Account1

Adhoc Retrievers3

Agent Sessions11

Alerts16

Analytics41

Annotations9

Apps34

Batches4

Bucket Batches22

Bucket Objects10

Bucket Syncs15

Bucket Uploads7

Buckets7

BYO Documents5

Cluster Executions7

Cluster Triggers8

Clusters9

Collection Documents19

Collection Lifecycle2

Collection Schema1

Collection Taxonomies1

Collections14

Custom Models8

Data Subject Access Requests3

Discovery4

Document Lineage3

Documents6

Events1

Extractor Publishing5

Extractors5

Feature Extractors2

Feature Search1

Features1

Health4

Inference1

Manifest7

Marketplace14

Models6

Namespace Clone1

Namespace Extractors2

Namespace Migrations7

Namespace Snapshots6

Namespaces10

Notifications12

Onboarding2

Organization API Keys5

Organization Audit5

Organization Billing22

Organization Connections8

Organization Infrastructure1

Organization Secrets4

Organization Targets1

Organization Usage3

Organization Users5

Organizations3

Pricing1

Public Apps API5

Public Extractor Marketplace2

Public Notifications API1

Public Retriever API7

Public Templates API8

Published Retrievers8

Quickstart1

Resource Search1

Retriever API Keys3

Retriever Benchmarks4

Retriever Evaluations9

Retriever Interactions5

Retriever Stages1

Retrievers15

Scaffold Templates3

Signup1

Source Adapter2

Support14

Tasks3

Taxonomies13

Taxonomy Analytics6

Templates23

Triggers10

Webhooks5

Custom Models

Upload a custom model

Changed on Oct 9, 2026

Upload custom model weights to the namespace.

Requirements:

Organization must be on Enterprise tier

Supported Model Formats:

safetensors: SafeTensors format (recommended for transformers)
onnx: ONNX Runtime format
pytorch: PyTorch state_dict or TorchScript
huggingface: HuggingFace model directory

Base Images (auto-selected based on format):

mixpeek/serve-gpu:latest: For safetensors, pytorch, huggingface (includes torch, transformers)
mixpeek/serve-minimal:latest: For ONNX (includes onnxruntime only)

Important: Models run in fixed base images. You cannot install additional pip packages. All required frameworks (torch, transformers, onnxruntime) are pre-installed.

post/v1/namespaces/{namespace_id}/models

Request

Base URL: https://api.mixpeek.com
URL: https://api.mixpeek.com/v1/namespaces/{namespace_id}/models
Auth: HTTP bearer

Path parameters

namespace_idstring required

Request body multipart/form-data

filestring binary required

Model archive (.tar.gz)

namestring required

Model name

versionstring required

Model version

model_format'safetensors' | 'onnx' | 'pytorch' | 'huggingface' required

Model format

frameworkstring nullable

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

task_typestring nullable

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

num_cpusnumber

CPU requirements

num_gpusinteger

GPU requirements

memory_gbnumber

Memory in GB

Response

Successful Response

successboolean required

Whether upload succeeded

model_idstring required

Unique model identifier

deployment_status'deployed' | 'pending' | 'failed' | 'not_deployed' required

Deployment status

endpointstring required

Model inference endpoint

model_archive_urlstring required

S3 URL where archive is stored

Changes

Oct 9, 202661a175e8eb9a Revision changes
- warning
  removed the optional property from the response with the status
- info
  added the non-success response with the status
- info
  added the non-success response with the status
- info
  added the optional property to the response with the status
- info
  added the required property to the response with the status
- info
  added the required property to the response with the status
Oct 6, 2026b75474e978ff Revision changes
- info
  added the media type application/json for the response with the status
- info
  added the media type application/json for the response with the status

Operation history (3 revisions)