https://api.openai.com. Rate limits are applied per organisation and scale automatically as your usage and spend increase.
Monitor your current tier, rate limits, and token usage in the OpenAI Platform dashboard.
Supported models
Garth supports the following OpenAI models for code review and scan requests.| Model | Best for | Context window |
|---|---|---|
gpt-4o | Recommended. Highest accuracy for code review, security analysis, and large diffs | 128k tokens |
gpt-4o-mini | Fast turnaround, lower cost, high-volume routine reviews | 128k tokens |
gpt-4-turbo | Complex reasoning over large codebases | 128k tokens |
gpt-4 | Baseline GPT-4 for standard reviews | 8k tokens |
Usage tiers
OpenAI automatically advances your account through usage tiers as your cumulative spend increases. Higher tiers unlock greater rate limits.| Tier | Requirement | Monthly spend limit |
|---|---|---|
| Free | Account created, no payment method required | $100 |
| Tier 1 | $5 paid | $100 |
| Tier 2 | $50 paid and 7+ days since first payment | $500 |
| Tier 3 | $100 paid and 7+ days since first payment | $1,000 |
| Tier 4 | $250 paid and 14+ days since first payment | $5,000 |
| Tier 5 | $1,000 paid and 30+ days since first payment | $200,000 |
You advance to the next tier as soon as your cumulative payments cross the threshold and the waiting period has elapsed. There is no manual upgrade process.
Rate limits by tier
Rate limits are measured in three dimensions:- RPM — requests per minute
- TPM — tokens per minute
- RPD — requests per day
Tier 1
| Model | RPM | TPM | RPD |
|---|---|---|---|
gpt-4o | 500 | 30,000 | 10,000 |
gpt-4o-mini | 500 | 200,000 | 10,000 |
gpt-4-turbo | 500 | 30,000 | 10,000 |
Tier 2
| Model | RPM | TPM | RPD |
|---|---|---|---|
gpt-4o | 5,000 | 450,000 | — |
gpt-4o-mini | 5,000 | 2,000,000 | — |
gpt-4-turbo | 5,000 | 450,000 | — |
Tier 3
| Model | RPM | TPM | RPD |
|---|---|---|---|
gpt-4o | 5,000 | 800,000 | — |
gpt-4o-mini | 5,000 | 4,000,000 | — |
gpt-4-turbo | 5,000 | 800,000 | — |
Tier 4
| Model | RPM | TPM | RPD |
|---|---|---|---|
gpt-4o | 10,000 | 2,000,000 | — |
gpt-4o-mini | 10,000 | 10,000,000 | — |
gpt-4-turbo | 10,000 | 2,000,000 | — |
Tier 5
| Model | RPM | TPM | RPD |
|---|---|---|---|
gpt-4o | 10,000 | 30,000,000 | — |
gpt-4o-mini | 30,000 | 150,000,000 | — |
gpt-4-turbo | 10,000 | 30,000,000 | — |
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 $5 in total payments.
Tier 2 — Small to medium teams
10–50 developers with regular PR activity. The 5,000 RPM / 450,000 TPM limit on
gpt-4o handles dozens of concurrent reviews comfortably.Tier 3 — Large engineering orgs
50–200 developers or multiple busy repositories. Nearly doubles the TPM versus Tier 2.
Tier 4 / Tier 5 — High-velocity platforms
200+ developers, monorepos, or CI pipelines generating high PR volume. Tier 5 supports up to 30M TPM on
gpt-4o.Token consumption per review
Each Garth review consumes input tokens (your diff and context) and output tokens (the review comments). Estimates below are forgpt-4o.
| 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 may delay when review comments are posted. What you will see:- A delayed review comment once the retry succeeds
- A dashboard notification if retries are exhausted and the review is dropped
- Increase your spend to advance to the next tier in the OpenAI Platform
- Switch to
gpt-4o-minito reduce per-request token usage - Contact support if you need help sizing the right tier
Getting an OpenAI API key
Create an OpenAI account
Go to platform.openai.com and sign up or log in.
Add a payment method
Navigate to Settings → Billing and add a payment method. Purchase at least $5 in credits to activate Tier 1 and unlock rate limits beyond the free tier.
Generate an API key
Go to API Keys in the left sidebar and click Create new secret key. Give it a descriptive name such as
garth-byok and set the permissions to All.Copy and store the key
Copy the key — it is shown only once. Paste it into Garth’s Settings → Integrations → LLM under the OpenAI provider.
Provider references
Official OpenAI documentation for models, pricing, and rate limits.OpenAI models
Full list of available GPT models with context windows and capabilities.
Rate limits
Official rate limit reference for all tiers and models.
Pricing
Per-token pricing for all OpenAI models.
API keys
Create and manage your OpenAI API keys.
Next steps
BYOK overview
Add your OpenAI key to Garth’s secure vault and set it as your active provider.
OpenAI Platform — Limits
View your current tier and live rate limit usage in the OpenAI Platform dashboard.