oz0 model resolve
Usage and flags for oz0 model resolve.
For: Operators and developers looking up a command.
Say what an agent's model resolves to in a tenant, as the edge resolves it when a job starts: each model with its format and the reasoning effort it is sent, the candidates left out and why, and each change made to the effort asked for (the tenant's ceiling, a level a model lacks).
Usage
oz0 model resolve <alias | provider/model...> [flags]
Flags
| Flag | Type | Default | Description |
|---|---|---|---|
--data | string | local for an agent whose data stays on the node | |
--effort | string | the reasoning effort the agent asks for: low, medium, high, xhigh, max | |
--json | bool | print JSON instead of a table | |
--min-context | string | the smallest context window it works with, such as 128k | |
--needs | strings | capabilities the agent needs: tools, vision, structured_output, thinking, pdf, audio, web_search, prompt_cache | |
--tenant | string | default | tenant |
Inherited flags
| Flag | Type | Default | Description |
|---|---|---|---|
--context | string | $OZ0_CONTEXT or <config dir>/orchestrator-zero/context.json | CLI context file written by server init |
--log-level | string | info | log level: debug, info, warn or error |
See all oz0 commands and the global flags.