> ## 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. # Quote GPU instance > Price an instance request before launching it. Runs the same placement as a launch: an existing `volumeId` pins placement to where that volume lives, and inline `storage` is priced in and placed with the GPU. Answers with the all-in hourly price, what survives stop and terminate, what keeps billing, and a `quoteId` to launch exactly this. A request that cannot be satisfied answers `409 no_capacity` with a reason and alternatives, before anything is created or charged. Nothing is reserved; quotes expire after 120 seconds. Requires compute `read` access. ## OpenAPI ````yaml /api-reference/openapi.json post /v1/gpu/instances/quote openapi: 3.0.3 info: title: AI Reserve Gateway API description: >- The AI Reserve API surface — OpenAI-compatible chat completions, Anthropic-compatible messages, Bedrock Converse, images, video, files, text-to-speech, realtime voice sessions, and provider-hidden GPU infrastructure — 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: 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: 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. paths: /v1/gpu/instances/quote: post: tags: - GPU Infrastructure summary: Quote GPU instance description: >- Price an instance request before launching it. Runs the same placement as a launch: an existing `volumeId` pins placement to where that volume lives, and inline `storage` is priced in and placed with the GPU. Answers with the all-in hourly price, what survives stop and terminate, what keeps billing, and a `quoteId` to launch exactly this. A request that cannot be satisfied answers `409 no_capacity` with a reason and alternatives, before anything is created or charged. Nothing is reserved; quotes expire after 120 seconds. Requires compute `read` access. operationId: quoteGpuInstance parameters: [] requestBody: required: true content: application/json: schema: type: object properties: accelerator: type: string enum: - A40_48GB - A100_80GB - H100_80GB - H100_NVL_94GB - H200_141GB - B200_180GB - B300_288GB - L40_48GB - L40S_48GB - RTX_2000_ADA_16GB - RTX_4000_ADA_20GB - RTX_6000_ADA_48GB - RTX_A5000_24GB - RTX_PRO_4000_24GB - RTX_PRO_4500_32GB - RTX_PRO_6000_96GB - RTX_PRO_6000_MIG_24GB - RTX_PRO_6000_MIG_48GB - MI300X_192GB count: default: 1 type: integer minimum: 1 maximum: 16 region: type: string enum: - north_america - united_states - canada - europe - asia_pacific - oceania name: type: string minLength: 1 maxLength: 120 image: type: string minLength: 1 maxLength: 500 pattern: >- ^(?![A-Za-z][A-Za-z0-9+.-]*:\/\/)[A-Za-z0-9][A-Za-z0-9./_:@-]*$ diskGb: default: 50 type: integer minimum: 1 maximum: 1024 volumeId: 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)$ volumeMountPath: default: /workspace type: string maxLength: 120 pattern: ^\/[A-Za-z0-9_-]+(?:\/[A-Za-z0-9_-]+)*\/?$ storage: type: object properties: persistentGb: type: integer minimum: 10 maximum: 4096 mountPath: default: /workspace type: string maxLength: 120 pattern: ^\/[A-Za-z0-9_-]+(?:\/[A-Za-z0-9_-]+)*\/?$ required: - persistentGb additionalProperties: false registryCredentialId: 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)$ sshKeyIds: default: [] maxItems: 20 type: array items: 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)$ sshPublicKey: type: string minLength: 1 maxLength: 16384 env: default: {} type: object additionalProperties: type: string maxLength: 16384 ports: anyOf: - type: array items: type: object properties: port: type: integer minimum: 1 maximum: 65535 protocol: type: string enum: - http - tcp - udp required: - port - protocol additionalProperties: false - type: string dockerStartCmd: default: [] maxItems: 32 type: array items: type: string maxLength: 4096 publicPortsAcknowledged: default: false type: boolean maxHourlyPrice: type: string pattern: ^\d{1,7}(?:\.\d{1,6})?$ required: - accelerator additionalProperties: false responses: '200': description: Priced. The request can be launched as quoted. content: application/json: schema: type: object properties: id: type: string description: Signed quote token. Same as `quoteId`. quoteId: type: string description: >- Pass as `quoteId` to `POST /v1/gpu/instances` to launch exactly what was quoted. Expires after 120 seconds. kind: type: string enum: - instance 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)))$ accelerator: type: string count: type: integer minimum: -9007199254740991 maximum: 9007199254740991 region: nullable: true description: Normalized region the instance would run in. type: string availability: type: string enum: - LOW - MEDIUM - HIGH - UNKNOWN maxHourlyPrice: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: USD amount as a six-decimal string. Never a float. price: type: object properties: gpuUsdPerHour: nullable: true type: string pattern: ^\d+(?:\.\d{1,6})?$ description: USD amount as a six-decimal string. Never a float. rootDiskUsdPerHour: nullable: true type: string pattern: ^\d+(?:\.