Per-Log Pricing: Examples & Companies

3 companies in the corpus Updated stub analysis
Definition

Per-Log Pricing is a billing unit where each LLM request log ingested or stored is metered — common in AI observability and evaluation platforms.

Also known as: Log Ingestion PricingLog-Based Billing

What is it

Per-log pricing is a billing unit where each LLM request log ingested or stored is metered — common in AI observability and evaluation platforms.

Each log represents one LLM call: the prompt sent, the response received, latency, token counts, model used, and cost estimate. Helicone, Humanloop, and Portkey meter these logs (Portkey and Helicone also call the unit a “request”) because more logs mean more storage, indexing, and analytics compute — the billing unit maps directly to the infrastructure cost driver.

None of these platforms resell model tokens: users bring their own OpenAI or Anthropic keys and pay providers directly, while the vendor charges for the logged workflow layer. That makes the log — not the token or the seat — the load-bearing pricing unit, the LLM-observability parallel to per-event pricing in traditional APM. For a primer on why a vendor picks logs over tokens, see choosing the right usage metric.

Every LLM call is one log — the allowance fills, then overage meters
1 LLM call = 1 log · free allowance fills, then $9 per 100K LLM CALLS LOG METER 100K included · $49 then +$9 / 100K Portkey · Developer 10K free $130 1M logs / mo $49 + 9 × $9 ~$310 cap at 3M then Enterprise Not tokens — you bring your own key. Helicone & Humanloop meter the same log unit; retention tiers stack a second cost on top of volume.

How it works

Per-log billing increments a counter each time a request flows through the observability proxy or the logging SDK reports a completed LLM call. The platform stores the request/response pair, metadata, and derived metrics (latency, cost estimate, token counts), aggregates monthly volume, and bills it against the plan allowance.

CompanyLog unitFree tierPaid entry
PortkeyOne recorded log per gateway requestDeveloper: 10,000 logs/mo, 3-day retentionProduction $49/mo — 100K logs, then $9 per 100K requests (up to 3M)
HeliconeOne LLM request/response pairHobby: 10,000 requests/mo, 1 GB, 7-day retentionPro $79/mo, Team $799/mo — 10K req + 1 GB, then usage-based overage
HumanloopOne prompt/tool/evaluator/flow callFree trial: 10,000 logs/mo (now sunset)Historical: datapoint tiers ($100 / $1,000), then log-metered Enterprise

The unit math is clearest with Portkey’s published rate. A production app generating 1,000,000 logged requests a month pays the $49 base plus overage on the 900,000 requests above the 100,000 included: $49 + (9 × $9) = $130. The overage ladder stops at 3M requests, capping self-serve spend at roughly $310/month before an Enterprise contract is required.

Helicone instead bundles logs with storage: Pro ($79) and Team ($799) each include 10,000 requests plus 1 GB, then meter usage-based overage on both logs and storage — its calculator estimates roughly $0.97/month for 10,000 requests with light storage. Retention is the second lever across all three: it climbs with plan tier (Portkey 3-day → 30-day; Helicone 7-day → 1-month → 3-month), so a customer on a longer retention window effectively pays more per log even at the same ingestion volume. Humanloop additionally counted every evaluation run and human judgment as a log, so eval-heavy workloads consumed quota faster than raw traffic alone. For how these meters aggregate usage events into a bill, see usage-based pricing strategy.


Companies using this

Three companies in the corpus meter LLM request logs as a primary billing unit: Portkey with a transparent $49 Production plan and a published $9-per-100K overage rate, Helicone with the most generous storage-inclusive free tier and Pro/Team overage on logs and storage, and Humanloop, which metered logs before Anthropic acqui-hired its team and the platform was sunset in 2025. All three targeted engineering teams running production LLM applications who need visibility into prompt quality, cost, and latency.


Company Product Pricing modelBilling unitsFree tier Verified
HeliconeOpen-source LLM observability & AI gatewayYes2026-06-09
HumanloopLLM evals, prompt management & observabilityYes2026-06-09
PortkeyAI gateway & LLMOps governance platformYes2026-06-10

Explore this theme in the knowledge graph

FAQ

What is per-log pricing in LLM observability platforms?

Per-log pricing meters each LLM API call captured and stored as a log record. Helicone, Humanloop, and Portkey all use log (or request) volume as a primary billing dimension: every time an application calls an LLM through the observability proxy or SDK, that call creates a log. Free tiers are deliberately generous — Helicone and Portkey both include 10,000 free logs per month — because the logs are the product without which the observability features have nothing to analyze.

How much do per-log observability platforms charge?

Portkey is the clearest published example: its Developer plan is free with 10,000 recorded logs per month, and Production is $49/month including 100,000 recorded logs, then $9 per additional 100,000 requests up to a 3M ceiling. Helicone's Hobby tier is free with 10,000 requests per month, and its $79 Pro and $799 Team plans include 10,000 requests plus 1 GB storage before usage-based overage applies. Humanloop metered logs before its 2025 shutdown but never republished a self-serve per-log rate.

How does retention affect per-log pricing?

Log retention adds a second cost dimension on top of the per-log rate. Platforms tier retention alongside volume: Helicone retains Hobby logs for 7 days, Pro for 1 month, and Team for 3 months, while Portkey retains Developer logs for 3 days and Production logs for 30 days. Longer retention windows require higher-priced plans, so for high-frequency LLM applications storage retention can drive as much cost as ingestion volume.

Is per-log pricing the same as per-token pricing?

No. Per-token pricing meters the raw input and output tokens an LLM processes and is charged by the model provider. Per-log pricing meters the observability record created for each call — one log per request regardless of how many tokens it contained. Helicone, Humanloop, and Portkey never resold model tokens; users bring their own provider keys and pay for the logged workflow layer instead.

Related billing units

Back to companies