Skip to main content
Lyzr Agent Studio uses a credit-based compute system to meter infrastructure usage and let you predict costs at a glance. Every action that invokes computation (model inference, semantic indexing, multi-agent orchestration) is measured in credits. One credit equals $1.

Credit allocation and plans

Lyzr credits are provisioned based on your subscription tier and reset or replenish on a fixed schedule. Top-ups can be purchased at any time and are stackable with plan credits.
PlanCreditsNotes
Free$20 credits/monthResets monthly on your signup date. No rollover.
Starter, Pro, EnterpriseScales with plan levelMonthly or annual billing.
One-time top-upAny amountCredits do not expire. Used after subscription credits are exhausted.

What consumes credits

Language model inference

Credits are deducted based on token count multiplied by a per-model rate. Heavier models consume more credits per token.
ModelRelative credit usageTypical use case
GPT-4o Mini1xLightweight chatbots, simple instructions
GPT-4o16xStrategic reasoning, agents with memory
Claude Haiku2xMid-weight contextual interactions
Claude Opus15-20xDeep reasoning and multi-hop workflows

Token length

Lyzr computes usage on the combined token length of the prompt (agent logic, user input, Knowledge Base context) and the response (model output). This includes RAG-retrieved knowledge, agent history when memory is enabled, and instruction chains in multi-agent workflows. A long SQL-generating prompt with schema context and a 500-word response can consume three to five times more credits than a standard chat exchange.

Platform features

FeatureCredit usageNotes
MemoryFreeStores interaction context for multi-turn dialogue.
Tools executionFixed per invocationEach call to a third-party integration (Slack, Gmail, and others) uses credits.
Knowledge BaseIndirectNo direct feature cost, but large documents increase prompt size.
Semantic ModelIndirect + inferenceEmbeds tabular metadata; credits are used when the LLM is invoked.
Knowledge GraphIndirect + processingGraph traversal and node summarization add token load.
Context RelevanceModerateAdds an LLM-based ranking layer over retrieved chunks.
Groundedness checksFixed per usePost-response factuality validation using internal validators.
Responsible AIVariableCost depends on the number of submodules invoked.

Credit consumption examples

These values assume 1 credit = $1. Typical usage results in fractional deductions.
ScenarioApproximate cost
Simple agent query using GPT-4o Mini0.01 - 0.02 credits
Tool-based agent querying Gmail + Slack0.10 - 0.25 credits
RAG agent using 5 PDF files with GPT-40.20 - 0.60 credits
Text-to-SQL with Semantic Model (with schema + sample rows)0.15 - 0.50 credits
Agent using Claude Opus with Context Relevance + Responsible AI0.80 - 1.20 credits

Credit management best practices

To avoid excessive credit burn on larger workloads:
  • Use light models (GPT-4o Mini, Claude Haiku) during development and testing.
  • Limit file size and chunk count in Knowledge Bases when setting up RAG.
  • Disable Responsible AI and Groundedness modules for internal use cases that don’t require them.
  • Use the prompt preview tools in Agent Studio to inspect token size before triggering an agent run.

Credit expiry and overflow

Plan typeExpiryOverflow handling
FreeResets every 30 daysNo rollover
Monthly planResets monthlyNo rollover unless a top-up is applied
Annual planRenewed annuallyQuota spreads evenly or loads in full
One-time top-upNever expiresApplied after subscription credits are exhausted

Monitoring credit usage

In-dashboard analytics for credit burn by agent, model-specific usage, peak usage windows, and low-credit alerts are coming soon.
Want to know exactly what each agent run costs by type? See Pricing for per-run rates broken down by agent complexity.