Deploy Model - Tensormesh User Documentation

Deploy Model

curl --request POST \
  --url https://api.tensormesh.ai/v1/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "modelName": "<string>",
  "userId": "<string>",
  "description": "<string>",
  "infra": {
    "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
    "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
    "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
    "onpremRegion": "<string>"
  },
  "modelPath": "<string>",
  "gpuCount": 123,
  "gpuType": "GPU_TYPE_UNSPECIFIED",
  "modelSpec": {},
  "apiKey": "<string>",
  "hfToken": "<string>",
  "kvCacheEnabled": true,
  "cpuOffloadingEnabled": true,
  "nodeId": "<string>"
}
'

import requests

url = "https://api.tensormesh.ai/v1/models"

payload = {
    "modelName": "<string>",
    "userId": "<string>",
    "description": "<string>",
    "infra": {
        "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
        "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
        "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
        "onpremRegion": "<string>"
    },
    "modelPath": "<string>",
    "gpuCount": 123,
    "gpuType": "GPU_TYPE_UNSPECIFIED",
    "modelSpec": {},
    "apiKey": "<string>",
    "hfToken": "<string>",
    "kvCacheEnabled": True,
    "cpuOffloadingEnabled": True,
    "nodeId": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    modelName: '<string>',
    userId: '<string>',
    description: '<string>',
    infra: {
      cloudProvider: 'CLOUD_PROVIDER_UNSPECIFIED',
      nebiusRegion: 'NEBIUS_REGION_UNSPECIFIED',
      lambdaRegion: 'LAMBDA_REGION_UNSPECIFIED',
      onpremRegion: '<string>'
    },
    modelPath: '<string>',
    gpuCount: 123,
    gpuType: 'GPU_TYPE_UNSPECIFIED',
    modelSpec: {},
    apiKey: '<string>',
    hfToken: '<string>',
    kvCacheEnabled: true,
    cpuOffloadingEnabled: true,
    nodeId: '<string>'
  })
};

fetch('https://api.tensormesh.ai/v1/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "model": {
    "modelId": "<string>",
    "deploymentId": "<string>",
    "userId": "<string>",
    "description": "<string>",
    "modelPath": "<string>",
    "modelName": "<string>",
    "status": "MODEL_STATUS_UNSPECIFIED",
    "events": [
      {
        "createdAt": "2023-11-07T05:31:56Z",
        "log": "<string>",
        "eventType": "EVENT_TYPE_UNSPECIFIED"
      }
    ],
    "createdAt": "2023-11-07T05:31:56Z",
    "updatedAt": "2023-11-07T05:31:56Z",
    "modelSpec": {},
    "infra": {
      "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
      "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
      "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
      "onpremRegion": "<string>"
    },
    "gpuCount": 123,
    "gpuType": "GPU_TYPE_UNSPECIFIED",
    "replicas": 123,
    "endpoint": "<string>",
    "apiKey": "<string>"
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

POST

https://api.tensormesh.ai

models

Deploy Model

curl --request POST \
  --url https://api.tensormesh.ai/v1/models \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "modelName": "<string>",
  "userId": "<string>",
  "description": "<string>",
  "infra": {
    "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
    "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
    "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
    "onpremRegion": "<string>"
  },
  "modelPath": "<string>",
  "gpuCount": 123,
  "gpuType": "GPU_TYPE_UNSPECIFIED",
  "modelSpec": {},
  "apiKey": "<string>",
  "hfToken": "<string>",
  "kvCacheEnabled": true,
  "cpuOffloadingEnabled": true,
  "nodeId": "<string>"
}
'

import requests

url = "https://api.tensormesh.ai/v1/models"

