granola-rate-limits

Understand Granola plan limits, usage quotas, and API rate limiting. Use when hitting meeting limits, choosing between plans, or managing Enterprise API rate limits. Trigger: "granola limits", "granola quota", "granola plan", "granola usage", "granola restrictions".

1,868 stars

Best use case

granola-rate-limits is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Understand Granola plan limits, usage quotas, and API rate limiting. Use when hitting meeting limits, choosing between plans, or managing Enterprise API rate limits. Trigger: "granola limits", "granola quota", "granola plan", "granola usage", "granola restrictions".

Teams using granola-rate-limits should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/granola-rate-limits/SKILL.md --create-dirs "https://raw.githubusercontent.com/jeremylongshore/claude-code-plugins-plus-skills/main/plugins/saas-packs/granola-pack/skills/granola-rate-limits/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/granola-rate-limits/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How granola-rate-limits Compares

Feature / Agentgranola-rate-limitsStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Understand Granola plan limits, usage quotas, and API rate limiting. Use when hitting meeting limits, choosing between plans, or managing Enterprise API rate limits. Trigger: "granola limits", "granola quota", "granola plan", "granola usage", "granola restrictions".

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Granola Rate Limits & Plan Quotas

## Overview
Granola has three plan tiers with different feature access and limits. There are no per-meeting minute caps or monthly meeting count limits on paid plans. Limits primarily apply to the free tier and the Enterprise API.

## Plan Comparison (Current as of March 2026)

### Basic (Free) — $0
| Feature | Limit |
|---------|-------|
| Meetings | 25 lifetime (not monthly) |
| Meeting history | Visible for 14 days only |
| Enhance Notes | Included |
| Templates | Built-in only |
| Granola Chat | Included |
| People & Companies | Included |
| Integrations | None |
| API access | None |

> The free plan is essentially a trial — 25 meetings total, ever. After that, you must upgrade.

### Business — $14/user/month
| Feature | Availability |
|---------|-------------|
| Meetings | Unlimited |
| Meeting history | Unlimited retention |
| Templates | Built-in + custom |
| Granola Chat | Included |
| People & Companies | Included |
| Slack integration | Native |
| Notion integration | Native |
| CRM (HubSpot, Attio, Affinity) | Native |
| Zapier | Full access |
| MCP (AI agent integration) | Included |
| Team shared folders | Included |
| Admin controls | Basic |
| AI training opt-out (org-wide) | Included |
| Priority support | Included |
| Public API access | Included |

### Enterprise — $35+/user/month
| Feature | Availability |
|---------|-------------|
| Everything in Business | Included |
| SSO (Okta, Google Workspace) | Included |
| SCIM provisioning | Included |
| AI training opt-out (enforced) | Default on |
| Usage analytics dashboard | Included |
| Enterprise API (full) | Included |
| Custom data retention policies | Configurable |
| SOC 2 Type 2 compliance report | Available |
| Dedicated account manager | Included |
| Volume discounts | Negotiable |

## API Rate Limits

### Enterprise API
- Rate limits are applied **per workspace** (not per user)
- When exceeded: HTTP `429 Too Many Requests` response
- Retry behavior: respect the `Retry-After` header
- No published rate numbers — contact Granola for workspace-specific limits

### Zapier Integration
- Zapier task limits are governed by your **Zapier plan**, not Granola
- Granola does not throttle outbound Zapier triggers
- For high-volume workspaces, add delay steps between Zap actions to avoid overwhelming downstream apps

## Usage Monitoring

### Check Usage in Granola
1. Click your avatar (bottom-left) > **Settings**
2. Navigate to **Account** or **Subscription**
3. View: current plan, meeting count, team seats, connected integrations

### Free Plan Usage Tracking
```
Meetings Used: 18 / 25 lifetime
History Visible: Last 14 days
Upgrade Required: After 25 meetings
```

### API Usage (Enterprise)
Monitor API usage through response headers:
```bash
# Check rate limit headers in API response
curl -s -I "https://api.granola.ai/v0/notes" \
  -H "Authorization: Bearer $GRANOLA_API_KEY" \
  | grep -i "rate-limit\|retry-after"
```

## What Happens at Limits

| Limit Hit | Behavior | Resolution |
|-----------|----------|------------|
| Free plan 25 meetings | New recordings blocked | Upgrade to Business ($14/mo) |
| Free plan 14-day history | Older notes hidden (not deleted) | Upgrade to restore access |
| API rate limit (429) | Requests rejected | Wait for `Retry-After` period, reduce request frequency |
| Zapier task limit | Zaps paused | Upgrade Zapier plan or reduce trigger frequency |
| Workspace seat limit | Can't add users | Purchase additional seats or remove inactive users |

