Model providers
Model providers: `GET /providers` is the public, OpenRouter-style view of what this deployment executes on (provider, upstream model, prices, health per executable target - never credentials); the `/admin/providers` endpoints add, check and map OpenAI-compatible endpoints at run time, and every API replica picks the change up without a restart.
get
Public Catalogue
Which providers this deployment executes on, the model behind every executable target, prices, health.
No credentials are exposed; providers[].host is the endpoint host only. Prices are USD per million
tokens from the reference catalogue when the upstream model is recognised, else the target's declared
cost. kinds lists the presets the console offers.
No authentication
Responses
| 200 | Successful Response |
curl -s "$OSR_URL/api/v1/providers"Something wrong or out of date on this page? Tell us - the page is named for you, so a one-line note is enough.
Marketplace
Browse, publish, install and rate agents, skills, personas, prompts, templates and tools.
Offers
Models by the token: an offer is one catalogue model served by one provider endpoint (`vendor/model@provider`), synthesised into the routing catalogue and sold at the customer price the pricing engine computes.