> ## 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. # Seal a selected offer, requested allocation, supported actions, price, and expiry. > Seal a selected offer, requested allocation, supported actions, price, and expiry.. Runs as the token's owner within their role; the portal's own authorization and audit log apply. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/admin/quote_sandbox 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/admin/quote_sandbox: post: tags: - 'Admin: Compute Runtime' summary: >- Seal a selected offer, requested allocation, supported actions, price, and expiry. description: >- Seal a selected offer, requested allocation, supported actions, price, and expiry.. Runs as the token's owner within their role; the portal's own authorization and audit log apply. operationId: quote_sandbox requestBody: required: true content: application/json: schema: type: object properties: workspaceId: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ offerId: type: string minLength: 1 maxLength: 255 requested: type: object properties: vcpu: type: integer minimum: 1 maximum: 256 memoryMb: type: integer minimum: 256 maximum: 2097152 diskGb: type: integer minimum: 1 maximum: 65536 architecture: type: string enum: - amd64 - arm64 region: nullable: true type: string minLength: 1 maxLength: 128 pattern: ^[A-Za-z0-9][A-Za-z0-9._-]*$ gpu: nullable: true type: object properties: accelerator: type: string minLength: 1 maxLength: 120 count: type: integer minimum: 1 maximum: 16 required: - count additionalProperties: false required: - vcpu - memoryMb - diskGb - architecture - region - gpu additionalProperties: false description: Provider-neutral resources requested by the caller. maxRateUsdPerHour: type: string pattern: ^\d{1,10}(?:\.\d{1,6})?$ clientId: description: >- Required only for a platform operator targeting an organization. type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ idempotencyKey: description: Optional stable retry key. type: string minLength: 8 maxLength: 180 pattern: ^[A-Za-z0-9:_-]+$ required: - workspaceId - offerId - requested additionalProperties: false responses: '200': description: 'Executed successfully (`ok: true`).' content: application/json: schema: allOf: - $ref: '#/components/schemas/AdminOutcome' - type: object properties: data: type: object properties: id: type: string minLength: 16 maxLength: 8192 description: >- Opaque sealed quote token. Treat it as a credential. quoteId: type: string minLength: 16 maxLength: 8192 description: >- Alias for `id`; pass this value when creating a sandbox. object: type: string enum: - sandbox_quote sealed: type: boolean enum: - true offerId: type: string minLength: 1 maxLength: 255 workspaceId: type: string format: uuid pattern: >- ^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$ profile: type: string enum: - standard-vm - elastic-vm - gpu - portable provider: type: object properties: id: type: string minLength: 1 maxLength: 120 pattern: ^[a-z0-9](?:[a-z0-9._-]*[a-z0-9])?$ description: >- Stable public provider slug. It is a response fact, never a placement input. name: type: string minLength: 1 maxLength: 120 required: - id - name additionalProperties: false description: >- The provider selected by the control plane. Provider account, offer, allocation, region, and operation identifiers are never exposed. requested: type: object properties: vcpu: type: integer minimum: 1 maximum: 256 memoryMb: type: integer minimum: 256 maximum: 2097152 diskGb: type: integer minimum: 1 maximum: 65536 architecture: type: string enum: - amd64 - arm64 region: nullable: true type: string minLength: 1 maxLength: 128 pattern: ^[A-Za-z0-9][A-Za-z0-9._-]*$ gpu: nullable: true type: object properties: accelerator: type: string minLength: 1 maxLength: 120 count: type: integer minimum: 1 maximum: 16 required: - count additionalProperties: false required: - vcpu - memoryMb - diskGb - architecture - region - gpu additionalProperties: false description: >- Provider-neutral resources requested by the caller. allocated: type: object properties: vcpu: type: integer minimum: 1 maximum: 256 memoryMb: type: integer minimum: 256 maximum: 2097152 diskGb: type: integer minimum: 1 maximum: 65536 architecture: type: string enum: - amd64 - arm64 region: type: string minLength: 1 maxLength: 128 pattern: ^[A-Za-z0-9][A-Za-z0-9._-]*$ gpu: nullable: true type: object properties: accelerator: type: string minLength: 1 maxLength: 120 count: type: