> ## Documentation Index > Fetch the complete documentation index at: https://runcrate.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # List cluster offers > The machines a cluster of this size can be created on now, priced by the machine: lowest `hourly_rate_per_node` first, at most 3 per location, interconnect and deployment type. Leave `gpus_per_node` out to see every size of machine for the GPU. Datacenter hosts only unless `include_community=true`. ## OpenAPI ````yaml /api-reference/openapi.json get /clusters/offers openapi: 3.1.0 info: title: Runcrate API version: 1.0.0 summary: OpenAI-compatible inference API + GPU infrastructure API. description: >- Runcrate exposes two API surfaces. The inference API at `https://api.runcrate.ai/v1` is OpenAI-compatible: it accepts the standard OpenAI SDK with the base URL changed. The infrastructure API at `https://www.runcrate.ai/api/v1` manages GPU instances, jobs, persistent volumes, environments, SSH keys, templates, and billing. Both share a single `rc_live_*` API key. Pricing is per-token, per-image, per-second, or per-minute on the inference API (varies by model; see https://www.runcrate.ai/api/models/catalog for live rates) and per-second on GPU rentals (see https://www.runcrate.ai/pricing for hourly rates per GPU class). All infrastructure API responses are wrapped in `{ "data": ... }`. List responses also include a `meta` object with pagination cursors. Error responses use `{ "error": { "code": "...", "message": "..." } }`. termsOfService: https://www.runcrate.ai/terms contact: name: Runcrate url: https://www.runcrate.ai/contact license: name: Proprietary url: https://www.runcrate.ai/terms servers: - url: https://api.runcrate.ai/v1 description: Inference API (OpenAI-compatible) - url: https://www.runcrate.ai/api/v1 description: >- Infrastructure API (instances, jobs, storage, environments, ssh-keys, templates, billing) security: - ApiKeyAuth: [] tags: - name: Chat description: OpenAI-compatible chat completions. - name: Messages description: Anthropic-compatible Messages API, for Claude Code and the Anthropic SDKs. - name: Responses description: >- OpenAI-compatible Responses API, for Codex and responses.create. Nothing is stored. - name: Images description: Text-to-image generation. - name: Videos description: Async text-to-video and image-to-video generation. - name: Audio description: Text-to-speech and speech-to-text. - name: Embeddings description: Vector embeddings for RAG and search. - name: Models description: Model catalog discovery. - name: Instances description: GPU instance lifecycle. - name: Jobs description: >- Run one command on its own GPU machine. The machine stops, and billing ends, when the command exits. - name: Schedules description: >- Start an instance or a job later: once at a set time, or on a repeating cron schedule in your timezone. - name: Clusters description: >- Multi-machine GPU clusters on a private network, with Slurm, Kubernetes or Ray, bought by the machine. All or nothing: every machine starts or none does, billed from when every machine is up. - name: Storage description: Persistent volume management. - name: Environments description: Resource isolation containers within a workspace. - name: Secrets description: >- Names of the secrets an environment's machines get. Values are set in the dashboard and never returned. - name: SSH Keys description: SSH key management for instance access. - name: Templates description: Pre-built instance images and configurations. - name: Billing description: Credit balance, transactions, usage metrics. - name: Model calls description: >- The log of calls to the inference API, kept 30 days: outcome, timing, tokens, cost, end user, session and tags. Never the prompt or the answer. paths: /clusters/offers: servers: - url: https://www.runcrate.ai/api/v1 get: tags: - Clusters summary: List cluster offers description: >- The machines a cluster of this size can be created on now, priced by the machine: lowest `hourly_rate_per_node` first, at most 3 per location, interconnect and deployment type. Leave `gpus_per_node` out to see every size of machine for the GPU. Datacenter hosts only unless `include_community=true`. operationId: listClusterOffers parameters: - name: gpu_type in: query schema: type: string description: e.g. `H100`. - name: gpus_per_node in: query schema: type: integer enum: - 1 - 2 - 4 - 8 description: >- Only machines with this many GPUs each. Another whole number answers 400, anything else 422. - name: nodes in: query schema: type: integer minimum: 2 maximum: 64 default: 2 description: >- The number of machines: only offers that can create this many, and `hourly_rate` is for this many. - name: region in: query schema: type: string description: A