> ## Documentation Index > Fetch the complete documentation index at: https://docs.halfpagetechnologies.com/llms.txt > Use this file to discover all available pages before exploring further. # Create an image record > Create an image record for the resumable upload flow. Pass `resumable: true` to open the upload in the same call: the response then carries `upload` with presigned part URLs — PUT each chunk of your file to its URL, call `POST /upload/{image_id}/complete`, and poll `GET /image/{image_id}` until `upload_status` is `ready`. (For files up to a few hundred MB the single-request `POST /upload` is simpler still — it creates the record for you and returns it `ready`.) The image counts against your plan's storage cap the moment it is created, so this returns `402` when the cap is reached — even before any bytes are uploaded. ## OpenAPI ````yaml /api-reference/openapi.json post /api/v1/image openapi: 3.1.0 info: title: HalfPage API description: > The **HalfPage API** runs Cellpose-based cell segmentation on your microscopy images programmatically — upload an image, run a prediction, and export the resulting cell masks, ROIs, and measurements. ## Base URL ``` https://api.halfpagetechnologies.com/backend/api/v1 ``` Every path in this reference is relative to that base URL. A staging environment is available at `https://staging-api.halfpagetechnologies.com/backend/api/v1`. ## Authentication Authenticate every request with an API key in the `Authorization` header as a bearer token: ``` Authorization: Bearer hp_live_xxxxxxxxxxxxxxxxxxxxxxxx ``` Create and manage keys from the **API Keys** section of the HalfPage dashboard — keys cannot be minted through the API. A key is scoped to the organization that owns it; every resource you create or read is confined to that organization. Requests without a valid key receive `401`; a valid key used against an endpoint outside the public product surface receives `403`. ## Core workflow Segmentation runs asynchronously on GPU workers, so the API is poll-based: 1. **Upload an image** (`POST /upload`) as `multipart/form-data` with a `file` field. One call: the image record is created automatically and the response returns it already `ready`, with the `image_id` for the next step. *(Large files: `POST /image` with `resumable: true` returns presigned part URLs — PUT the chunks, call `POST /upload/{image_id}/complete`, then poll `GET /image/{image_id}` until `upload_status` is `ready`.)* 2. **Pick a model** (`GET /models`) and **submit a prediction** (`POST /job/prediction`) with the `image_id` and a `model_id`. This returns a `job_id`. 3. **Poll the job** (`GET /job/{job_id}`) until `status` is `COMPLETED`; the response then carries a `segmentation_id`. 4. **Export** results for that segmentation as CSV measurements (`GET /export/{segmentation_id}/measurements.csv`), GeoJSON ROIs (`.../rois.geojson`), or an ImageJ ROI archive (`.../rois.zip`). To collect a whole project at once, `GET /export/project/{folder_id}/measurements.csv` returns every analyzed image in it as one CSV. ## Quotas Uploads and analyses are metered against your plan. Exceeding your image storage cap or monthly analysis cap returns `402` with a human-readable `detail` explaining the limit — upgrade your plan to raise it. version: 1.0.0 servers: - url: https://api.halfpagetechnologies.com/backend description: Production - url: https://staging-api.halfpagetechnologies.com/backend description: Staging security: [] tags: - name: upload description: >- Get microscopy images into HalfPage. The single-request `POST /upload` is the simplest path: it creates the image record for you and returns it `ready`. For large files over flaky connections, use the resumable flow: `POST /image` with `resumable: true` (or `init`), PUT the presigned parts, then `complete` (no ETag bookkeeping needed) and poll the image until `ready`. - name: job description: >- Submit and poll asynchronous GPU jobs. `POST /job/prediction` runs segmentation on a ready image; `POST /job/training` fine-tunes a custom model. Both return a `job_id` you poll via `GET /job/{job_id}` until it is `COMPLETED`. - name: image description: >- Create and manage image records. `POST /image` starts the resumable upload flow (with `resumable: true` it returns presigned part URLs in the same call); poll `GET /image/{image_id}` for the upload lifecycle (`uploading` → `processing` → `ready`) and metadata such as pixel `shape`, and delete images you no longer need. - name: segmentation description: >- Read the segmentations produced by prediction jobs and derive new ones. A segmentation is the set of detected cell ROIs for an image; fetch its metadata, regenerate its mask from annotations, or fork a refinement to iterate on the result. - name: export description: >- Download results in analysis-ready formats: a CSV of per-cell measurements, a GeoJSON of ROI polygons, or a ZIP of ImageJ-compatible ROIs. Export one segmentation at a time, or pull every analyzed image in a project into a single CSV. Both CSV endpoints accept a `columns` parameter to narrow the output to the measurements you care about. - name: models description: >- List the segmentation models available to your organization — the shared public base models (e.g. `cpsam`) plus any custom models you have trained — to choose a `model_id` for a prediction job. paths: /api/v1/image: post: tags: - image summary: Create an image record description: >- Create an image record for the resumable upload flow. Pass `resumable: true` to open the upload in the same call: the response then carries `upload` with presigned part URLs — PUT each chunk of your file to its URL, call `POST /upload/{image_id}/complete`, and poll `GET /image/{image_id}` until `upload_status` is `ready`. (For files up to a few hundred MB the single-request `POST /upload` is simpler still — it creates the record for you and returns it `ready`.) The image counts against your plan's storage cap the moment it is created, so this returns `402` when the cap is reached — even before any bytes are uploaded. operationId: create_image_api_v1_image_post requestBody: content: application/json: schema: $ref: '#/components/schemas/CreateImageRequest' required: true responses: '201': description: The image record was created; upload the pixels next. content: application/json: schema: $ref: '#/components/schemas/CreateImageResponse' example: id: 3fa85f64 name: sample.tif upload_status: uploading image_type: TIFF size: 4194304 created_at: '2026-07-16T12:00:00Z' upload: upload_id: 2~aBcD3fGhIjKlMnOpQrStUvWxYz part_size: 33554432 urls: - part_number: 1 url: https://halfpage.s3.amazonaws.com/...