integer minimum: 1 maximum: 16 memoryMb: type: integer minimum: 0 exclusiveMinimum: true maximum: 9007199254740991 required: - accelerator - count additionalProperties: false required: - vcpu - memoryMb - diskGb - architecture - region - gpu additionalProperties: false description: >- Resources actually allocated. This never contains provider-native identifiers. supportedActions: maxItems: 8 type: array items: type: string enum: - start - stop - pause - resume - execute - expose_endpoint - revoke_endpoint - terminate pricing: type: object properties: currency: type: string enum: - USD billingModel: type: string enum: - reserved - observed description: >- `reserved` settles sealed quote-rate time increments; `observed` settles provider-reported actual spend after the reporting lag. rateUsdPerHour: type: string pattern: ^\d{1,10}(?:\.\d{1,6})?$ billingIncrementSeconds: type: integer minimum: 1 maximum: 3600 minimumChargeUsd: type: string pattern: ^\d{1,10}(?:\.\d{1,6})?$ reserveUsd: type: string pattern: ^\d{1,10}(?:\.\d{1,6})?$ description: Amount reserved when the quote is accepted. required: - currency - billingModel - rateUsdPerHour - billingIncrementSeconds - minimumChargeUsd - reserveUsd additionalProperties: false createdAt: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z|([+-](?:[01]\d|2[0-3]):[0-5]\d)))$ expiresAt: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d:[0-5]\d(?:\.\d+)?(?:Z|([+-](?:[01]\d|2[0-3]):[0-5]\d)))$ required: - id - quoteId - object - sealed - offerId - workspaceId - profile - provider - requested - allocated - supportedActions - pricing - createdAt - expiresAt additionalProperties: false description: >- A sealed, expiring provider and price decision. Accepting it cannot silently switch providers. '400': description: Invalid input for this operation, or a confirm token problem. content: application/json: schema: $ref: '#/components/schemas/AdminRefusal' '401': description: >- Missing, expired or revoked management token. Inference API keys are refused. content: application/json: schema: $ref: '#/components/schemas/AdminAuthError' '403': description: The operation is not available at the caller's access level. content: application/json: schema: $ref: '#/components/schemas/AdminRefusal' '404': description: Unknown operation id. content: application/json: schema: $ref: '#/components/schemas/AdminRefusal' '409': description: The target changed since it was described (`target_changed`). content: application/json: schema: $ref: '#/components/schemas/AdminRefusal' '422': description: >- Executed but the operation reported a failure (`ok: false`, see `message`). content: application/json: schema: $ref: '#/components/schemas/AdminOutcome' '429': description: Organization request budget exhausted; see `Retry-After`. content: application/json: schema: $ref: '#/components/schemas/AdminAuthError' security: - managementToken: [] components: schemas: AdminOutcome: type: object properties: status: type: string enum: - executed ok: type: boolean description: Whether the operation succeeded. summary: type: string description: >- The consent line describing what was done, built from resolved labels. message: type: string description: Human-readable result line. data: description: Operation payload (reads) or detail worth relaying (writes). secret: description: >- A one-time secret the operation minted (API key, credential). Shown once; store it now. type: string sensitive: description: 'Present exactly when `secret` is: redact this response from logs.' type: boolean enum: - true required: - status - ok - summary - message additionalProperties: false AdminRefusal: type: object properties: status: type: string enum: - refused code: type: string enum: - unknown_op - not_allowed - insufficient_scope - invalid_input - confirm_invalid - confirm_expired - target_changed error: type: string required: - status - code - error additionalProperties: false AdminAuthError: type: object properties: error: type: string error_description: type: string required: - error - error_description additionalProperties: false 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). managementToken: type: http scheme: bearer bearerFormat: aireserve_mcp_… description: >- A management token: minted by the OAuth flow (`aireserve login`, or an MCP client's Authenticate step) or on the portal Keys page under Management Keys. Inference API keys are refused. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.