Read a Model
const url = 'https://example.com/apis/nodus.dev/v1/namespaces/example/models/example';const options = {method: 'GET'};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url https://example.com/apis/nodus.dev/v1/namespaces/example/models/exampleParameters
Section titled “ Parameters ”Path Parameters
Section titled “ Path Parameters ”The project.
The object’s name.
Responses
Section titled “ Responses ”OK
Model is a model callable through the inference data plane, published read-only in the catalog project nodus. Pass spec.id (or an alias) as the model of a request; the rates are what a request is quoted at now.
object
object
object
object
object
object
object
ModelSpec is what the catalog declares about a Model.
object
Aliases are other ids that name the same model.
ModelCapabilities are the request features a Model supports.
object
JSONSchema is true when the model follows a response JSON schema.
PromptCaching is true when repeated prompt prefixes bill at the cache-read rate.
Reasoning is true when the model reasons before it answers.
Streaming is true when responses stream as server-sent events.
Tools is true when the model calls tools.
ContextTokens is the context window in tokens.
DeprecationTime is when the model stops serving, once announced.
Description says what the model is for.
DisplayName is the model’s human-readable name.
Family groups related models, such as gpt-oss.
ID is the model id a request names, such as openai/gpt-oss-120b.
ImageTokenAllowance is the input tokens held for each inline image.
MaxOutputTokens is the most tokens one response generates.
ModelModalities lists a Model’s input and output modalities: Text, Image, Audio or Embedding.
object
Input are the modalities the model reads.
Output are the modalities the model writes.
Operations are the inference routes the model serves.
Preview marks a model that may change or leave the catalog without notice.
ModelPricing is a Model’s customer rates as decimal USD strings; a unit the model does not bill is absent.
object
AudioMinimumSeconds is the least audio one transcription or translation request is billed for.
AudioPerSecondUSD is the rate of a second of transcribed or translated audio.
CacheReadPerMillionTokensUSD is the rate of a million input tokens read from the prompt cache.
CacheWritePerMillionTokensUSD is the rate of a million input tokens written to the prompt cache.
InputPerMillionTokensUSD is the rate of a million input tokens.
OutputPerMillionTokensUSD is the rate of a million output tokens.
PricebookVersion is the pricing version the rates come from, which receipts record.
SpeechPerMillionCharactersUSD is the rate of a million characters of generated speech.
ModelStatus is whether a Model serves requests now.
object
Available mirrors the Available condition.
Conditions carry Ready and Available; both are False with reason UpstreamUnavailable while no route serves the model, and Unknown in a process that does not serve inference.
object
Phase is Ready while requests for the model are served, else Pending.
Example generated
{ "apiVersion": "example", "kind": "example", "metadata": { "annotations": { "additionalProperty": "example" }, "creationTimestamp": "example", "deletionGracePeriodSeconds": 1, "deletionTimestamp": "example", "finalizers": [ "example" ], "generateName": "example", "generation": 1, "labels": { "additionalProperty": "example" }, "managedFields": [ { "apiVersion": "example", "fieldsType": "example", "fieldsV1": { "additionalProperty": "example" }, "manager": "example", "operation": "example", "subresource": "example", "time": "example" } ], "name": "example", "namespace": "example", "ownerReferences": [ { "apiVersion": "example", "blockOwnerDeletion": true, "controller": true, "kind": "example", "name": "example", "uid": "example" } ], "resourceVersion": "example", "selfLink": "example", "uid": "example" }, "spec": { "aliases": [ "example" ], "capabilities": { "jsonSchema": true, "promptCaching": true, "reasoning": true, "streaming": true, "tools": true }, "contextTokens": 1, "deprecationTime": "example", "description": "example", "displayName": "example", "family": "example", "id": "example", "imageTokenAllowance": 1, "maxOutputTokens": 1, "modalities": { "input": [ "example" ], "output": [ "example" ] }, "operations": [ "example" ], "preview": true, "pricing": { "audioMinimumSeconds": 1, "audioPerSecondUSD": "example", "cacheReadPerMillionTokensUSD": "example", "cacheWritePerMillionTokensUSD": "example", "inputPerMillionTokensUSD": "example", "outputPerMillionTokensUSD": "example", "pricebookVersion": "example", "speechPerMillionCharactersUSD": "example" } }, "status": { "available": true, "conditions": [ { "lastTransitionTime": "example", "message": "example", "observedGeneration": 1, "reason": "example", "status": "example", "type": "example" } ], "phase": "example" }}default
Section titled “ default ”An error: a metav1.Status whose reason is a registered code.
Status is the error body of every API response: a Kubernetes metav1.Status (so kubectl and client-go understand it) plus three top-level extensions that those clients ignore (ADR-028).
object
object
object
Docs is the URL of the code’s docs page.
Fix says what to do next, for example a CLI command or the field to change.
object
object
RequestID identifies the request in logs and support tickets.
Example generated
{ "apiVersion": "example", "code": 1, "details": { "causes": [ { "field": "example", "message": "example", "reason": "example" } ], "group": "example", "kind": "example", "name": "example", "retryAfterSeconds": 1, "uid": "example" }, "docs": "example", "fix": "example", "kind": "example", "message": "example", "metadata": { "continue": "example", "remainingItemCount": 1, "resourceVersion": "example", "selfLink": "example", "shardInfo": { "selector": "example" } }, "reason": "example", "requestId": "example", "status": "example"}