&partNumber=1 '401': description: >- Missing or invalid credentials. Supply a valid `Authorization: Bearer hp_live_...` API key. content: application/json: example: detail: Requires authentication schema: $ref: '#/components/schemas/ErrorResponse' '402': description: >- Image storage quota exceeded for your plan. Upgrade to store more images. content: application/json: example: detail: >- You've reached your storage limit of 100 images. Upgrade to store more. schema: $ref: '#/components/schemas/ErrorResponse' '404': description: The resource does not exist, or is not in your organization. content: application/json: example: detail: Image with id 3fa85f64-5717-4562-b3fc-2c963f66afa6 not found schema: $ref: '#/components/schemas/ErrorResponse' '422': description: >- The request body is invalid (e.g. missing `name`/`size`, or a bad `size` with `resumable`). '501': description: >- `resumable: true` but storage does not support multipart uploads (local dev only). security: - HTTPBearer: [] components: schemas: CreateImageRequest: properties: name: type: string title: Name description: Filename or label for the image. examples: - sample.tif size: type: integer title: Size description: Total size of the image file in bytes. examples: - 4194304 image_type: $ref: '#/components/schemas/ImageType' description: Image format. Only `TIFF` is currently supported. default: TIFF additional_info: additionalProperties: true type: object title: Additional Info description: Arbitrary JSON metadata to store alongside the image. folder_id: anyOf: - type: string format: uuid - type: 'null' title: Folder Id description: >- Optional folder to place the image in; it must belong to your organization. API clients typically have no folders and omit this. resumable: type: boolean title: Resumable description: >- Set to `true` to also open a resumable upload in the same call: the response then carries `upload` with presigned part URLs sized for `size` (so `size` must be exact). PUT each chunk to its URL, then call `POST /upload/{image_id}/complete` — no separate `/init` call needed. default: false type: object required: - name - size title: CreateImageRequest description: >- The metadata for a new image record. The pixels are uploaded separately; `size` is the total byte size of the file you will upload. Set `resumable` to also receive the presigned upload plan in the same response. Server-controlled fields (`id`, `created_by`, `organization_id`, `upload_status`) are not accepted here. examples: - name: sample.tif size: 4194304 CreateImageResponse: properties: id: type: string title: Id name: type: string title: Name upload_status: $ref: '#/components/schemas/UploadStatus' image_type: $ref: '#/components/schemas/ImageType' size: type: integer title: Size shape: anyOf: - items: type: integer type: array - type: 'null' title: Shape folder_id: anyOf: - type: string format: uuid - type: 'null' title: Folder Id created_at: type: string format: date-time title: Created At processed_at: anyOf: - type: string format: date-time - type: 'null' title: Processed At upload_error: anyOf: - type: string - type: 'null' title: Upload Error upload: anyOf: - $ref: '#/components/schemas/InitUploadResponse' - type: 'null' type: object required: - id - name - upload_status - image_type - size - created_at title: CreateImageResponse description: |- The created image record, plus — when `resumable: true` was requested — the presigned upload plan under `upload` (otherwise `null`). examples: - created_at: '2026-07-01T12:00:00Z' id: 3fa85f64-5717-4562-b3fc-2c963f66afa6 image_type: TIFF name: sample.tif processed_at: '2026-07-01T12:00:05Z' shape: - 512 - 512 - 3 size: 4194304 upload_status: ready ErrorResponse: properties: detail: type: string title: Detail examples: - Job with id 11111111-1111-1111-1111-111111111111 not found type: object required: - detail title: ErrorResponse description: |- The body returned for a handled error: a single human-readable ``detail`` string. ImageType: type: string enum: - TIFF title: ImageType UploadStatus: type: string enum: - uploading - processing - ready - failed title: UploadStatus description: >- Lifecycle of a resumable S3 multipart image upload. uploading -> row created, bytes still being PUT directly to S3 processing -> object landed in S3, backend is converting it off the event loop ready -> conversion done, `shape` populated, image is usable failed -> aborted or conversion failed (orphan-sweep cron will reap it) InitUploadResponse: properties: upload_id: type: string title: Upload Id part_size: type: integer title: Part Size urls: items: $ref: '#/components/schemas/PartUrlOut' type: array title: Urls type: object required: - upload_id - part_size - urls title: InitUploadResponse description: >- The presigned multipart plan: PUT each chunk of the file to its `url` (in part order), then call `/complete` — no body needed, the server verifies the uploaded parts with storage directly. The internal S3 object key is deliberately not exposed: the presigned `url`s already encode everything the client needs, and the key layout is a server-side implementation detail we keep off the public contract. examples: - part_size: 33554432 upload_id: 2~aBcD3fGhIjKlMnOpQrStUvWxYz urls: - part_number: 1 url: https://halfpage.s3.amazonaws.com/...&partNumber=1 - part_number: 2 url: https://halfpage.s3.amazonaws.com/...&partNumber=2 PartUrlOut: properties: part_number: type: integer title: Part Number url: type: string title: Url type: object required: - part_number - url title: PartUrlOut securitySchemes: HTTPBearer: type: http scheme: bearer ````