start free with 10 million spans, logs, and metrics each month. No credit card required.

[Start free](https://logfire.pydantic.dev/login?intent=signup) · [Book a demo](https://pydantic.dev/contact)

## Score freely at production scale

_Estimated monthly charges for score records in Braintrust Pro and Logfire_

| Production coverage | Scores | Braintrust Pro base + score charge | Estimated Logfire monthly charge |
| --- | --- | --- | --- |
| 10M runs × 10% sampled × 3 scores | 3M scores/month | $4,674/month | $49/month |
| 10M runs × 25% sampled × 5 scores | 12.5M scores/month | $18,924/month | $54/month |
| 100M runs × 10% sampled × 5 scores | 50M scores/month | $75,174/month | $129/month |

### Exact pricing math and sources

Braintrust Pro base plus score charges compared with the Logfire plan and normal record usage attributable to the score results. Processed-data and extended-retention charges are disclosed but omitted from the totals because the score count does not determine either meter.

**Basis:** USD; public monthly list price. Prices checked 2026-09-12.

#### Published inputs

- **Braintrust Pro base:** $249/month — [Braintrust source](https://www.braintrust.dev/pricing)
- **Braintrust Pro included model credits:** $100/month — [Braintrust source](https://www.braintrust.dev/docs/plans-and-limits)
- **Braintrust Pro processed data:** 5 GB included, then $3/GB — [Braintrust source](https://www.braintrust.dev/pricing)
- **Braintrust Pro retention:** 30 days included; up to 180 days at $0.50/GB/month after the included period — [Braintrust source](https://www.braintrust.dev/pricing)
- **Braintrust Pro included scores:** 50,000 scores/month — [Braintrust source](https://www.braintrust.dev/pricing)
- **Braintrust Pro additional scores:** $1.50 per 1,000 scores — [Braintrust source](https://www.braintrust.dev/pricing)
- **Logfire Personal base:** $0/month — [Pydantic Logfire source](https://pydantic.dev/pricing)
- **Logfire Team base:** $49/month — [Pydantic Logfire source](https://pydantic.dev/pricing)
- **Logfire included telemetry:** 10,000,000 records/month — [Pydantic Logfire source](https://pydantic.dev/pricing)
- **Logfire additional telemetry:** $2 per 1,000,000 records — [Pydantic Logfire source](https://pydantic.dev/pricing)

#### Assumptions

- **Recorded scores:** Sampled runs × scores per sampled run — Braintrust counts each recorded online or offline score toward monthly usage. ([Braintrust source](https://www.braintrust.dev/pricing))
- **Score-to-record mapping:** 1 recorded score = 1 Logfire record — Score results use Logfire's normal telemetry allowance and overage rate; there is no additional score-specific meter. ([Pydantic Logfire source](https://pydantic.dev/pricing))
- **Included Braintrust value:** $100/month in model credits and unlimited users — The credits do not reduce the cash subscription total, but they can offset model usage through Braintrust and are material included value. ([Braintrust source](https://www.braintrust.dev/docs/plans-and-limits), [Braintrust source](https://www.braintrust.dev/pricing))

#### Calculations

##### 10M runs × 10% sampled × 3 scores

3,000,000 recorded scores in the month.

**Braintrust: $4,674**

1. Pro base: `$249` = **$249**
1. Additional scores: `(3,000,000 − 50,000 included) ÷ 1,000 × $1.50` = **$4,425**

**Logfire: $49**

1. Team base: `$49` = **$49**
1. Additional records: `(3M − 10M included) ÷ 1M × $2` = **$0**

##### 10M runs × 25% sampled × 5 scores

12,500,000 recorded scores in the month.

**Braintrust: $18,924**

1. Pro base: `$249` = **$249**
1. Additional scores: `(12,500,000 − 50,000 included) ÷ 1,000 × $1.50` = **$18,675**

**Logfire: $54**

1. Team base: `$49` = **$49**
1. Additional records: `(12.5M − 10M included) ÷ 1M × $2` = **$5**

##### 100M runs × 10% sampled × 5 scores

50,000,000 recorded scores in the month.

