Model Catalog

· 5 models admin only

Provider: All

Model	Display name	Expertise	Aptitudes · benchmarks	Price · context
claude-opus-4-8 anthropic	Claude Opus 4.8 Note: house default	Long-form reasoning and careful multi-step analysis over large documents.	judge reasoning general swe 0.69 · mmlu 0.90	$15 · $75 200K
gpt-5 openai	GPT-5	Fast, broad general knowledge; strong at code and structured output.	coder reasoning general swe 0.72 · gpqa 0.55	$10 · $30 1M
gemini-2.0-pro google	Gemini 2.0 Pro	Very large context windows and image understanding; long-document summarizing.	judge long-context vision mmlu 0.88	$2.50 · $10 2M
llama-3.3-70b ollama local	Llama 3.3 70B Note: self-hosted (Ollama)	Everyday chat at near-zero cost; the cheap tier for routine questions.	general open-weight mmlu 0.86	$0 · $0 Compute only · 32K
gpt-4o openai	GPT-4o Note: superseded by gpt-5	not set	general mmlu 0.85	$2.50 · $10

Showing 1–5 of 5 Rows per page 25 1