## Plan Selection Guide

| Scenario | Recommended Plan |
|----------|-----------------|
| Trying Granola (< 25 meetings) | Basic (Free) |
| Individual user, needs integrations | Business ($14/mo) |
| Team of 2-10, shared folders + CRM | Business ($14/user/mo) |
| 10+ users, SSO/SCIM required | Enterprise ($35+/user/mo) |
| Regulated industry (SOC 2, GDPR) | Enterprise |
| API access for custom workflows | Business (basic) or Enterprise (full) |

## Billing Details
- **Annual billing:** Save 10-15% vs monthly
- **Prorated upgrades:** Upgrade mid-cycle, pay difference
- **Seat management:** Add/remove seats in Settings > Team
- **No per-minute charges:** Granola does not charge by meeting duration or transcription minutes

## Error Handling

| Error | Cause | Fix |
|-------|-------|-----|
| "Meeting limit reached" | Free plan exhausted (25 lifetime) | Upgrade to Business |
| "Subscription expired" | Payment method failed | Update payment in Settings > Billing |
| API 429 response | Rate limit exceeded | Implement exponential backoff, reduce request frequency |
| "Feature not available" | Feature requires higher plan | Check plan comparison above and upgrade |

## Resources
- [Granola Pricing](https://www.granola.ai/pricing)
- [Pricing Blog (ROI Calculator)](https://www.granola.ai/blog/granola-pricing-plans-features-roi)
- [Enterprise API Docs](https://docs.granola.ai/help-center/sharing/integrations/enterprise-api)
- [API Changelog](https://docs.granola.ai/api-reference/changelog)

## Next Steps
Proceed to `granola-security-basics` for security and compliance configuration.

Related Skills

workhuman-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Workhuman rate limits for employee recognition and rewards API. Use when integrating Workhuman Social Recognition, or building recognition workflows with HRIS systems. Trigger: "workhuman rate limits".

wispr-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Wispr Flow rate limits for voice-to-text API integration. Use when integrating Wispr Flow dictation, WebSocket streaming, or building voice-powered applications. Trigger: "wispr rate limits".

windsurf-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Understand and manage Windsurf credit system, usage limits, and model selection. Use when running out of credits, optimizing AI usage costs, or understanding the credit-per-model pricing structure. Trigger with phrases like "windsurf credits", "windsurf rate limit", "windsurf usage", "windsurf out of credits", "windsurf model costs".

webflow-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Handle Webflow Data API v2 rate limits — per-key limits, Retry-After headers, exponential backoff, request queuing, and bulk endpoint optimization. Use when hitting 429 errors, implementing retry logic, or optimizing API request throughput. Trigger with phrases like "webflow rate limit", "webflow throttling", "webflow 429", "webflow retry", "webflow backoff", "webflow too many requests".

vercel-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Handle Vercel API rate limits, implement retry logic, and configure WAF rate limiting. Use when hitting 429 errors, implementing retry logic, or setting up rate limiting for your Vercel-deployed API endpoints. Trigger with phrases like "vercel rate limit", "vercel throttling", "vercel 429", "vercel retry", "vercel backoff", "vercel WAF rate limit".

veeva-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Veeva Vault rate limits for REST API and clinical operations. Use when working with Veeva Vault document management and CRM. Trigger: "veeva rate limits".

vastai-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Handle Vast.ai API rate limits with backoff and request optimization. Use when encountering 429 errors, implementing retry logic, or optimizing API request throughput. Trigger with phrases like "vastai rate limit", "vastai throttling", "vastai 429", "vastai retry", "vastai backoff".

twinmind-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Implement TwinMind rate limiting, backoff, and optimization patterns. Use when handling rate limit errors, implementing retry logic, or optimizing API request throughput for TwinMind. Trigger with phrases like "twinmind rate limit", "twinmind throttling", "twinmind 429", "twinmind retry", "twinmind backoff".

together-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Together AI rate limits for inference, fine-tuning, and model deployment. Use when working with Together AI's OpenAI-compatible API. Trigger: "together rate limits".

techsmith-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

TechSmith rate limits for Snagit COM API and Camtasia automation. Use when working with TechSmith screen capture and video editing automation. Trigger: "techsmith rate limits".

supabase-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

Manage Supabase rate limits and quotas across all plan tiers. Use when hitting 429 errors, configuring connection pooling, optimizing API throughput, or understanding tier-specific quotas for Auth, Storage, Realtime, and Edge Functions. Trigger: "supabase rate limit", "supabase 429", "supabase throttle", "supabase quota", "supabase connection pool", "supabase too many requests".

stackblitz-rate-limits

1868
from jeremylongshore/claude-code-plugins-plus-skills

WebContainer resource limits: memory, CPU, file system size, process count. Use when working with WebContainers or StackBlitz SDK. Trigger: "webcontainer limits".