\d{1,6})?$ description: USD amount as a six-decimal string. Never a float. instanceUsdPerHour: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: GPU + root disk. persistentStorageUsdPerHour: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: New or attached persistent volume. totalRunningUsdPerHour: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: Everything that bills while the instance runs. storageOnlyUsdPerHour: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: What keeps billing after stop or terminate. required: - gpuUsdPerHour - rootDiskUsdPerHour - instanceUsdPerHour - persistentStorageUsdPerHour - totalRunningUsdPerHour - storageOnlyUsdPerHour additionalProperties: false storage: type: object properties: rootGb: type: integer minimum: -9007199254740991 maximum: 9007199254740991 rootPersistence: type: string enum: - ephemeral persistent: nullable: true type: object properties: volumeId: nullable: true description: >- Null on a quote for storage that will be created at launch. 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)$ sizeGb: type: integer minimum: -9007199254740991 maximum: 9007199254740991 mountPath: type: string status: type: string usdPerHour: type: string pattern: ^\d+(?:\.\d{1,6})?$ description: >- Hourly storage price. Continues after the instance stops or is terminated. billsUntilDeleted: type: boolean enum: - true survivesStop: type: boolean enum: - true survivesTerminate: type: boolean enum: - true multiAttach: type: boolean enum: - false description: One instance at a time. required: - volumeId - sizeGb - mountPath - usdPerHour - billsUntilDeleted - survivesStop - survivesTerminate - multiAttach additionalProperties: false description: >- A persistent volume as seen from an instance or quote, with the facts that matter for your bill and your files. required: - rootGb - rootPersistence - persistent additionalProperties: false runtime: type: object properties: type: type: string enum: - container profile: nullable: true type: string required: - type - profile additionalProperties: false capabilities: type: object properties: start: type: boolean stop: type: boolean restart: type: boolean ssh: type: boolean logs: type: boolean persistentVolumes: type: boolean stopPreservesRootDisk: type: boolean required: - start - stop - restart - ssh - logs - persistentVolumes - stopPreservesRootDisk additionalProperties: false required: - id - quoteId - kind - expiresAt - accelerator - count - region - availability - price - storage - runtime - capabilities additionalProperties: false description: >- A priced, placeable instance request. If this is returned, the request can be launched as quoted; a request that cannot be satisfied answers `409 no_capacity` instead. '400': description: Invalid request, missing Idempotency-Key, or schema violation. content: application/json: schema: $ref: '#/components/schemas/ComputeError' '401': description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/ComputeError' '402': description: >- Wallet not enabled or not funded (`insufficient_funds`, `storage_delinquent`). content: application/json: schema: $ref: '#/components/schemas/ComputeError' '403': description: Key lacks the required compute access (`read` or `manage`). content: application/json: schema: $ref: '#/components/schemas/ComputeError' '404': description: Resource not found or owned by another organization. content: application/json: schema: $ref: '#/components/schemas/ComputeError' '409': description: >- `no_capacity` with `details` (see `ComputeNoCapacityDetails`): why nothing can be placed and what would work; or `volume_in_use` when the named volume is not ready or already attached. content: application/json: schema: $ref: '#/components/schemas/ComputeError' '503': description: Compute disabled or provider unavailable. content: application/json: schema: $ref: '#/components/schemas/ComputeError' security: - bearerAuth: [] - apiKeyAuth: [] components: schemas: ComputeError: type: object properties: error: type: object properties: message: type: string type: type: string enum: - invalid_request_error - authentication_error - permission_error - server_error param: nullable: true type: string code: type: string description: >- Machine-readable Compute error code, e.g. `quote_expired`, `price_changed`, `operation_conflict`, `no_capacity`, `volume_in_use`, `insufficient_funds`, `compute_access_required`, `not_found`. details: description: >- Machine-readable context for some codes. For `no_capacity` see `ComputeNoCapacityDetails`. type: object additionalProperties: {} required: - message - type - param - code additionalProperties: false required: - error additionalProperties: false description: OpenAI-shaped error envelope returned on every 4xx/5xx. 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). apiKeyAuth: type: apiKey in: header name: x-api-key description: The same API key sent as an `x-api-key` header. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.