Anthropic models
Pricing (per 1M tokens):
Model limits:
Anthropic models have a 200k token context window (~800k chars). Kong uses prompt caching to reduce costs on repeated system prompt content.
OpenAI models
Pricing (per 1M tokens):
Model limits:
OpenAI standard models have 128k token context (~512k chars). Reasoning models (
o1, o3-mini) have 200k context but use smaller batch sizes due to higher per-call cost.
Custom providers
No pricing is tracked for custom endpoints. Token counts are still recorded and displayed in the analysis summary. See Custom Endpoints for configuration.Cost estimation
Rough cost ranges by binary size (using Claude Opus as baseline):
These vary significantly with:
- Model choice —
gpt-4o-miniis ~30x cheaper thanclaude-opus-4-6 - Binary complexity — obfuscated code requires more tool calls
- Signature matches — known library functions skip LLM analysis entirely
Further reading
- LLM Providers — provider setup and configuration
- Custom Endpoints — using local models