clade-rate-limits

Included with Lifetime

$97 forever

Handle Anthropic rate limits — understand tiers, implement backoff, Use when working with rate-limits patterns. optimize throughput, and monitor usage. Trigger with "anthropic rate limit", "claude 429", "anthropic throttling", "anthropic usage limits", "claude tokens per minute".

AI Agentssaasanthropicclauderate-limits

What this skill does

# Anthropic Rate Limits

## Overview

Anthropic enforces three types of limits: requests per minute (RPM), input tokens per minute (TPM), and output tokens per minute. Limits depend on your spend tier.

## Rate Limit Tiers

| Tier | Qualification | RPM | Input TPM | Output TPM |
|------|--------------|-----|-----------|------------|
| Tier 1 | Free | 50 | 40,000 | 8,000 |
| Tier 2 | $40+ spend | 1,000 | 80,000 | 16,000 |
| Tier 3 | $200+ spend | 2,000 | 160,000 | 32,000 |
| Tier 4 | $400+ spend | 4,000 | 400,000 | 80,000 |
| Scale | Custom | Custom | Custom | Custom |

> **Check your tier:** console.anthropic.com → Settings → Limits

## Response Headers

Every API response includes rate limit headers:

```
claude-ratelimit-requests-limit: 1000
claude-ratelimit-requests-remaining: 998
claude-ratelimit-requests-reset: 2025-01-01T00:01:00Z
claude-ratelimit-tokens-limit: 80000
claude-ratelimit-tokens-remaining: 79500
claude-ratelimit-tokens-reset: 2025-01-01T00:01:00Z
retry-after: 5
```

## Built-In SDK Retries

The SDK automatically retries 429 and 529 errors with exponential backoff:

```typescript
import Anthropic from '@claude-ai/sdk';

const client = new Anthropic({
  maxRetries: 3, // default: 2. Set to 0 to disable.
});
```

## Custom Backoff

```typescript
async function callWithBackoff(params: Anthropic.MessageCreateParams, maxRetries = 5) {
  for (let attempt = 0; attempt < maxRetries; attempt++) {
    try {
      return await client.messages.create(params);
    } catch (err) {
      if (err instanceof Anthropic.RateLimitError) {
        const retryAfter = Number(err.headers?.['retry-after'] || 2 ** attempt);
        const jitter = Math.random() * 1000;
        console.log(`Rate limited. Retry in ${retryAfter}s (attempt ${attempt + 1})`);
        await new Promise(r => setTimeout(r, retryAfter * 1000 + jitter));
      } else {
        throw err;
      }
    }
  }
  throw new Error('Exceeded max retries');
}
```

## Throughput Optimization

| Strategy | Impact |
|----------|--------|
| Use Message Batches API | Bypasses rate limits entirely (async, 24h SLA) |
| Use prompt caching | Cached tokens don't count toward input TPM |
| Use smaller models for simple tasks | Lower token counts = more requests per minute |
| Pre-count tokens with `countTokens` | Avoid wasted requests that will fail |
| Queue and batch requests | Smooth out bursts |

## Token Counting

```typescript
// Count before sending — avoid burning RPM on requests that'll fail
const count = await client.messages.countTokens({
  model: 'claude-sonnet-4-20250514',
  messages,
  system: systemPrompt,
});
console.log(`This request will use ${count.input_tokens} input tokens`);
```

## Python

```python
import anthropic
import time

client = anthropic.Anthropic(max_retries=5)

# Or manual handling:
try:
    message = client.messages.create(...)
except anthropic.RateLimitError as e:
    retry_after = float(e.response.headers.get("retry-after", 5))
    time.sleep(retry_after)
```

## Output

- Rate limit tier identified from response headers
- SDK configured with appropriate `maxRetries` setting
- Custom backoff implemented with jitter for high-throughput use cases
- Throughput optimized using batches, caching, or model selection

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| API Error | Check error type and status code | See `clade-common-errors` |

## Examples

See Rate Limit Tiers table, Response Headers section, Built-In SDK Retries, Custom Backoff implementation, and Throughput Optimization strategies above.

## Resources

- [Rate Limits Docs](https://docs.anthropic.com/en/api/rate-limits)
- [Message Batches](https://docs.anthropic.com/en/api/creating-message-batches) — no rate limits
- [Token Counting](https://docs.anthropic.com/en/api/counting-tokens)

## Next Steps

See `clade-cost-tuning` for cost optimization strategies.

## Prerequisites

- Completed `clade-install-auth`
- Understanding of HTTP response headers
- Familiarity with exponential backoff patterns

## Instructions

### Step 1: Review the patterns below

Each section contains production-ready code examples. Copy and adapt them to your use case.

### Step 2: Apply to your codebase

Integrate the patterns that match your requirements. Test each change individually.

### Step 3: Verify

Run your test suite to confirm the integration works correctly.

Files: 2

Size: 6.4 KB

Complexity: 25/100

Category: AI Agents

Source: https://github.com/jeremylongshore/claude-code-plugins-plus-skills/tree/main/plugins/saas-packs/claude-pack/skills/clade-rate-limits

Related in AI Agents

skill-development

Included

Comprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.

AI Agentsscripts

reprompter

Included

Transform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.

AI Agentsscripts

adaptive-compaction

Included

Adaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.

AI Agentsscripts

agent-skill-creator

Included

Create cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.

AI Agentsscripts

llm-wiki

Included

Use when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.

AI Agentsscripts

skill-master

Included

Agent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.

AI Agentsscripts