**Braintrust: $75,174**

1. Pro base: `$249` = **$249**
1. Additional scores: `(50,000,000 − 50,000 included) ÷ 1,000 × $1.50` = **$74,925**

**Logfire: $129**

1. Team base: `$49` = **$49**
1. Additional records: `(50M − 10M included) ÷ 1M × $2` = **$80**

#### Source ledger

- [**Braintrust — Braintrust pricing**](https://www.braintrust.dev/pricing) — official vendor source; checked 2026-09-12. “50k scores + $1.50/1k” Braintrust's on-page calculator itemizes its platform, processed-data, score, and retention meters.
- [**Braintrust — Plans and limits**](https://www.braintrust.dev/docs/plans-and-limits) — official vendor source; checked 2026-09-12. “Pro ($249/month)” Braintrust Pro includes $100 per month in model credits, 5 GB processed data, and 30-day retention.
- [**Pydantic Logfire — Pricing and plans for Pydantic Logfire**](https://pydantic.dev/pricing) — official vendor source; checked 2026-09-12. “Covers 10 million logs, spans, and metrics every month.” The official calculator shows 20 million records and no extra seats totaling $69/month on Team.

#### What this calculation does not include

- Braintrust processed-data and retention charges are excluded, so the Braintrust estimates are lower than a complete bill when those meters exceed their allowances.
- Braintrust Pro includes $100 per month in model credits. The credit does not lower the displayed invoice, but it can offset built-in model usage; provider and model costs are otherwise excluded from both products.
- Braintrust includes 5 GB of processed data and 30-day retention. Processed data includes traces, experiments, datasets, prompts, metadata, outputs, and attachments, then costs $3/GB.
- Each Logfire score result is counted as one record here. The other trace, evaluator, log, and metric records created by an evaluation workload are excluded.

## Common questions

### Can I send Braintrust SDK evals to Logfire?

Yes. Point the Braintrust SDK at Logfire and keep your existing eval suite. Future eval runs appear in the Evals workspace alongside the traces and telemetry that explain each result. Existing Braintrust history and Braintrust-hosted services are not imported.

### How do Logfire and Braintrust compare on evaluation pricing?

Logfire does not add a separate per-score meter: score results use its normal record allowance and $2-per-million paid-plan overage. All three worked examples use Team: 3 million score records total $49; 12.5 million total $54; and 50 million total $129. Braintrust Pro lists a $249 monthly base with 50,000 scores included, then $1.50 per 1,000 scores, producing $4,674, $18,924, and $75,174 for the same three score counts. Pro also includes $100 in model credits; those credits do not reduce the invoice but can offset built-in model usage. Processed-data and extended-retention charges are excluded.

### Do both Logfire and Braintrust support online and offline evaluation?

Yes. Both support offline experiments and asynchronous scoring of production traffic. Logfire uses the same Pydantic Evals evaluators online and offline, keeps every result attached to its OpenTelemetry trace, and does not add a separate score meter.

### What is Logfire's advantage for production AI systems?

Logfire investigates the whole production system, not only the AI output: browser activity, agent and model calls, tool calls, APIs, databases, logs, metrics, services, and infrastructure. From a failing run, teams can annotate it, query it with SQL or MCP, export it into an evaluation case, use the prompt optimizer to propose a trace-backed change, and ship managed prompts, agent specs, tools, and skills with versioning, targeting, and rollout controls.

### Can Logfire replace Braintrust for production evaluation?

Yes. Logfire combines online and offline Pydantic Evals, annotation queues, no separate per-score meter, trace-backed prompt optimization, and managed configuration with the full production context around an agent: browser, services, databases, logs, metrics, and infrastructure.

## Ready to switch from Braintrust?

Get started with 10 million free spans, logs, and metrics per month. No credit card required.

Start free: https://logfire.pydantic.dev/login?intent=signup — [View pricing](https://pydantic.dev/pricing)

---

See also: [Logfire alternatives](https://pydantic.dev/logfire/alternatives) ([markdown](https://pydantic.dev/logfire/alternatives.md)), [Pydantic Logfire](https://pydantic.dev/logfire), and [pricing](https://pydantic.dev/pricing).