Anthropic automatically upgrades your API account through usage tiers as your cumulative credit purchases increase. Each tier unlocks higher rate limits — more requests per minute, more input tokens per minute, and more output tokens per minute.Documentation Index
Fetch the complete documentation index at: https://docs.heygarth.ai/llms.txt
Use this file to discover all available pages before exploring further.
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.| Tier | Credit purchase required | Max single purchase | Monthly spend limit |
|---|---|---|---|
| Tier 1 | $5 | $100 | $100 |
| Tier 2 | $40 | $500 | $500 |
| Tier 3 | $200 | $1,000 | $1,000 |
| Tier 4 | $400 | $200,000 | $200,000 |
| Monthly Invoicing | Contact sales | — | No limit |
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
Tier 1
Entry-level limits after a $5 credit purchase. Suitable for evaluation and small pilots.| Model | RPM | ITPM | OTPM |
|---|---|---|---|
| Claude Sonnet 4.x | 50 | 30,000 | 8,000 |
| Claude Haiku 4.5 | 50 | 50,000 | 10,000 |
Tier 2
Unlocked after $40 in cumulative credit purchases. Suitable for small teams with moderate PR volume.| Model | RPM | ITPM | OTPM |
|---|---|---|---|
| Claude Sonnet 4.x | 1,000 | 450,000 | 90,000 |
| Claude Haiku 4.5 | 1,000 | 450,000 | 90,000 |
Tier 3
Unlocked after $200 in cumulative credit purchases. Suitable for growing engineering teams.| Model | RPM | ITPM | OTPM |
|---|---|---|---|
| Claude Sonnet 4.x | 2,000 | 800,000 | 160,000 |
| Claude Haiku 4.5 | 2,000 | 1,000,000 | 200,000 |
Tier 4
Unlocked after $400 in cumulative credit purchases. Suitable for large organisations with high PR velocity.| Model | RPM | ITPM | OTPM |
|---|---|---|---|
| Claude Sonnet 4.x | 4,000 | 2,000,000 | 400,000 |
| Claude Haiku 4.5 | 4,000 | 4,000,000 | 800,000 |
Sonnet 4.x limits apply to combined traffic across
claude-sonnet-4-6, claude-sonnet-4-5, and claude-sonnet-4.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.| Token type | Counts towards ITPM? |
|---|---|
| Uncached input tokens | Yes |
| Cache creation tokens | Yes |
| Cache read tokens | No (current models) |
| Output tokens | Counted under OTPM separately |
Choosing the right tier for your team
Tier 1 — Evaluation or very small teams
Fewer than 10 developers, infrequent PRs, or you are trialling BYOK before committing. Requires only a $5 credit deposit.
Tier 2 — Small to medium teams
10–50 developers with regular PR activity. The 1,000 RPM / 450,000 ITPM limit on Sonnet handles dozens of concurrent reviews comfortably. Requires $40 total in credit purchases.
Tier 3 — Large engineering orgs
50–200 developers or multiple busy repositories. Tier 3 doubles the RPM and nearly doubles ITPM versus Tier 2. Requires $200 in credit purchases.
Tier 4 — High-velocity platforms
200+ developers, monorepos, or CI pipelines generating a high volume of short-lived PRs. Requires $400 in credit purchases. For limits beyond Tier 4, contact Anthropic sales for monthly invoicing with no spend cap.
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.| Review size | Typical input tokens | Typical output tokens |
|---|---|---|
| Small PR (1–5 files, < 200 lines) | 3,000 – 8,000 | 500 – 1,500 |
| Medium PR (5–20 files, 200–800 lines) | 8,000 – 25,000 | 1,500 – 4,000 |
| Large PR (20+ files, 800+ lines) | 25,000 – 80,000 | 4,000 – 10,000 |
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
Create an Anthropic account
Go to console.anthropic.com and sign up or log in.
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.
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.Copy and store the key
Copy the key — it is shown only once. Paste it into Garth’s Settings → Integrations → LLM.
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.