Pick a mode, not a model.

Quorum routes your prompt through a panel of frontier models, has them critique each other, and returns one synthesized answer — behind an API shaped like the one you already use.

Get a key → Read the docs 
curl https://www.quorum.dog/v1/chat/completions \
  -H "Authorization: Bearer $QUORUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "quorum-standard", "messages": [{"role": "user", "content": "..."}]}'
OpenAI-compatible. Swap model and base_url — most SDK integrations just work.

Two modes today

quorum-standard
$0.05–$0.15 surcharge (by question difficulty) + token rate

Three seats across Anthropic, Google, and OpenAI. Critique activates on harder questions — and the surcharge scales with it: $0.05 light, $0.10 medium, $0.15 hard.

quorum-max
~$0.32 surcharge + token rate

Frontier-only seats. Critique runs on every question — Quorum's highest-quality deliberation.

How billing actually works

Know the price before you pay.

Send /v1/estimate the same prompt and model you'd send to /v1/chat/completions. You get back the real difficulty classification — light, medium, or hard — and the exact surcharge you'd be charged running it for real, pulled from the same classifier and pricing table production runs on. 

curl https://www.quorum.dog/v1/estimate \
  -H "Authorization: Bearer $QUORUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "quorum-standard", "messages": [{"role": "user", "content": "..."}]}'

# → {"difficulty": "medium", "surcharge": "$0.10"}

Always free

Bring your own key — in development

Route deliberation through your own OpenAI, Google, or AWS/Bedrock account and billing instead of Quorum's pooled keys. Orchestration (the judge and synthesis passes) always stays on Quorum's own keys. Join the beta waitlist and tell us why you want it — it shapes what we build first.

Full reference, error codes, and a request builder live in the docs.

Get a key → Read the docs