LLM Providers

Kong supports three LLM providers out of the box:

Provider	Default Model	Setup
Anthropic	`claude-opus-4-6`	Set `ANTHROPIC_API_KEY` env var
OpenAI	`gpt-4o`	Set `OPENAI_API_KEY` env var
Custom	User-specified	Configure via `kong setup` or `--base-url` flag

Anthropic (Claude)

Default model: claude-opus-4-6 Setup:

export ANTHROPIC_API_KEY="sk-ant-..."

Get your key at console.anthropic.com. Available models:

Model	Best for
`claude-opus-4-6`	Highest quality analysis (default)
`claude-sonnet-4-6`	Balanced quality and cost
`claude-haiku-4-5-20251001`	Fastest, lowest cost

Pricing (per 1M tokens):

Model	Input	Output	Cache Write	Cache Read
claude-opus-4-6	$5.00	$25.00	$6.25	$0.50
claude-sonnet-4-6	$3.00	$15.00	$3.75	$0.30
claude-haiku-4-5	$1.00	$5.00	$1.25	$0.10

OpenAI (GPT-4o)

Default model: gpt-4o Setup:

export OPENAI_API_KEY="sk-..."

Get your key at platform.openai.com. Available models:

Model	Best for
`gpt-4o`	High quality analysis (default)
`gpt-4o-mini`	Fast, low cost
`o1`	Complex reasoning (slower, higher cost)
`o3-mini`	Advanced reasoning (balanced)

Pricing (per 1M tokens):

Model	Input	Output	Cached Input
gpt-4o	$2.50	$10.00	$1.25
gpt-4o-mini	$0.15	$0.60	$0.075
o1	$15.00	$60.00	$7.50
o3-mini	$1.10	$4.40	$0.55

Smart routing

If you’ve configured multiple providers via kong setup, Kong uses your default provider. Override at runtime:

kong analyze ./binary --provider openai --model gpt-4o-mini

If your default provider’s API key isn’t set, Kong falls back to any other configured provider that has a valid key.

Rate limiting

Kong uses automatic token-bucket rate limiting to stay within API rate limits. No configuration needed — it proactively sleeps between requests when approaching the limit. This prevents 429 Too Many Requests errors during large analyses.

Getting Started

Core Concepts

Usage

Configuration

LLM Providers

Anthropic (Claude)

OpenAI (GPT-4o)

Smart routing

Rate limiting

Further reading

​Anthropic (Claude)

​OpenAI (GPT-4o)

​Smart routing

​Rate limiting

​Further reading

Anthropic (Claude)

OpenAI (GPT-4o)

Smart routing

Rate limiting

Further reading