> ## Documentation Index > Fetch the complete documentation index at: https://docs.aireserve.com/llms.txt > Use this file to discover all available pages before exploring further. # Submit image edit job > Edit existing images: send `model`, a `prompt` describing the change, and `images` — one to nine public HTTPS URLs (the promptless utility models `bria-background-remove` and `topaz-image-upscale` take one image and no `prompt`). Asynchronous — answers **202** with a job (`{ id, status }`); poll `GET /v1/images/edits/{job_id}` until `status` is `succeeded` or `failed` and read the output URL from `result.images[0].url`. Billed per output image at the provider's list price (plus a per-input fee where the provider charges one), reserved at submit and settled when the job completes. Unknown and video model ids answer `400`. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/images/edits openapi: 3.0.3 info: title: AI Reserve Gateway API description: >- The AI Reserve API surface — inference, durable environments, workspaces, sandboxes, executions, agent runs, GPU infrastructure, and fine-tuning — all behind one endpoint and one API key. version: 1.0.0 servers: - url: https://api.aireserve.com security: - bearerAuth: [] tags: - name: Customers description: >- Per-end-customer usage, cost, and billable amounts for organizations that tag requests with their own customers. - name: Dedicated GPU endpoints description: >- OpenAI-compatible inference on your organization's own dedicated HuggingFace vLLM deployments, called with an ordinary AI Reserve API key. GPU time is billed from the wallet; requests add no per-token charge. - name: GPU Infrastructure description: >- Provision and manage provider-hidden GPU instances. The recommended Instances API accepts workload requirements and an hourly price ceiling; AI Reserve handles provider placement internally. Every mutation is asynchronous and returns an operation to poll. - name: Environments description: Immutable, versioned runtime definitions. - name: Workspaces description: Durable project storage pinned to one environment version. - name: Sandboxes description: >- Ephemeral provider-disclosed compute allocated from sealed quotes. Requests remain provider-neutral. - name: Executions description: Durable asynchronous operations and command, service, or agent executions. - name: Agent Runs description: Durable Agent SDK runs with replayable events and external artifacts. - name: Customer keys description: >- Mint, list, and revoke API keys pinned to your own end customers (and their organizations), so spend splits per customer without per-request tagging. - name: AWS CLI login description: >- Browser-authorization endpoints consumed by `aws login --profile …` (AWS CLI v2.32.0+). All three routes are unauthenticated — the caller has no credential until `/v1/token` succeeds. - name: Fine-tuning description: >- Fine-tune open models on your own data. Data lives in an S3 bucket inside your organization's AWS hub account; you name a base, LoRA or full, a price ceiling and how the result must be servable, and AI Reserve places the run on a backend internally. The result is a model in your bucket you can deploy or download. - name: 'Admin: Catalog' description: Discover the operations available to this token. - name: 'Admin: Analytics' description: Usage, spend and attribution reads. - name: 'Admin: API Keys' description: Organization and team inference keys. - name: 'Admin: Billing' description: Wallet, ledger and invoice reads. - name: 'Admin: Compute' description: GPU machines and persistent storage (quote, launch, inspect, stop). - name: 'Admin: Compute Runtime' description: >- Portable environments, workspaces, sandboxes, executions, operations and durable agent runs. - name: 'Admin: Containers' description: The organization's AWS account, ECS services, logs and secrets. - name: 'Admin: Files' description: Organization shared files. - name: 'Admin: Members' description: 'People in the organization: invite, profile, team, access, role.' - name: 'Admin: Models & Routing' description: Model availability, defaults, fallbacks and routing. - name: 'Admin: Organization' description: Retention, logging, branding, sign-in domains, classification. - name: 'Admin: Personal' description: The caller's own usage, budget, API keys and preferences. - name: 'Admin: Teams & Budgets' description: Teams, spend caps and allocations. - name: 'Admin: Training' description: Fine-tuning datasets, runs, models and deployments. paths: /v1/images/edits: post: tags: - Images summary: Submit image edit job description: >- Edit existing images: send `model`, a `prompt` describing the change, and `images` — one to nine public HTTPS URLs (the promptless utility models `bria-background-remove` and `topaz-image-upscale` take one image and no `prompt`). Asynchronous — answers **202** with a job (`{ id, status }`); poll `GET /v1/images/edits/{job_id}` until `status` is `succeeded` or `failed` and read the output URL from `result.images[0].url`. Billed per output image at the provider's list price (plus a per-input fee where the provider charges one), reserved at submit and settled when the job completes. Unknown and video model ids answer `400`. requestBody: required: true content: application/json: schema: type: object required: - model - images properties: model: minLength: 1 maxLength: 256 type: string prompt: minLength: 1 maxLength: 32000 type: string images: minItems: 1 maxItems: 9 type: array items: minLength: 1 maxLength: 4096 pattern: ^https?:// type: string size: pattern: ^\d{3,4}[x*]\d{3,4}$ type: string seed: minimum: -1 maximum: 2147483647 type: integer user: type: string example: model: nano-banana-2-edit prompt: Replace the sky with a dramatic sunset images: - https://example.com/photo.png responses: '202': description: >- Job accepted. Poll `GET /v1/images/edits/{job_id}` until `status` is `succeeded` or `failed`. content: application/json: schema: $ref: '#/components/schemas/ImageEditJob' example: id: 9c3f1a2b-4d5e-6f7a-8b9c-0d1e2f3a4b5c object: image.generation.job kind: image model: nano-banana-2-edit status: queued created_at: 1762459200 completed_at: null result: null error: null artifact_expires_at: null upstream_deleted_at: null '400': description: >- Validation error — the model is not an image-editing model, a prompt is missing (or sent to a promptless model), or an image URL is not HTTPS. '401': description: Missing or invalid API key. '402': description: Wallet balance insufficient to reserve the job's price. '403': description: >- No client context attached to the key, or the model is not on the key's allowlist. '429': description: Rate limit or the organization's concurrent image-job cap exceeded. '503': description: >- The provider rejected the job or is unavailable. Nothing was charged; retry. components: schemas: ImageEditJob: type: object description: >- An asynchronous image-edit job. Submit answers it with `status: queued`; polling returns the same object until it is terminal. required: - id - object - kind - model - status - created_at - completed_at - result - error properties: id: type: string format: uuid description: Job id — the path parameter for `GET /v1/images/edits/{job_id}`. object: type: string enum: - image.generation.job kind: type: string enum: - image model: type: string description: The image-editing model id the job was submitted with. status: type: string enum: - queued - running - succeeded - failed description: '`succeeded` and `failed` are terminal.' created_at: type: integer description: Unix seconds. completed_at: type: integer nullable: true description: Unix seconds once the job is terminal. result: type: object nullable: true additionalProperties: true description: >- Set when `status` is `succeeded`. The edited image URLs are under `images[].url`. properties: images: type: array items: type: object additionalProperties: true properties: url: type: string format: uri width: type: integer height: type: integer error: type: string nullable: true description: Set when `status` is `failed`. A failed job is never charged. artifact_expires_at: type: integer nullable: true description: >- Unix seconds after which the provider may delete the output; download before then. upstream_deleted_at: type: integer nullable: true served_model: type: string description: Present when a same-weights sibling served the job. served_provider: type: string description: Present alongside `served_model`. securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your AI Reserve API key (aireserve_api_…) from the API Keys page in the portal (https://portal.aireserve.com/keys). ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.