Open engineering utility · pricing snapshot

LLM-as-a-Judge
Cost Calculator

LLM-as-a-judge uses a language model to score an AI system's output against a rubric such as correctness, groundedness, relevance, safety, or task completion. This calculator estimates the judge-model inference bill and the separate observability-platform bill from one normalized monthly workload.

Default answer: 10,000 application traces, 100% ingestion, 100% evaluation, one judge call, and one month of LangSmith Developer retention produce a $95.00 monthly estimate: $45.00 for Claude Sonnet 5 judge tokens, $25.00 for base-trace overage, and $25.00 to upgrade all traces beyond the 14-day base window.

Coverage
5 vendors · 12 public plans
Default judge
Claude Sonnet 5 · $2 input / $10 output per MTok
Default workload
10K traces · 1,500 input + 150 output tokens
Billing dimensions
Events · data volume · retention time
Result states
Exact · lower bound · not computable
Data policy
USD list price before tax · source-dated · no tracking

The normalization work belongs to custom software and AI product engineering because telemetry shape, evaluation coverage, retention, and model routing are architecture decisions before they are invoice lines.

  • Runs in the browser
  • No workload data leaves the page
  • Shareable URL state
  • JSON and CSV export

Interactive cost model

Calculate monthly LLM evaluation cost

Enter application traffic first, then separate telemetry ingestion from judge coverage. Observations and scores affect platform meters. Judge calls and tokens affect model inference.

01 / Workload

Define the workload

Traffic and evaluation coverage

Traffic flows in this order: application traces → sampled traces → evaluated traces → judge calls.

Data volume and retention
Judge model and token shape

Default: Claude Sonnet 5 standard synchronous, uncached, global pricing. The previously announced September 2026 increase was canceled. $2/$10 is now the standard rate. Batch, cache, regional, and tool fees are not applied automatically.

Observability platform plan

02 / Estimate

Monthly result

Exact
Estimated monthly total $95.00

$9.50 per 1K application traces

Ingested traces
10,000
Evaluated traces
10,000
Judge calls
10,000
Judge model
$45.00
Plan fee
$0.00
Usage overage
$25.00
Data overage
$0.00
Extended retention
$25.00
Platform subtotal
$50.00
Event count: ingested base traces
5,000 base traces/month included. One month requests the 400-day extended tier because base retention is 14 days.
  • Monthly USD estimate before tax.
  • One decimal GB equals 1,000,000,000 bytes.
  • Evaluation rate applies after sampling.
  • One sampled application trace maps to one LangSmith base trace.

Transparent calculation chain

LLM-as-a-judge cost formula

The model and platform branches must be calculated separately. A platform may bill every stored event while the judge runs on a sampled subset. Collapsing application traffic, telemetry, scores, and model calls into one trace count hides the main cost drivers.

  1. ingested traces = application traces × sampling rate
  2. evaluated traces = ingested traces × evaluation rate
  3. judge calls = evaluated traces × judge calls per evaluated trace
  4. model cost = judge calls × ((input tokens × input $/MTok) + (output tokens × output $/MTok)) ÷ 1,000,000
  5. processed GB = ingested traces × bytes per trace ÷ 1,000,000,000
  6. GB-months = processed GB × retention months
  7. monthly total = model cost + plan fee + usage overage + data overage + retention cost
Evaluation applies after telemetry sampling. Platform-specific conversion starts only after the normalized workload quantities are known.

Default unit economics

Input cost per call
1,500 × $2 ÷ 1,000,000 = $0.0030
Output cost per call
150 × $10 ÷ 1,000,000 = $0.0015
Total judge cost per call
$0.0045
Judge cost per 1,000 calls
$4.50
Judge cost per 100,000 calls
$450.00
Judge cost per 1,000,000 calls
$4,500.00
Marginal monthly cost changes at 100,000 evaluated traces
Input changeModel-cost changePlatform effectInterpretation
+100 input tokens per judge call+$20.00None directlyLonger rubrics, references, or retrieved context scale input spend linearly.
+10 output tokens per judge call+$10.00None directlyVerbose rationales can outweigh their small token count because output is priced higher.
A second judge call per evaluated trace+$450.00May add another stored scoreMulti-rubric and ensemble evaluation multiply model calls even when trace count is unchanged.
+1 observation per ingested trace$0.00+1 Langfuse unit and +1 Arize span per traceInstrumentation depth can increase platform cost without changing judge inference.
+1 score per evaluated trace$0.00 unless it needs another judge call+1 Langfuse unit and +1 Braintrust scoreA stored score and an LLM call are related but not identical billing events.
+1 month of retention$0.00Depends on fixed window or variable GB-month rateRetention is always a coverage constraint, but only some vendors publish a variable charge.

