Skip to main content
POST
Upload a custom model

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

namespace_id
string
required

Body

multipart/form-data
file
string
required

Model archive (.tar.gz)

name
string
required

Model name

version
string
required

Model version

model_format
enum<string>
required

Model format

Available options:
safetensors,
onnx,
pytorch,
huggingface
framework
string | null

ML framework (e.g., sentence-transformers)

task_type
string | null

Task type (e.g., embedding, classification)

num_cpus
number
default:1

CPU requirements

num_gpus
integer
default:0

GPU requirements

memory_gb
number
default:4

Memory in GB

Response

Successful Response

Response model for model upload.

success
boolean
required

Whether upload succeeded

model_id
string
required

Unique model identifier

deployment_status
enum<string>
required

Deployment status

Available options:
deployed,
pending,
failed,
not_deployed
endpoint
string
required

Model inference endpoint

model_archive_url
string
required

S3 URL where archive is stored