perplexity-rate-limits
Sets up exponential backoff and request queuing to handle Perplexity API rate limits.
Install
mkdir -p .claude/skills/perplexity-rate-limits && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/8280" && unzip -o skill.zip -d .claude/skills/perplexity-rate-limits && rm skill.zipInstalls to .claude/skills/perplexity-rate-limits
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Implement Perplexity rate limiting, backoff, and request queuing.Key capabilities
- →Implement exponential backoff with jitter for API requests
- →Queue Perplexity API requests to manage rate limits
- →Utilize a token bucket algorithm for fine-grained rate control
- →Handle HTTP 429 and 5xx errors with retry logic
- →Space requests 1.2 seconds apart to avoid burst rate limits
How it works
The skill implements exponential backoff with jitter to retry failed requests and uses queue-based or token bucket mechanisms to control request rates.
Inputs & outputs
When to use perplexity-rate-limits
- →Handling 429 errors
- →Implementing retry logic
- →Optimizing request throughput
About perplexity-rate-limits
It implements resilient request patterns to handle 429 status codes and optimize API throughput. It includes code for exponential backoff with jitter to ensure stable communication with the Perplexity Sonar API.
Implement Perplexity rate limiting, backoff, and idempotency patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for Perplexity. Trigger with phrases like "perplexity rate limit", "perplexity throttling", "perplexity 429", "perplexity retry", "perplexity backoff".
Prerequisites
Limitations
- →Rate limits apply per API key, not per model
- →Free/Starter tier has a 50 RPM limit
- →Search API has a limit of approximately 3 requests/second
How it compares
This skill automates retry logic and request queuing, unlike manually managing API call timing and error handling.
Compared to similar skills
perplexity-rate-limits side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| perplexity-rate-limits (this skill) | 0 | 2mo | No flags | Intermediate |
| exa-performance-tuning | 3 | 2mo | Review | Intermediate |
| documenso-performance-tuning | 0 | 2mo | Review | Intermediate |
| gamma-performance-tuning | 0 | 2mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by jeremylongshore
View all by jeremylongshore →You might also like
exa-performance-tuning
jeremylongshore
Optimize Exa API performance with caching, batching, and connection pooling. Use when experiencing slow API responses, implementing caching strategies, or optimizing request throughput for Exa integrations. Trigger with phrases like "exa performance", "optimize exa", "exa latency", "exa caching", "exa slow", "exa batch".
documenso-performance-tuning
jeremylongshore
Optimize Documenso integration performance with caching, batching, and efficient patterns. Use when improving response times, reducing API calls, or optimizing bulk document operations. Trigger with phrases like "documenso performance", "optimize documenso", "documenso caching", "documenso batch operations".
gamma-performance-tuning
jeremylongshore
Optimize Gamma API performance and reduce latency. Use when experiencing slow response times, optimizing throughput, or improving user experience with Gamma integrations. Trigger with phrases like "gamma performance", "gamma slow", "gamma latency", "gamma optimization", "gamma speed".
juicebox-prod-checklist
jeremylongshore
Execute Juicebox production deployment checklist. Use when preparing for production launch, validating deployment readiness, or performing pre-launch reviews. Trigger with phrases like "juicebox production", "deploy juicebox prod", "juicebox launch checklist", "juicebox go-live".
openevidence-performance-tuning
jeremylongshore
Optimize OpenEvidence clinical query performance and response times. Use when improving latency, optimizing query efficiency, or tuning caching for clinical AI applications. Trigger with phrases like "openevidence performance", "openevidence slow", "optimize openevidence", "openevidence latency", "speed up clinical queries".
v3-mcp-optimization
ruvnet
MCP server optimization and transport layer enhancement for claude-flow v3. Implements connection pooling, load balancing, tool registry optimization, and performance monitoring for sub-100ms response times.