## List custom models

`client.Models.List(ctx, query) (*CursorPage[InferenceModel], error)`

**get** `/v5/models`

List the custom model records registered in your account.

Returns a paginated list of the model records managed through this API — models your account deploys through the `launch` or `llmengine` serving vendors — optionally filtered by name and by model vendor, and scoped to the caller's account. This is different from `GET /v5/chat/completions/models`, which lists the models available to invoke for chat completions; this endpoint returns the managed records along with their deployment status, not the catalog of callable completion models.

### Parameters

- `query ModelListParams`

  - `EndingBefore param.Field[string]`

  - `Limit param.Field[int64]`

  - `ModelVendor param.Field[InferenceModelVendor]`

  - `Name param.Field[string]`

  - `SortBy param.Field[string]`

  - `SortOrder param.Field[SortOrder]`

  - `StartingAfter param.Field[string]`

### Returns

- `type InferenceModel struct{…}`

  - `ID string`

    The unique identifier of the entity.

  - `CreatedAt Time`

    The date and time when the entity was created in ISO format.

  - `CreatedByIdentityType InferenceModelCreatedByIdentityType`

    The type of identity that created the entity.

    - `const InferenceModelCreatedByIdentityTypeUser InferenceModelCreatedByIdentityType = "user"`

    - `const InferenceModelCreatedByIdentityTypeServiceAccount InferenceModelCreatedByIdentityType = "service_account"`

  - `CreatedByUserID string`

    The user who originally created the entity.

  - `ModelType InferenceModelType`

    - `const InferenceModelTypeGeneric InferenceModelType = "generic"`

    - `const InferenceModelTypeCompletion InferenceModelType = "completion"`

    - `const InferenceModelTypeChatCompletion InferenceModelType = "chat_completion"`

  - `ModelVendor InferenceModelVendor`

    - `const InferenceModelVendorOpenAI InferenceModelVendor = "openai"`

    - `const InferenceModelVendorCohere InferenceModelVendor = "cohere"`

    - `const InferenceModelVendorVertexAI InferenceModelVendor = "vertex_ai"`

    - `const InferenceModelVendorAnthropic InferenceModelVendor = "anthropic"`

    - `const InferenceModelVendorAzure InferenceModelVendor = "azure"`

    - `const InferenceModelVendorGemini InferenceModelVendor = "gemini"`

    - `const InferenceModelVendorLaunch InferenceModelVendor = "launch"`

    - `const InferenceModelVendorLlmengine InferenceModelVendor = "llmengine"`

    - `const InferenceModelVendorModelZoo InferenceModelVendor = "model_zoo"`

    - `const InferenceModelVendorBedrock InferenceModelVendor = "bedrock"`

    - `const InferenceModelVendorXai InferenceModelVendor = "xai"`

    - `const InferenceModelVendorFireworksAI InferenceModelVendor = "fireworks_ai"`

  - `Name string`

  - `Status InferenceModelStatus`

    - `const InferenceModelStatusFailed InferenceModelStatus = "failed"`

    - `const InferenceModelStatusReady InferenceModelStatus = "ready"`

    - `const InferenceModelStatusDeploying InferenceModelStatus = "deploying"`

    - `const InferenceModelStatusDeploymentTimeout InferenceModelStatus = "deployment_timeout"`

  - `ModelAvailability InferenceModelAvailability`

    - `const InferenceModelAvailabilityUnknown InferenceModelAvailability = "unknown"`

    - `const InferenceModelAvailabilityAvailable InferenceModelAvailability = "available"`

    - `const InferenceModelAvailabilityUnavailable InferenceModelAvailability = "unavailable"`

  - `ModelMetadata map[string, any]`

  - `Object InferenceModelObject`

    - `const InferenceModelObjectModel InferenceModelObject = "model"`

  - `StatusReason string`

  - `VendorConfiguration InferenceModelVendorConfigurationUnion`

    - `type LaunchVendorConfiguration struct{…}`

      - `ModelImage LaunchVendorConfigurationModelImage`

        - `Command []string`

        - `Registry string`

        - `Repository string`

        - `Tag string`

        - `EnvVars map[string, any]`

        - `HealthcheckRoute string`

        - `PredictRoute string`

        - `ReadinessDelay int64`

        - `RequestSchema map[string, any]`

        - `ResponseSchema map[string, any]`

        - `StreamingCommand []string`

        - `StreamingPredictRoute string`

      - `ModelInfra LaunchVendorConfigurationModelInfra`

        - `CPUs LaunchVendorConfigurationModelInfraCPUsUnion`

          - `string`

          - `int64`

        - `EndpointType string`

          - `const LaunchVendorConfigurationModelInfraEndpointTypeAsync LaunchVendorConfigurationModelInfraEndpointType = "async"`

