diff --git a/docs/build/api/gpu_cloud.md b/docs/build/api/gpu_cloud.md index 1891cf6..d43144a 100644 --- a/docs/build/api/gpu_cloud.md +++ b/docs/build/api/gpu_cloud.md @@ -34,7 +34,7 @@ When you create a key in the Fluence Console, give it **View & manage** access t | `GET` | `/v3/gpu/offers` | Lists offers: one placement each, with hardware, price, and availability | | `GET` | `/v3/gpu/offers/{id}` | Returns one offer | | `GET` | `/v3/gpu/offer-groups` | Groups offers by GPU configuration, with the lowest price of each group | -| `GET` | `/v3/gpu/offer-facets` | Lists the values you can filter by, such as GPU models, countries, and providers, with counts | +| `GET` | `/v3/gpu/offer-facets` | Lists the values you can filter by, such as GPU models and countries, with counts | | `GET` | `/v3/gpu/offer-picks` | Returns the cheapest offers with at least the GPU memory you need | | `POST` | `/v3/gpu/instance-quotes` | Shows which offer a request would get and at what price, without renting | @@ -62,7 +62,7 @@ The OpenAPI document also has volume endpoints. Volumes are not available yet. S ## Find an offer -An offer is one placement that you can rent. It names a provider, a region, a GPU model and count, the rest of the machine, a rental type, and a price. Each offer has a `workload`: `container`, `vm`, or `baremetal`. +An offer is one placement that you can rent. It names a region, a GPU model and count, the rest of the machine, a rental type, and a price. Each offer has a `workload`: `container`, `vm`, or `baremetal`. Choose the call that matches what you know: @@ -80,12 +80,12 @@ Choose the call that matches what you know: | `gpuVramGib`, `minGpuVramGib` | Memory of each GPU in GiB, exact or at least | | `gpuCount`, `minGpuCount` | GPUs per machine, exact or at least | | `minVcpu`, `minMemoryGib`, `minStorageGib` | Machine size, at least | -| `country`, `regionLabel`, `provider` | Location. `country` is a two-letter ISO code. `provider` takes several names separated by commas. | +| `country`, `regionLabel` | Location. `country` is a two-letter ISO code. | | `hostTier` | `dedicated`, `shared`, or `unknown` | | `cpuArchitecture` | `x86_64`, `arm64`, or `unknown` | | `maxPricePerHour` | The highest price per instance-hour in USD, as a decimal string, for example `0.50` | | `available` | `false` also lists offers without capacity left. Without credentials, only offers on sale are listed. | -| `q` | Text in the GPU vendor, GPU model, provider, or region label | +| `q` | Text in the GPU vendor, GPU model, or region label | To sort, set `sort` to `price`, `vram`, `vcpu`, `memory`, `storage`, or `availability`, and `order` to `asc` or `desc`. Without `sort`, the cheapest offers come first. @@ -99,7 +99,7 @@ curl "https://api.fluence.dev/v3/gpu/offers?workload=vm&rentalType=spot&minGpuVr Besides the hardware and the price, an offer has these fields: -- `offerKind`: `provider_sku` is an item of a provider catalog, and `host_offer` is one host. `market_profile` is an Akash offer that fixes the hardware profile and the highest bid, but not the host. Akash picks the host from bids when you create the instance. +- `offerKind`: `provider_sku` is an item of a provider catalog, and `host_offer` is one host. `market_profile` is an offer that fixes the hardware profile and the highest bid, but not the host. Bids choose the host when you create the instance. - `hostTier`: `dedicated`, `shared`, or `unknown`. - `region`, `dataCenter`, and `origin`: where the machine runs. - `topology`: GPU links, such as NVLink. @@ -156,7 +156,7 @@ Send `POST /v3/gpu/instances` with an `Idempotency-Key` header. The body has: - `gpu`: `vendor`, `model`, and `count`, as offers name them. - `offerId` to rent one exact offer, or `maxPricePerHour` to let the API choose the cheapest matching offer at or below this price. One of them is required. With `offerId`, the other requirements must still fit the offer. - `rentalType`: `on_demand` or `spot`. On-demand is the default. - - Optional limits, such as `minVcpu`, `minMemoryGib`, `minStorageGib`, `region`, `providers`, `hostTier`, and `cpuArchitecture`. + - Optional limits, such as `minVcpu`, `minMemoryGib`, `minStorageGib`, `region`, `hostTier`, and `cpuArchitecture`. - Exactly one of `container`, `vm`, or `baremetal`, matching the workload. For a container: @@ -216,7 +216,7 @@ An instance has the fields of its request, and these fields: - `status`: see [Instance statuses](../gpu_cloud/overview.md#instance-statuses). - `statusDetail`: why the instance is in its status. Some values: - - `awaiting_bids`: Akash collects bids for the instance. + - `awaiting_bids`: the instance waits for bids. - `provider_rate_limited`: the provider limits how often instances are created. The launch continues by itself, and nothing is billed before the instance runs. - `out_of_stock`: the provider had no capacity for the offer. Nothing is billed, and another offer can succeed. - `user_requested`: you deleted the instance. @@ -224,7 +224,7 @@ An instance has the fields of its request, and these fields: - `provider_terminated`: the provider ended the instance. - `isBilling`: `true` while the instance is billed. - `isTerminal`: `true` for `ended` and `failed`. -- `placement`: the offer that the instance runs on, with its provider, region, hardware, and capabilities. +- `placement`: the offer that the instance runs on, with its region, hardware, and capabilities. - `price`: the price fixed when the instance was created. - `charged`: the amount charged so far in `total`, as of `asOf`. - `actions`: what you can do with the instance now: `rename`, `delete`, `update`, `logs`, and `events`. @@ -239,7 +239,7 @@ An instance has the fields of its request, and these fields: - `live=true` lists only instances that are not ended or failed. `live=false` lists only ended and failed ones. - `status` takes one status or several, separated by commas. -- `workload`, `rentalType`, `provider`, `country`, and `createdVia` match those fields. +- `workload`, `rentalType`, `country`, and `createdVia` match those fields. - `q` matches text in the instance ID, name, or GPU model. To sort, set `sort` to `createdAt`, `name`, `status`, `pricePerHour`, or `activatedAt`. The newest instances come first by default. diff --git a/docs/build/gpu_cloud/overview.md b/docs/build/gpu_cloud/overview.md index e4785f5..6069dae 100644 --- a/docs/build/gpu_cloud/overview.md +++ b/docs/build/gpu_cloud/overview.md @@ -9,13 +9,13 @@ Fluence GPU Cloud rents GPUs from several providers in data centers around the w ## Offers -An offer is one machine configuration that you can rent: a provider, a region, a GPU model and count, vCPU, memory, local storage, and a price. Each offer is for one workload type and one rental type. Offers also show: +An offer is one machine configuration that you can rent: a region, a GPU model and count, vCPU, memory, local storage, and a price. Each offer is for one workload type and one rental type. Offers also show: - Availability. An offer that recently ran out of capacity can stay on sale. If a launch fails because the provider has no capacity, nothing is charged. - An estimate of how long provisioning takes. - What the instance supports, for example logs, events, container updates, and private registries. -Most offers are one machine type of a provider. Some Akash offers fix only the hardware and the highest price: Akash picks the host from provider bids when you launch the instance. +Most offers are one machine type of a provider. Some container offers fix only the hardware and the highest price. Bids choose the host when you launch the instance. Prices and availability change as providers change them.