OpenRouter-style routing across LLM providers and QPU backends through a single OpenAI-compatible interface — with mitigation and a confidence score on the quantum side. This page reads the live deployment.
| ID | Owner | Modality | Pricing / capacity | |
|---|---|---|---|---|
| loading… | ||||
| Model / backend | Requests | Units | Cost (USD) |
|---|---|---|---|
| loading… | |||
Aggregate across all visitors (auth off on the public demo). Every Orchestrator demo click meters here.
# auto-route a prompt across LLM providers (OpenAI-compatible) curl …/api/v1/chat/completions -H 'content-type: application/json' -d '{ "model": "auto", "route": "cheapest", "messages": [{"role":"user","content":"What is a QUBO?"}] }' # route a QUBO across quantum backends + solve, with a confidence score curl …/api/v1/quantum/jobs -H 'content-type: application/json' -d '{ "type": "qubo", "Q": [[-1,2,0],[0,-1,0],[0,0,-1]], "policy": "highest_fidelity", "prefer_hardware": false }'