LiteLLMModel
litellm.home-operations.com / v1alpha1
apiVersion: litellm.home-operations.com/v1alpha1
kind: LiteLLMModel
metadata:
name: example
apiVersion
string
APIVersion defines the versioned schema of this representation of an object.
Servers should convert recognized schemas to the latest internal value, and
may reject unrecognized values.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources
kind
string
Kind is a string value representing the REST resource this object represents.
Servers may infer this from the endpoint the client submits requests to.
Cannot be updated.
In CamelCase.
More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds
metadata
object
spec object
LiteLLMModelSpec defines a single proxy model_list entry.
info object
Info is the typed model_info block for this model.
extra
object
Extra holds any further model_info keys, merged verbatim under the typed
fields (which win on conflict).
maxInputTokens
integer
MaxInputTokens is the context window size (max_input_tokens).
format:
int64
maxOutputTokens
integer
MaxOutputTokens is the maximum completion length (max_output_tokens).
format:
int64
maxTokens
integer
MaxTokens is the model's total token budget (max_tokens).
format:
int64
mode
string
Mode is the endpoint mode, e.g. "chat", "messages", "embedding".
supportsFunctionCalling
boolean
SupportsFunctionCalling advertises tool/function-calling support.
supportsPromptCaching
boolean
SupportsPromptCaching advertises prompt-caching support.
supportsVision
boolean
SupportsVision advertises image-input support.
modelName
string required
ModelName is the public name clients call (model_list[].model_name).
params object required
Params is the litellm_params block for this model.
additional
object
Additional holds any further litellm_params, merged verbatim under the typed
fields (which win on conflict).
apiBase
string
APIBase is the provider base URL. Mutually exclusive with APIBaseRef.
apiBaseRef object
APIBaseRef sources the provider base URL from a Secret. Mutually exclusive with APIBase.
key
string required
Key within the Secret holding the value.
name
string required
Name of the Secret.
apiKey
string
APIKey is a literal or os.environ/VAR API key. Prefer APIKeyRef for real secrets.
apiKeyRef object
APIKeyRef sources the provider API key from a Secret. Mutually exclusive with APIKey.
key
string required
Key within the Secret holding the value.
name
string required
Name of the Secret.
apiVersion
string
APIVersion for providers that require it (e.g. Azure).
dropParams
boolean
DropParams drops request params the provider does not support instead of erroring.
model
string required
Model is the underlying provider model identifier, e.g. "openai/glm-5.2".
rpm
integer
RPM caps requests-per-minute for this deployment.
format:
int64
tpm
integer
TPM caps tokens-per-minute for this deployment.
format:
int64
proxyRef
string
ProxyRef explicitly binds this model to a LiteLLMProxy by name in the same
namespace. When set it takes precedence over any proxy's modelSelector.
status object
LiteLLMModelStatus reports which proxies currently include this model.
conditions []object
Conditions represent the latest observations of the model's state.
lastTransitionTime
string required
lastTransitionTime is the last time the condition transitioned from one status to another.
This should be when the underlying condition changed. If that is not known, then using the time when the API field changed is acceptable.
format:
date-time
message
string required
message is a human readable message indicating details about the transition.
This may be an empty string.
maxLength:
32768
observedGeneration
integer
observedGeneration represents the .metadata.generation that the condition was set based upon.
For instance, if .metadata.generation is currently 12, but the .status.conditions[x].observedGeneration is 9, the condition is out of date
with respect to the current state of the instance.
format:
int64minimum:
0
reason
string required
reason contains a programmatic identifier indicating the reason for the condition's last transition.
Producers of specific condition types may define expected values and meanings for this field,
and whether the values are considered a guaranteed API.
The value should be a CamelCase string.
This field may not be empty.
pattern:
^[A-Za-z]([A-Za-z0-9_,:]*[A-Za-z0-9_])?$minLength:
1maxLength:
1024
status
string required
status of the condition, one of True, False, Unknown.
enum:
True, False, Unknown
type
string required
type of condition in CamelCase or in foo.example.com/CamelCase.
pattern:
^([a-z0-9]([-a-z0-9]*[a-z0-9])?(\.[a-z0-9]([-a-z0-9]*[a-z0-9])?)*/)?(([A-Za-z0-9][-A-Za-z0-9_.]*)?[A-Za-z0-9])$maxLength:
316No matches. Try .spec.info for an exact path