πŸ“˜ Understanding Credits in Lyzr Agent Studio

Lyzr Agent Studio uses a credit-based compute system to manage infrastructure usage, ensure system fairness, and optimize for both low-latency experimentation and high-throughput production.

Every action that invokes computation β€” whether model inference, semantic indexing, or multi-agent orchestration β€” is metered in terms of credits. This allows users to monitor and scale usage predictably across plans.


πŸ”Ή Credit Allocation and Plans

Lyzr credits are provisioned based on your account’s subscription tier. Credits reset or replenish on a fixed schedule and can be supplemented as needed.

Free Tier

  • 500 credits/month automatically provisioned to each new account.
  • These credits refresh monthly based on your signup date.
  • Ideal for trying out agents, creating simple RAG flows, and basic API calls.
  • Credit allocation scales with plan level (Starter, Pro, Enterprise).
  • Plans are available on monthly or annual billing cycles.
  • Top-ups can be purchased at any time.

One-Time Top-Ups

  • Used to prevent service interruptions when monthly quota is exhausted.
  • Credits from top-ups do not expire.
  • Stackable with recurring plan credits.

πŸ”Ή What Consumes Credits?

Lyzr’s platform operations are broken down into credit-metered units. The following subsystems contribute to credit consumption:

1. Language Model Inference

  • Token-based billing per LLM (similar to OpenAI’s pricing model).
  • Models have differing price-per-token multipliers:
ModelRelative Credit UsageTypical Use Case
GPT-4o Mini1Γ—Lightweight chatbots, simple instructions
GPT-4o16Γ—Strategic reasoning, agents with memory
Claude Haiku2Γ—Midweight contextual interactions
Claude Opus15–20Γ—Deep reasoning and multi-hop workflows

πŸ’‘ Heavier models yield higher accuracy, but also consume more tokens. Choose based on your use case.


2. Token Length: Input + Output

  • Lyzr computes usage on the combined token length of:
    • Prompt (agent logic, user input, KB context)
    • Response (model output)
  • This includes:
    • RAG-pulled knowledge
    • Agent history (if memory is enabled)
    • Instruction chains and multi-agent dependencies

Example: A long SQL-generating prompt with schema context and 500-word response can consume up to 3–5Γ— more credits than a standard chat exchange.


3. Platform Features & Services

FeatureCredit UsageNotes
MemoryFreeStores interaction context for multi-turn dialogue. No credit cost.
Tools ExecutionFixed CostEach invocation of a 3P integration (e.g., Slack, Gmail) uses credits.
Knowledge Base (Classic)IndirectNo feature cost, but large documents increase prompt size.
Semantic ModelIndirect + InferenceEmbeds tabular metadata, uses credits when LLM is invoked.
Knowledge GraphIndirect + ProcessingGraph traversal + node summarization incurs token load.
Context Relevance FilteringModerateAdds LLM-based ranking layer over retrieved chunks.
Groundedness ChecksFixed per usePost-response factuality validation using internal validators.
Responsible AI ModulesVariableCost depends on number of submodules invoked (e.g., hallucination, profanity).

πŸ”Ή Credit Consumption Examples

ScenarioApproximate Credit Cost
Simple agent query using GPT-4o Mini1–2 credits
Tool-based agent querying Gmail + Slack10–25 credits
RAG agent using 5 PDF files with GPT-420–60 credits
Text-to-SQL with Semantic Model (with schema + sample rows)15–50 credits
Agent using Claude Opus with Context Relevance + RAI80–120 credits

These values are estimates and depend on prompt structure and content size.


πŸ”Ή Credit Management Best Practices

To avoid excessive credit burn, especially on larger workloads:

  • βœ… Use light models (GPT-4o Mini, Haiku) during development and testing.
  • βœ… Limit file size and chunk count in KBs when setting up RAG.
  • βœ… Disable unnecessary modules like RAI or Groundedness for internal use-cases.
  • βœ… Use preview tools in Studio to inspect prompt-token size before triggering agent run.

πŸ”Ή Monitoring Credit Usage (Coming Soon)

Lyzr will soon support in-dashboard analytics to monitor:

  • Credit burn by agent
  • Model-specific usage
  • Peak usage windows
  • Alerts for low-credit thresholds

πŸ”Ή Credit Expiry and Overflow

Plan TypeExpiry RulesOverflow Handling
Free PlanResets every 30 daysNo rollover
Monthly PlanResets monthlyNo rollover unless top-up applied
Annual PlanRenewed annuallyQuota spreads evenly or loaded in full
One-Time Top-UpNever expiresUsed after subscription credits are exhausted

Summary

ComponentRole
CreditsUnit of Lyzr compute usage
Tracked DimensionsModel, token count, tools, features
ReplenishmentMonthly/annual plans or one-time top-ups
MonitoringIn progress (dashboard reporting soon)
OptimizationChoose light models, minimize token overhead, selective tools

With this understanding, developers and builders on Lyzr can architect intelligent agents efficiently and affordably, optimizing both performance and compute cost.