Compare the meter, not the logo

Three observability billing families

Event count

LangSmith meters base traces. Langfuse counts traces, observations, and scores. Arize counts spans. Braintrust counts stored scores. Event shape changes the invoice even at the same application traffic.

Data volume

Braintrust bills processed GB and Arize AX Pro publishes additional-GB pricing. Bytes per trace depend on prompt length, response length, attributes, metadata, and the number of recorded steps.

Volume × time

Confident AI meters GB-months. Braintrust Pro prices data beyond 30 days. LangSmith uses base and extended trace tiers. Langfuse and Arize publish fixed access windows per plan.

Normalized plan evidence

LLM observability pricing comparison

The table compares public list-price mechanics, not feature quality or vendor suitability. The modeled boundary states exactly when the calculator withholds a total instead of extrapolating an unpublished price.

Public plan fees, meters, allowances, retention, and modeled overages verified August 13, 2026
Vendor / planBase feeMeter and included allowanceRetentionPublished overage usedModeled boundaryFirst-party source
LangSmith Developer$0 · 1 seat5K base traces/month14-day base; 400-day extended$0.005/additional base trace; $0.0025/extended upgradeMore than 1 seat or more than 400 daysLangSmith pricing
LangSmith Plus$39/seat/month10K base traces/month14-day base; 400-day extended$0.005/additional base trace; $0.0025/extended upgradeMore than 400 daysLangSmith pricing
Langfuse Hobby$050K units/month; unit = trace + observation + score30 days data accessNo public Hobby overageUnits above 50K or retention above 30 daysLangfuse pricing; unit definition
Langfuse Core$29/month100K units/month90 days data access$8, $7, $6.50, then $6 per 100K graduated bandsRetention above 90 daysLangfuse pricing
Langfuse Pro$199/month100K units/month3 years data access$8, $7, $6.50, then $6 per 100K graduated bandsRetention above 3 yearsLangfuse pricing
Braintrust Starter$010K scores + 1 GB processed/month14 days$2.50/1K scores; $4/GBRetention above 14 daysBraintrust pricing
Braintrust Pro$249/month50K scores + 5 GB processed/month30 days included; up to 180 days$1.50/1K scores; $3/GB; $0.50/GB/month after 30 daysRetention above 180 daysBraintrust pricing
Arize AX Free$025K spans + 1 GB/month15 daysNo public Free overageEither allowance exceeded or retention above 15 daysArize pricing
Arize AX Pro$50/month50K spans + 10 GB/month30 days$0.0008/additional span; $3/additional GBRetention above 30 daysArize pricing
Confident AI Free$01 GB-monthVariable within GB-month allowanceExcess trace spans are droppedReturns a lower bound above 1 GB-monthConfident AI pricing
Confident AI Starter$200/month5 GB-monthsVariable$1/additional GB-monthNumeric list-price path remains computableConfident AI pricing
Confident AI Team$2,000/month75 GB-monthsVariable$1/additional GB-monthNumeric list-price path remains computableConfident AI pricing

Normalization assumptions: one sampled application trace maps to one LangSmith base trace. One observation maps to one Arize span. Langfuse partial 100K bands are prorated. These are calculator conversions, not vendor-authored workload guarantees.

Reproducible examples

Worked LLM evaluation cost scenarios

Each row names the workload details that change the answer. Totals use the same deterministic functions as the interactive calculator and exclude tax, discounts, and hosted evaluator token fees.

Six reference workloads showing model cost, platform cost, retention behavior, and result state
ScenarioNormalized workloadJudge modelPlatformTotalState and decision meaning
Default LangSmith Developer10K app / 10K ingested / 10K evaluated / 1 month$45.00$50.00: $25 base overage + $25 extended upgrade$95.00Exact. All selected conversions are public.
Production sampling100K app × 25% sampled × 20% evaluated = 5K judge calls; 14-day retention$22.50LangSmith Developer $100.00 base overage$122.50Exact. Sampling reduces both telemetry and downstream judge calls.
Langfuse unit expansion1M ingested; 100K evaluated; 2 observations; 1 score = 3.1M units; 90 days$450.00Core $29 + $219 graduated usage = $248.00$698.00Exact under proration assumption. Observations dominate unit count.
Braintrust score overage100K ingested and evaluated; 100K scores; 1 GB; 30 days$450.00Pro $249 + $75 score overage = $324.00$774.00Exact. Included model credits are not deducted.
Arize AX Pro span overage30K ingested × 2 observations = 60K spans; 0.3 GB; 30 days$135.00Pro $50 + $8 span overage = $58.00$193.00Exact. The public additional-span conversion is applied.
Confident AI Free coverage gap200K traces × 10 KB × 1 month = 2 GB-months$900.00$0.00; only 1 GB-month retained$900.00 lower boundLower bound. Zero fee does not mean full telemetry coverage.

