---
title: "List inference flavors"
method: GET
path: "/cloud/v3/inference/flavors"
tags: ["Everywhere Inference"]
---

# List inference flavors

`GET /cloud/v3/inference/flavors`

## Query parameters

- `limit` integer — Optional. Limit the number of returned items
- `offset` integer — Optional. Offset value is used to exclude the first set of records from the result

## Response `200`

OK

- InferenceFlavorOutSerializerV3List
  - `count` integer, required — Number of objects
  - `results` InferenceFlavorOutSerializerV3[], required — Objects
    - `cpu` number, required — Inference flavor cpu count.
    - `description` string, required — Inference flavor description.
    - `gpu` integer, required — Inference flavor gpu count.
    - `gpu_compute_capability` string, required — Inference flavor gpu compute capability.
    - `gpu_memory` number, required — Inference flavor gpu memory in Gi.
    - `gpu_model` string, required — Inference flavor gpu model.
    - `is_gpu_shared` boolean, required — Inference flavor is gpu shared.
    - `memory` number, required — Inference flavor memory in Gi.
    - `name` string, required — Inference flavor name.

---

[API](https://skmtc.dev/g-core/apis/gcore-openapi.md) · [All operations](https://skmtc.dev/g-core/apis/gcore-openapi/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/g-core/gcore-openapi/revisions/09e652815095/schema)