payload = {
    "modelName": "<string>",
    "userId": "<string>",
    "description": "<string>",
    "infra": {
        "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
        "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
        "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
        "onpremRegion": "<string>"
    },
    "modelPath": "<string>",
    "gpuCount": 123,
    "gpuType": "GPU_TYPE_UNSPECIFIED",
    "modelSpec": {},
    "apiKey": "<string>",
    "hfToken": "<string>",
    "kvCacheEnabled": True,
    "cpuOffloadingEnabled": True,
    "nodeId": "<string>"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    modelName: '<string>',
    userId: '<string>',
    description: '<string>',
    infra: {
      cloudProvider: 'CLOUD_PROVIDER_UNSPECIFIED',
      nebiusRegion: 'NEBIUS_REGION_UNSPECIFIED',
      lambdaRegion: 'LAMBDA_REGION_UNSPECIFIED',
      onpremRegion: '<string>'
    },
    modelPath: '<string>',
    gpuCount: 123,
    gpuType: 'GPU_TYPE_UNSPECIFIED',
    modelSpec: {},
    apiKey: '<string>',
    hfToken: '<string>',
    kvCacheEnabled: true,
    cpuOffloadingEnabled: true,
    nodeId: '<string>'
  })
};

fetch('https://api.tensormesh.ai/v1/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "model": {
    "modelId": "<string>",
    "deploymentId": "<string>",
    "userId": "<string>",
    "description": "<string>",
    "modelPath": "<string>",
    "modelName": "<string>",
    "status": "MODEL_STATUS_UNSPECIFIED",
    "events": [
      {
        "createdAt": "2023-11-07T05:31:56Z",
        "log": "<string>",
        "eventType": "EVENT_TYPE_UNSPECIFIED"
      }
    ],
    "createdAt": "2023-11-07T05:31:56Z",
    "updatedAt": "2023-11-07T05:31:56Z",
    "modelSpec": {},
    "infra": {
      "cloudProvider": "CLOUD_PROVIDER_UNSPECIFIED",
      "nebiusRegion": "NEBIUS_REGION_UNSPECIFIED",
      "lambdaRegion": "LAMBDA_REGION_UNSPECIFIED",
      "onpremRegion": "<string>"
    },
    "gpuCount": 123,
    "gpuType": "GPU_TYPE_UNSPECIFIED",
    "replicas": 123,
    "endpoint": "<string>",
    "apiKey": "<string>"
  }
}

{
  "code": 123,
  "message": "<string>",
  "details": [
    {
      "@type": "<string>"
    }
  ]
}

Authorizations

Authorization

string

header

required

Bearer authentication using an access token. Format: Bearer <access_token>

Body

application/json

modelName

string

Model nick name. Must be unique per user.

userId

string

User ID who owns this model. Must be a valid UUID.

description

string

Optional description of the model.

infra

object

Infra specifies the infrastructure configuration for deploying and running models.

This message defines where a model deployment should run by specifying both the cloud provider and the specific region. It uses a oneof for region selection to ensure type-safe region specification based on the chosen provider.

See also: tensormesh/common/v1/cloud_provider.proto for provider and region enum definitions

Show child attributes

modelPath

string

Model path (e.g., HuggingFace model ID).

gpuCount

integer<int64>

Number of GPUs to allocate for this model.

gpuType

enum<string>

default:GPU_TYPE_UNSPECIFIED

GPUType specifies the type of GPU to use for a model deployment.

This enum defines the supported GPU types for model deployments. It allows clients to specify the exact GPU hardware they need for their models.

enum definitions

Available options:

GPU_TYPE_UNSPECIFIED,

GPU_TYPE_A100,

GPU_TYPE_H100,

GPU_TYPE_H200,

GPU_TYPE_B200

modelSpec

object

Additional model-specific configuration.

apiKey

string

hfToken

string

kvCacheEnabled

boolean

Enable KV cache.

cpuOffloadingEnabled

boolean

Enable CPU offloading.

nodeId

string

Response

A successful response.

model

object

Model represents a model instance created by user.

Show child attributes

Create Stripe Setup Intent

Model Check

⌘I