inferencing, infer
Subcommands
- model list — List available models
- endpoint list — List inferencing endpoints
- chat — Send a chat completion request
CLI v7.0.0 renamed
list-models to model list and list-endpoints to endpoint list. The old names still work but are hidden from help.model list
Returns a list of all models available on the serverless platform.model, models; list, ls
Flags
| Flag | Description |
|---|---|
Emit the full JSON payload (mutually exclusive with -q) | |
jq filter for value extraction (see Query output with -q) | |
Show at most N results (client-side; every result is still fetched). Cuts before -q. 0 for all |
--json prints a bare JSON array of models.
Examples
endpoint list
Returns a list of all model endpoints available for use by the specified organization.endpoint, endpoints; list, ls
Flags
| Flag | Description |
|---|---|
| Organization ID or name | |
Emit the full JSON payload (mutually exclusive with -q) | |
jq filter for value extraction (see Query output with -q) | |
Show at most N results (client-side; every result is still fetched). Cuts before -q. 0 for all |
--json prints a bare JSON array of endpoints.
Examples
chat
Send a chat completion request to the inference API using a configuration file. Supports both batch and interactive modes.Flags
Reasoning content
When you use the interactive TUI (--ui) with a model that supports reasoning, the model’s thought process appears in a separate “Thought Process” bubble above the response. The reasoning streams live as the model works through the problem, and the final answer appears in the standard response bubble once reasoning is complete.
This gives you visibility into how the model arrives at its answer without cluttering the final response.
Examples
Related
Models
Learn about available models on the Nscale platform.
Chat Use Case
End-to-end guide for chat inferencing.