          - `const LaunchVendorConfigurationModelInfraEndpointTypeSync LaunchVendorConfigurationModelInfraEndpointType = "sync"`

          - `const LaunchVendorConfigurationModelInfraEndpointTypeStreaming LaunchVendorConfigurationModelInfraEndpointType = "streaming"`

        - `GPUType string`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaTeslaT4 LaunchVendorConfigurationModelInfraGPUType = "nvidia-tesla-t4"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaAmpereA10 LaunchVendorConfigurationModelInfraGPUType = "nvidia-ampere-a10"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaAmpereA100 LaunchVendorConfigurationModelInfraGPUType = "nvidia-ampere-a100"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaAmpereA100e LaunchVendorConfigurationModelInfraGPUType = "nvidia-ampere-a100e"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaHopperH100 LaunchVendorConfigurationModelInfraGPUType = "nvidia-hopper-h100"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaHopperH100_1g20gb LaunchVendorConfigurationModelInfraGPUType = "nvidia-hopper-h100-1g20gb"`

          - `const LaunchVendorConfigurationModelInfraGPUTypeNvidiaHopperH100_3g40gb LaunchVendorConfigurationModelInfraGPUType = "nvidia-hopper-h100-3g40gb"`

        - `GPUs int64`

        - `HighPriority bool`

        - `Labels map[string, string]`

        - `MaxWorkers int64`

        - `Memory string`

        - `MinWorkers int64`

        - `PerWorker int64`

        - `PublicInference bool`

        - `Storage string`

    - `type LlmEngineVendorConfiguration struct{…}`

      - `Model string`

      - `ChatTemplateOverride string`

      - `CheckpointPath string`

      - `CPUs int64`

      - `DefaultCallbackURL string`

      - `EndpointType string`

      - `GPUType string`

      - `GPUs int64`

      - `HighPriority bool`

      - `InferenceFramework string`

      - `InferenceFrameworkImageTag string`

      - `Labels map[string, string]`

      - `MaxWorkers int64`

      - `Memory string`

      - `MinWorkers int64`

      - `NodesPerWorker int64`

      - `NumShards int64`

      - `PerWorker int64`

      - `PostInferenceHooks []string`

      - `PublicInference bool`

      - `Quantize string`

      - `Source string`

      - `Storage string`

### Example

```go
package main

import (
  "context"
  "fmt"

  "github.com/scaleapi/sgp-dev-go"
  "github.com/scaleapi/sgp-dev-go/option"
)

func main() {
  client := sgpdev.NewClient(
    option.WithAPIKey("My API Key"),
    option.WithAccountID("My Account ID"),
  )
  page, err := client.Models.List(context.TODO(), sgpdev.ModelListParams{

  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", page)
}
```

#### Response

```json
{
  "has_more": true,
  "items": [
    {
      "id": "id",
      "created_at": "2019-12-27T18:11:19.117Z",
      "created_by_identity_type": "user",
      "created_by_user_id": "created_by_user_id",
      "model_type": "generic",
      "model_vendor": "openai",
      "name": "name",
      "status": "failed",
      "model_availability": "unknown",
      "model_metadata": {
        "foo": "bar"
      },
      "object": "model",
      "status_reason": "status_reason",
      "vendor_configuration": {
        "model_image": {
          "command": [
            "string"
          ],
          "registry": "registry",
          "repository": "repository",
          "tag": "tag",
          "env_vars": {
            "foo": "bar"
          },
          "healthcheck_route": "healthcheck_route",
          "predict_route": "predict_route",
          "readiness_delay": 0,
          "request_schema": {
            "foo": "bar"
          },
          "response_schema": {
            "foo": "bar"
          },
          "streaming_command": [
            "string"
          ],
          "streaming_predict_route": "streaming_predict_route"
        },
        "model_infra": {
          "cpus": "string",
          "endpoint_type": "async",
          "gpu_type": "nvidia-tesla-t4",
          "gpus": 0,
          "high_priority": true,
          "labels": {
            "foo": "string"
          },
          "max_workers": 0,
          "memory": "memory",
          "min_workers": 0,
          "per_worker": 0,
          "public_inference": true,
          "storage": "storage"
        }
      }
    }
  ],
  "total": 0,
  "limit": 0,
  "object": "list"
}
```