Providers
One endpoint, every provider behind it.
This deployment routes 17 targets and executes 4 of them on 1 OpenAI-compatible provider. Prices are list prices per million tokens from the reference catalogue when the upstream model is recognised (0 of 4), otherwise the target's declared cost. Send model: "auto" to /v1/chat/completions and the router picks among these; pin any target id to bypass routing.
- providers
- 1
- executable
- 4
- requests · 7d
- 5
Connected providers
- azurenot checked
- Kind
- custom
- Host
- oai-osr-ua2c6onyidguw.openai.azure.com
- Models
- 4
- Source
- operator console
Executable targets
Each row is a routing target the OpenAI-compatible proxy can answer with, the upstream model it runs as and what a million tokens cost. Targets without a provider still take part in decisions, plans and quotes; see all routing targets.
| Target | Kind | Provider | Input / 1M | Output / 1M | Context | Capabilities | Health | Requests · 7d |
|---|---|---|---|---|---|---|---|---|
 On-prem private model azure/llm-onprem | llm | azure | $1.00 | $1.00 | - | - | 4 | |
Frontier reasoning model azure/llm-frontier | llm | azure | $15.0 | $15.0 | - | - | 1 | |
Mid-tier model azure/llm-mid | llm | azure | $3.00 | $3.00 | - | - | 0 | |
Small fast model azure/llm-small | llm | azure | $0.20 | $0.20 | - | - | 0 |
Programmatic access: GET /api/v1/providers (no key required), GET /v1/models with a key. Operators manage providers on the console; see the platform guide.