region, the start of one, or a city or country. - name: include_community in: query schema: type: boolean default: false - name: stack in: query schema: type: string enum: - none - slurm - kubernetes - ray description: Only offers that can run this stack. - name: volume in: query schema: type: boolean default: false description: >- The cluster will get a volume (`storage_id`): only machines that may hold one, never community hosts. responses: '200': description: Offers. content: application/json: schema: type: object required: - data properties: data: type: array items: $ref: '#/components/schemas/ClusterOffer' '400': description: >- `bad_request`: `gpus_per_node` is a whole number machines do not come with (they have 1, 2, 4 or 8 GPUs). content: application/json: schema: $ref: '#/components/schemas/Error' '401': $ref: '#/components/responses/Unauthorized' '404': description: >- `FEATURE_OFF`: self-serve clusters are not on for this workspace yet (request a quote in the dashboard). content: application/json: schema: $ref: '#/components/schemas/Error' '422': description: >- `validation_error`: `nodes`, `gpus_per_node` or `stack` is out of range. content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ClusterOffer: type: object description: >- One kind of machine a cluster of this size can be created on now, priced by the machine. Offers change as capacity moves: create soon after reading one. required: - offer_id - gpu_type - gpus_per_node - node_count - min_nodes - max_nodes - nodes_available - deployment_type - host_tier - location - interconnect - hourly_rate_per_node - hourly_rate - stacks - resize - node properties: offer_id: type: string description: Pass it to `POST /clusters`. gpu_type: type: string example: H100 gpus_per_node: type: integer enum: - 1 - 2 - 4 - 8 description: GPUs on each machine. node_count: type: integer description: 'The number of machines `hourly_rate` is for: the `nodes` asked for.' min_nodes: type: integer max_nodes: type: integer allowed_node_counts: type: array items: type: integer description: >- Only these numbers of machines can be created from this offer. Absent: any from `min_nodes` to `max_nodes`. nodes_available: type: integer nullable: true description: How many machines can start now; null when only a launch can tell. deployment_type: type: string enum: - vm - baremetal - container host_tier: type: string enum: - datacenter - community description: Community hosts appear only with `include_community=true`. location: type: string example: Dallas, TX, United States country_code: type: string description: >- ISO country code of the location. Absent when the location names no known country. example: US interconnect: $ref: '#/components/schemas/ClusterInterconnect' hourly_rate_per_node: type: number description: USD per hour for one machine. hourly_rate: type: number description: >- USD per hour for the whole cluster: `hourly_rate_per_node` times `node_count`. stacks: type: array items: type: string enum: - none - slurm - kubernetes - ray description: The software this offer can run. resize: type: boolean description: Workers can be added or removed after create. boot_estimate_sec: type: integer description: How long a machine of this offer usually takes to boot, when known. node: type: object description: One machine. required: - vcpus - memory_gb - storage_gb properties: vcpus: type: integer memory_gb: type: number storage_gb: type: number vram_gb: type: number description: Per GPU. Error: type: object required: - error properties: error: type: object required: - code - message properties: code: type: string description: >- Machine-readable error code (e.g. `validation_error`, `unauthorized`, `not_found`, `insufficient_credits`, `rate_limited`, `internal_error`). message: type: string description: Human-readable error message. details: type: object additionalProperties: true description: Optional structured error context. ClusterInterconnect: type: object description: How the machines talk to each other. required: - kind - label properties: kind: type: string enum: - infiniband - roce - ethernet description: Self-serve clusters are `ethernet` today. rate_gbps: type: number description: Link rate per machine, when known. label: type: string description: What the dashboard shows, e.g. `Ethernet`. note: type: string description: >- What the link is good for, when it is not a training fabric. Every `ethernet` cluster has one. responses: Unauthorized: description: Missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: ApiKeyAuth: type: http scheme: bearer description: >- Use a Runcrate API key with the `rc_live_*` prefix as the bearer token. Create one at https://www.runcrate.ai/dashboard/api-keys. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.