Operational use

How to use the estimate in an evaluation budget

Measure a real trace sample

Export a bounded sample from production or staging. Count application traces, observations, stored scores, prompt tokens, completion tokens, and serialized bytes. A measured median plus a high-percentile scenario is more useful than a generic average trace.

Separate ingestion from evaluation

Set sampling to the telemetry coverage you intend to retain. Set evaluation rate to the subset that receives an LLM judge. A team can ingest 100% for debugging and judge 5% for quality monitoring.

Represent every rubric call

If correctness, groundedness, and safety use separate prompts, enter three judge calls. If they produce three stored scores from one combined call, enter one judge call and three scores. This distinction changes model and platform cost differently.

Stress the retention boundary

Run the intended compliance or debugging window, not the vendor default. A plan may be inexpensive at 14 days and unusable at 90 days even when monthly event volume is unchanged.

Decision rules for common LLM evaluation architectures
Architecture choiceInput to changeExpected cost effectCheck before accepting
Online judge on a production sampleEvaluation rateJudge tokens and stored scores fall; ingested telemetry may notConfirm the sampled set still covers rare failures and high-risk segments.
Multiple rubric promptsJudge calls per evaluated traceToken cost scales with call countCheck whether a combined rubric preserves calibration and diagnostic value.
Verbose chain-of-thought-like rationaleOutput tokensHigh sensitivity at output-token rateRequest only the explanation needed for audit or debugging.
Deep agent tracingObservations and bytes per traceMore Langfuse units, Arize spans, and data volumeDo not record redundant payloads or secrets solely for observability.
Long incident or compliance retentionRetention monthsUpgrade, variable storage, plan change, or not-computable stateValidate legal retention and deletion requirements outside this cost tool.
Self-hosted observabilityNot representedCloud plan fee may disappear; infrastructure and operations appearBuild a separate TCO model for compute, storage, backups, upgrades, and on-call work.

Scope control

What the calculator includes, excludes, and refuses to guess

Included

  • Direct judge-model input and output tokens
  • Judge-call multiplicity
  • Trace sampling and post-sampling evaluation rate
  • Plan and seat fees for listed self-serve tiers
  • Published event, score, span, GB, and GB-month overages
  • Published fixed retention windows and variable retention charges
  • Known lower-bound and not-computable states

Excluded

  • Taxes, currency conversion, discounts, startup credits, and negotiated contracts
  • Prompt caching, batch API discounts, data residency multipliers, and tool-specific model fees
  • Platform-hosted online-evaluator token charges
  • Human annotation, rubric design, calibration, and adjudication labor
  • Application inference outside the judge calls
  • Self-hosted compute, storage, networking, backups, security, and maintenance
  • Business value, model quality, latency, reliability, and vendor feature fit

Failure modes that can invalidate a cost estimate

Common modeling errors, their direction of bias, and the corrective check
Failure modeLikely biasWhy it happensCorrective check
Treating one trace as one billable unit everywhereUnderstates platform costA trace can contain many observations, spans, and scores.Inspect each vendor's meter and count the matching stored objects.
Applying evaluation rate before telemetry samplingMisstates both branchesThe two percentages describe different gates.Calculate ingested traces first, then evaluated traces.
Equating a stored score with a judge callCan overstate or understate model costOne call can emit several scores; repeated calls can emit one final score.Count actual model invocations and stored score objects separately.
Using 10 KB as an invariantEither directionTrace payload varies with prompts, outputs, metadata, and instrumentation depth.Measure serialized bytes from a representative workload sample.
Ignoring retentionUnderstates charge or overstates coverageSome plans have short fixed windows or paid extended storage.Run the required retention window and inspect the result state.
Subtracting platform credits from direct model costUnderstates model spendCredits may cover only vendor-hosted features or built-in models.Keep provider-billed tokens separate unless a contract proves the offset.
Reading free as unlimitedOverstates coverageFree tiers can stop ingestion, drop excess spans, or omit overage prices.Check both allowance and behavior after the allowance.
Treating a dated snapshot as a quoteUnknownVendors can change prices and plan terms after verification.Reopen the linked first-party page before a purchase or renewal.

