> ## Documentation Index
> Fetch the complete documentation index at: https://praison.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Caching
> Cache LLM responses to reduce costs and latency with a single parameter
Caching stores LLM responses to avoid redundant API calls, cutting costs and speeding up repeat queries.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="Assistant",
instructions="Answer customer support questions.",
caching=True,
)
agent.start("What is your return policy?")
```
The user asks the same support question again; a cache hit returns the prior answer without another LLM call.
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph LR
subgraph "Caching Flow"
Request[📝 Request] --> Check{🔍 Cache?}
Check -->|Hit| Return[⚡ Instant Return]
Check -->|Miss| LLM[🤖 LLM API]
LLM --> Store[💾 Store Result]
Store --> Return
end
classDef request fill:#6366F1,stroke:#7C90A0,color:#fff
classDef cache fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef result fill:#10B981,stroke:#7C90A0,color:#fff
class Request request
class Check,Store cache
class LLM,Return result
```
## Quick Start
Enable caching with a single flag — identical requests return instantly from cache.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="Support Bot",
instructions="You are a helpful assistant.",
caching=True,
)
agent.start("Summarise the benefits of caching.")
```
Pass `"prompt"` to enable provider-level prompt caching alongside response caching.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="Support Bot",
instructions="You are a helpful assistant.",
caching="prompt",
)
agent.start("Summarise the benefits of caching.")
```
Use `CachingConfig` to control response caching and provider-level prompt caching separately.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, CachingConfig
agent = Agent(
name="Researcher",
instructions="Answer research questions using memory.",
llm="anthropic/claude-3-5-sonnet",
caching=CachingConfig(
enabled=True,
prompt_caching=True,
),
)
agent.start("What are the cost savings from prompt caching?")
```
***
## How It Works
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
sequenceDiagram
participant User
participant Agent
participant Cache
participant LLM
User->>Agent: "What is the return policy?"
Agent->>Cache: Check for cached response
alt Cache hit
Cache-->>Agent: Return stored response
else Cache miss
Agent->>LLM: Send request to LLM API
LLM-->>Agent: Response
Agent->>Cache: Store response
end
Agent-->>User: Response
```
| Phase | What happens |
| ------------------- | ----------------------------------------------------------------- |
| 1. Request received | Agent checks the cache using the request as key |
| 2. Cache hit | Stored response returned instantly — no API cost |
| 3. Cache miss | LLM processes the request, result stored for next time |
| 4. Prompt caching | Provider caches stable prefix (system prompt, tools) across turns |
***
## Choosing Your Caching Level
```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
graph TB
Start([Start]) --> Q1{Repeat same
questions?}
Q1 -->|Yes| RC[Response Caching
caching=True]
Q1 -->|No| Q2{Large stable
system prompt?}
Q2 -->|Yes| PC[Prompt Caching
prompt_caching=True]
Q2 -->|No| NC[No caching needed]
classDef decision fill:#F59E0B,stroke:#7C90A0,color:#fff
classDef action fill:#10B981,stroke:#7C90A0,color:#fff
classDef start fill:#6366F1,stroke:#7C90A0,color:#fff
class Q1,Q2 decision
class RC,PC,NC action
class Start start
```
***
## Configuration Options
Full list of options, types, and defaults — `CachingConfig`
| Option | Type | Default | Description |
| ---------------- | -------------- | ------- | -------------------------------------------------------- |
| `enabled` | `bool` | `True` | Enable or disable response caching |
| `prompt_caching` | `bool \| None` | `None` | Enable provider-level prompt caching (Anthropic, Google) |
***
## Common Patterns
### Pattern 1 — FAQ Bot with response caching
Identical user questions are answered from cache, saving API calls.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent
agent = Agent(
name="FAQ Bot",
instructions="Answer frequently asked questions about our product.",
caching=True,
)
response1 = agent.start("What are your business hours?")
response2 = agent.start("What are your business hours?") # cache hit
```
### Pattern 2 — Research agent with prompt caching
Large system prompts and tool definitions are cached at the provider level, reducing token costs on every turn.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, CachingConfig
agent = Agent(
name="Research Assistant",
instructions="You are an expert research assistant with access to a large knowledge base.",
llm="anthropic/claude-3-5-sonnet",
memory=True,
caching=CachingConfig(
enabled=True,
prompt_caching=True,
),
)
agent.start("Summarise last month's findings on climate data.")
agent.start("What trends stand out?") # stable prefix cached
```
### Pattern 3 — Disable caching for real-time data
Turn off caching when responses must always be fresh.
```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}}
from praisonaiagents import Agent, CachingConfig
agent = Agent(
name="Live Prices",
instructions="Report real-time stock prices.",
caching=CachingConfig(enabled=False),
)
agent.start("What is the current price of AAPL?")
```
***
## Best Practices
Caching delivers the most value when users ask similar questions repeatedly — support bots, FAQ systems, and document Q\&A are ideal candidates. Start with `caching=True` and measure cache-hit rates before adding configuration.
If your `instructions` string is long (policies, personas, tool lists), setting `prompt_caching=True` caches the stable prefix at the provider level. This reduces per-turn token cost significantly on Anthropic and Google models.
Pricing feeds, live dashboards, and highly personalised answers change on every request. Set `CachingConfig(enabled=False)` to bypass the cache entirely and always call the LLM.
Pairing `caching=True` with `memory=True` lets the agent recall past sessions while still serving cached responses for repeated questions — fewer API calls and consistent answers.
***
## Related
Prompt Caching — provider-level caching for stable context
Prompt Cache Optimization — tips to maximise cache hit rates