Inference API
- POST🆕 Inference by environment
- POSTProduction deployment
- POSTDevelopment deployment
- POSTPublished deployment
- OpenAI compatible endpoints
- Wake deployment endpoints
- Deprecated endpoints
Async Inference API
Management API
- GETGet all secrets
- POSTUpsert a secret
- 🆕 Manage model environments
- 🆕 Manage chain environments
- GETGet instance types
- Get models
- DELDelete models
- Get chains
- DELDelete chains
- Get model deployments
- DELDelete model deployments
- Get chain deployments
- DELDelete chain deployments
- Promote deployment
- Update model deployment autoscaling settings
- Activate model deployment
- Deactivate model deployment
Get all model environments
Gets all environments for a given model
Authorizations
You must specify the scheme 'Api-Key' in the Authorization header. For example, Authorization: Api-Key <Your_Api_Key>
Path Parameters
Response
list of environments
Autoscaling settings for the environment
Timeframe of traffic considered for autoscaling decisions
Number of requests per replica before scaling up
Maximum number of replicas
Minimum number of replicas
Waiting period before scaling down any active replica
Time the environment was created in ISO 8601 format
Current deployment of the environment
Number of active replicas
Autoscaling settings for the deployment. If null, the model has not finished deploying
Timeframe of traffic considered for autoscaling decisions
Number of requests per replica before scaling up
Maximum number of replicas
Minimum number of replicas
Waiting period before scaling down any active replica
Time the deployment was created in ISO 8601 format
The environment associated with the deployment
Unique identifier of the deployment
Whether the deployment is the development deployment of the model
Whether the deployment is the production deployment of the model
Unique identifier of the model
Name of the deployment
Status of the deployment
BUILDING, DEPLOYING, DEPLOY_FAILED, LOADING_MODEL, ACTIVE, UNHEALTHY, BUILD_FAILED, BUILD_STOPPED, DEACTIVATING, INACTIVE, FAILED, UPDATING, SCALED_TO_ZERO, WAKING_UP Unique identifier of the model
Name of the environment
Promotion settings for the environment
Duration of the ramp up in seconds
Whether to ramp up traffic while promoting
Whether to deploy on all promotions. Enabling this flag allows model code to safely handle environment-specific logic. When a deployment is promoted, a new deployment will be created with a copy of the image.
Was this page helpful?