Entity definitions

LLM evaluation and observability glossary

Application trace
One end-to-end application operation before the calculator applies telemetry sampling. Depending on the system, it may represent a chat turn, agent run, retrieval request, or workflow execution.
Ingested trace
An application trace sent to the observability platform after sampling. This calculator assumes one sampled application trace becomes one vendor trace where a trace-based meter is used.
Evaluated trace
An ingested trace selected for scoring after the evaluation rate is applied. It may receive zero, one, or several judge calls and stored scores.
Observation
A recorded step inside a trace, such as an LLM generation, tool call, retrieval, event, or span. Langfuse counts observations as units; the Arize conversion treats observations as spans.
Score
A stored quality result such as correctness, relevance, groundedness, safety, or task completion. A score may come from an LLM judge, code evaluator, human annotator, or user feedback.
Judge call
One invocation of the judge model. Multiple rubric prompts, retries, debate, or ensemble voting can create multiple calls for one evaluated trace.
LLM-as-a-judge
An evaluation method in which a language model applies explicit criteria to another model's output and returns a label, score, comparison, rationale, or structured verdict.
MTok
One million tokens, the unit used for model input and output pricing. Provider tokenizers can produce different counts for the same text.
Processed GB
Decimal gigabytes derived here from ingested traces multiplied by bytes per trace, divided by one billion. Vendor definitions can include or exclude different payload components.
GB-month
One gigabyte retained for one month. It combines data volume and time, so either larger traces or longer retention raises the measured quantity.
Exact result
Every selected component has a public numeric conversion, the workload stays within supported windows, and calculator assumptions are stated.
Lower-bound result
The known cost is calculable but full requested coverage is not delivered. The displayed amount is a floor, not a complete equivalent service.
Not-computable result
A necessary price is unpublished or a fixed retention boundary is exceeded. Known subtotals remain visible, while total and cost per 1,000 traces are withheld.

Focused answers

LLM-as-a-judge cost FAQ

How much does one LLM-as-a-judge evaluation cost?

With the default 1,500 input tokens, 150 output tokens, and Claude Sonnet 5 rates of $2 and $10 per million tokens, one judge call costs $0.0045 before platform charges. Change model rates and token shape for another model or rubric.

Are trace sampling and evaluation rate the same?

No. Sampling controls which application traces are ingested. Evaluation rate is applied after sampling and controls which ingested traces receive judge calls. Ingesting 100% and evaluating 5% preserves broad debugging coverage while limiting judge inference.

How should multiple judges or rubric dimensions be entered?

Count model invocations in the judge calls per evaluated trace field and persisted outputs in scores per evaluated trace. Three separate rubric prompts usually mean three calls and three scores. One combined prompt returning three dimensions means one call and three scores.

Why can a result be not computable?

The state appears when a required public conversion is absent or the requested retention exceeds a published fixed window. Known components remain visible, but the calculator does not invent the missing charge.

Does the calculator include hosted evaluator token fees?

No. The judge-model estimate assumes direct provider billing. Platform-hosted evaluator charges, plan credits, caching, batch discounts, taxes, and negotiated discounts are excluded. Enter a custom effective token rate only when the billing contract supports it.

Can this compare a self-hosted observability stack?

Not directly. Self-hosting replaces some SaaS fees with compute, object storage, databases, backups, upgrades, security controls, and engineering operations. Those costs require a separate total-cost-of-ownership model.

Ownership and evidence

Sources, authorship, and correction policy

Maintainer and publisher

Maintained by Dmytro Nasyrov, Founder & CTO of Pharos Production. Published by Pharos Production as an open engineering utility.

Relevant credential
PhD in Artificial Intelligence
Version
1.1.0
Published
Pricing semantically verified
Independent review
Independent external review is not claimed.

AI-assisted disclosure

This page and its implementation were AI-assisted. Numeric pricing fields were checked against linked first-party pages, normalized into a public dataset, and exercised by deterministic tests. AI assistance is not a substitute for vendor confirmation or independent review.

Verification boundary

Source-level semantic verification and URL monitoring are different controls. The scheduled reachability check detects unreachable source URLs but does not verify pricing semantics. A person must review plan meaning before changing the registry date or numeric fields.

Correction and update policy

Report a price, formula, source, or accessibility defect through GitHub Issues. A correction must identify the affected claim, first-party source, effective date when known, code path, test impact, and changelog entry. Historical releases remain in Git.