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.
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.
| Company | Log unit | Free tier | Paid entry |
|---|---|---|---|
| Portkey | One recorded log per gateway request | Developer: 10,000 logs/mo, 3-day retention | Production $49/mo — 100K logs, then $9 per 100K requests (up to 3M) |
| Helicone | One LLM request/response pair | Hobby: 10,000 requests/mo, 1 GB, 7-day retention | Pro $79/mo, Team $799/mo — 10K req + 1 GB, then usage-based overage |
| Humanloop | One prompt/tool/evaluator/flow call | Free 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.
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
- Credit-Based BillingA billing unit where customers pre-purchase or are allocated a pool of credits that deplete as they use the product, often at variable rates per feature.
- Token-Based PricingA billing unit common in LLM and AI products, where customers are charged per input and output token processed.
- Per-Seat PricingA billing unit where the vendor charges a fixed fee per named user, regardless of how much each user consumes.
- Per-Resolution PricingA billing unit unique to AI customer-support products, where the vendor charges only when an AI agent resolves a customer issue without escalation.
- Bandwidth-Based PricingA billing unit where customers are charged per gigabyte of data transferred out of the platform.
- Per-Function-Invocation PricingA billing unit where customers are charged per serverless function invocation, often combined with a separate compute-time charge.
- CPU-Hour PricingA billing unit where customers are charged for the CPU time their workloads consume, typically measured in vCPU-seconds or vCPU-hours.
- GB-Hour PricingA billing unit where customers are charged for the memory their workloads consume over time, measured in gigabyte-hours.
- GPU-Hour PricingA billing unit where customers are charged for GPU time consumed, typically measured per-second or per-hour by GPU type.
- Per-API-Call PricingA billing unit where customers are charged per API request, regardless of payload size or processing time.
- Per-GB Storage PricingA billing unit where customers are charged per gigabyte of data stored on the platform per month.
- Media-Minute PricingA billing unit where customers are charged per minute of audio or video processed — used by speech, voice, and video AI vendors.
- Per-Request PricingA billing unit where customers are charged per request served — the generic meter for inference endpoints, search, scraping, and browser infrastructure.
- Per-Event PricingA billing unit where customers are charged per event ingested — the native meter of observability and billing-infrastructure platforms.
- Vector Storage PricingA billing unit where customers are charged for vectors stored or indexed — the storage dimension of vector database pricing.
- Per-Character PricingA billing unit where customers are charged per character of text processed — the standard meter for text-to-speech and translation.
- Per-Document PricingA billing unit where customers are charged per document processed or generated — common in AI writing, SEO, and document-intelligence tools.
- Per-Page PricingA billing unit where customers are charged per page crawled, parsed, or rendered — the meter for web scraping and document parsing.
- Per-Transaction PricingA billing unit where customers are charged per financial or billing transaction processed — the meter of billing and accounting platforms.
- Active-User PricingA billing unit where customers are charged per monthly or daily active user rather than per provisioned seat.
- Per-Task PricingA billing unit where customers are charged per task an automation or agent executes — Zapier's historical unit, now spreading to AI agents.
- Per-Unit PricingA billing unit used by robotics, hardware AI, and some SaaS companies where the metered object is a physical or abstract 'unit' — a robot deployed, a device sold, or a defined deliverable.
- Workflow Execution PricingA billing unit where each end-to-end workflow or automation run is metered and billed, regardless of the compute steps it contains.
- Per-Message PricingA billing unit where each individual message or reply in a conversation is metered, common in AI chat and voice platforms.
- Per-Invoice PricingA billing unit used by billing infrastructure platforms where each invoice generated or processed is metered as the primary cost driver.
- Per-Action PricingA billing unit where each discrete action taken by an AI agent or automation is metered — common in browser automation and agentic workflow tools.
- Per-Image PricingA billing unit where each AI-generated image is metered, common in image generation APIs and multimodal AI platforms.
- Per-Conversation PricingA billing unit where each complete customer conversation — from first message to resolution — is metered as a single chargeable event.
- Per-Record PricingA billing unit where each data record processed, labeled, or extracted is metered — common in data platforms and web scraping services.
- Per-Word PricingA billing unit common in translation and localization platforms where the metered object is the word count of content processed.
- Per-Video PricingA billing unit where each AI-generated video is metered, common in video generation and synthetic media platforms.
- Milestone-Based PricingA billing unit used in drug discovery and biotech AI where payment is tied to achieving defined research milestones rather than time or compute consumed.
- Per-Outcome PricingA billing unit where payment is triggered by verified outcomes delivered — distinct from outcome-based pricing models, this refers specifically to 'outcomes' as a countable billing unit.
- Per-Datapoint PricingA billing unit where each individual data measurement or signal ingested is metered — common in cloud cost intelligence and ML evaluation platforms.
- Per-Interaction PricingA billing unit where each patient-agent or user-agent interaction is metered, common in healthcare AI and customer engagement platforms.
- Data Licensing PricingA pricing structure where access to proprietary datasets or data assets is licensed separately from the software or services, common in AI training data and clinical data platforms.
- Robot-Hour PricingA billing unit where each hour a robot or autonomous system operates is metered — the robotics equivalent of a GPU-hour.
- Per-Contact PricingA billing unit where each contact or lead in the database is metered, common in AI sales development and outbound automation platforms.
- Per-Mailbox PricingA billing unit where each connected email mailbox or sending account is metered, common in AI outbound sales and email automation platforms.
- Browser-Hour PricingA billing unit where each hour of headless browser compute time is metered, common in web scraping and browser automation platforms.
- Per-Generation PricingA billing unit where each AI-generated creative asset — image, video, or design — is counted as a 'generation' and metered accordingly.
- Per-Ticket PricingA billing unit where each customer support ticket handled by an AI agent is metered — common in AI customer service platforms.
- Per-Trace PricingA billing unit where each distributed trace — a complete record of an LLM request chain — is metered, common in AI observability platforms.
- Per-IP PricingA billing unit where each IP address or proxy endpoint allocated is metered — used by web scraping proxy providers.
- Per-Device PricingA billing unit where each hardware device or endpoint connected to the AI platform is metered.
- Per-Case PricingA billing unit used in legal AI platforms where each case or matter processed by the AI is metered.
- Per-Report PricingA billing unit where each AI-generated report or analysis document is metered as a discrete output.