Rate limits are enforced at the organisation level, measured separately per model. You can monitor your current tier and live usage in Anthropic Console → Limits.
Spend tiers
Advancing to the next tier requires a cumulative credit purchase that meets the threshold below. You advance immediately upon reaching it.Credit purchase is the cumulative amount deposited into your Anthropic account (excluding tax), not your total spend. You advance as soon as you cross the threshold — there is no waiting period.
Rate limits by tier
Rate limits are measured in three dimensions:- RPM — requests per minute
- ITPM — uncached input tokens per minute (cached tokens do not count for most models)
- OTPM — output tokens per minute
Start Tier
Entry-level limits for evaluation.Build Tier
Suitable for small to medium teams with moderate PR volume.Scale Tier
Suitable for large organisations with high PR velocity.Sonnet 4.x limits apply to combined traffic across all 4.x models. Exact limits scale dynamically based on your usage patterns.
How ITPM works (cache-aware)
A key advantage of the Claude API is that cached input tokens do not count towards your ITPM rate limit on current models. Only uncached input tokens and tokens being written to cache consume your ITPM quota.
This means effective throughput is significantly higher than the raw ITPM number suggests. If 80% of your input tokens are served from cache, you can process 5× more total input tokens per minute than your ITPM limit implies.
Choosing the right tier for your team
Start Tier — Evaluation or very small teams
Fewer than 10 developers, infrequent PRs, or you are trialling BYOK before committing. Active immediately upon funding your account.
Build Tier — Small to medium teams
10–50 developers with regular PR activity. The higher RPM and ITPM limits handle dozens of concurrent reviews comfortably.
Scale Tier — Large engineering orgs
50+ developers, monorepos, or CI pipelines generating a high volume of short-lived PRs.
Token consumption per review
Each Garth review consumes input tokens (your diff and context) and output tokens (the review comments). Estimates below are for Claude Sonnet 4.x.Rate limit errors
If your account hits a rate limit, Garth retries automatically with exponential backoff. Sustained limits (e.g. many large PRs merging simultaneously) may delay review posting. What you will see:- A delayed review comment once the retry succeeds
- A dashboard notification if retries are exhausted and the review is dropped
- Advance to the next tier by purchasing additional credits in the Anthropic Console
- Enable or increase prompt caching to reduce ITPM consumption
- Contact support if you need help sizing the right tier
Getting an Anthropic API key
1
Create an Anthropic account
Go to console.anthropic.com and sign up or log in.
2
Purchase credits
Navigate to Billing and purchase at least $5 in credits. This activates Tier 1 immediately. Purchase $40 total to reach Tier 2, $200 for Tier 3, or $400 for Tier 4.
3
Generate an API key
Go to Settings → API Keys in the Anthropic Console and click Create Key. Give it a descriptive name such as
garth-byok.4
Copy and store the key
Copy the key — it is shown only once. Paste it into Garth’s Settings → Integrations → LLM.
Provider references
Official Anthropic documentation for models, pricing, and rate limits.Claude models overview
Full list of available Claude models with context windows and capabilities.
API rate limits
Official rate limit reference for all tiers and models.
Pricing
Per-token pricing for all Claude models.
Anthropic Console — API keys
Create and manage your Anthropic API keys.
Next steps
BYOK overview
Add your Claude API key to Garth’s secure vault and set it as your active provider.
Anthropic Console — Limits
View your current tier and live rate limit usage in the Anthropic Console.