Usage

Get usage details for the team.

curl --request GET \
  --url https://api.friendli.ai/v1/team/usage \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.friendli.ai/v1/team/usage"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.friendli.ai/v1/team/usage', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.friendli.ai/v1/team/usage"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "has_more": false,
  "data": [
    {
      "start_time": "2023-11-07T00:00:00Z",
      "end_time": "2023-11-08T00:00:00Z",
      "results": [
        {
          "num_model_requests": 1200,
          "input_tokens": 180000,
          "input_cached_tokens": 45000,
          "output_tokens": 62000,
          "product_type": "model_apis",
          "model": "zai-org/GLM-5.2",
          "user_id": "user_id_123",
          "processed_audio_length_ms": 0
        }
      ]
    },
    {
      "start_time": "2023-11-08T00:00:00Z",
      "end_time": "2023-11-09T00:00:00Z",
      "results": [
        {
          "num_model_requests": 800,
          "input_tokens": 120000,
          "input_cached_tokens": 30000,
          "output_tokens": 41000,
          "product_type": "dedicated_endpoints",
          "model": "dedicated-endpoint-01",
          "user_id": "user_id_456",
          "gpu_usage": {
            "a100": 120000,
            "h100": 80000
          },
          "processed_audio_length_ms": 0
        }
      ]
    }
  ]
}

GET

team

usage

Get usage details for the team.

curl --request GET \
  --url https://api.friendli.ai/v1/team/usage \
  --header 'Authorization: Bearer <token>'

import requests

url = "https://api.friendli.ai/v1/team/usage"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://api.friendli.ai/v1/team/usage', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.friendli.ai/v1/team/usage"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

{
  "has_more": false,
  "data": [
    {
      "start_time": "2023-11-07T00:00:00Z",
      "end_time": "2023-11-08T00:00:00Z",
      "results": [
        {
          "num_model_requests": 1200,
          "input_tokens": 180000,
          "input_cached_tokens": 45000,
          "output_tokens": 62000,
          "product_type": "model_apis",
          "model": "zai-org/GLM-5.2",
          "user_id": "user_id_123",
          "processed_audio_length_ms": 0
        }
      ]
    },
    {
      "start_time": "2023-11-08T00:00:00Z",
      "end_time": "2023-11-09T00:00:00Z",
      "results": [
        {
          "num_model_requests": 800,
          "input_tokens": 120000,
          "input_cached_tokens": 30000,
          "output_tokens": 41000,
          "product_type": "dedicated_endpoints",
          "model": "dedicated-endpoint-01",
          "user_id": "user_id_456",
          "gpu_usage": {
            "a100": 120000,
            "h100": 80000
          },
          "processed_audio_length_ms": 0
        }
      ]
    }
  ]
}

Get usage details for the team. If X-Friendli-Team is omitted, this endpoint uses the default team configured in Friendli Suite. To request successfully, it is mandatory to enter a Personal API Key (e.g. flp_XXX) value in the Bearer Token field. Refer to the authentication section on our introduction page to learn how to acquire this variable and visit here to generate your API Key.

Authorizations

Authorization

string

header

required

When using Friendli Suite API for inference requests, you need to provide a Friendli Token for authentication and authorization purposes.

For more detailed information, please refer here.

Headers

X-Friendli-Team

string | null

ID of team to run requests as (optional parameter).

Query Parameters

start_time

string<date-time>

required

RFC 3339 timestamp in UTC. Must fall on a 5-minute boundary (e.g., 2026-01-01T10:05:00Z). It must be no earlier than one year ago. When bucket_width=1h, it must align to an hour boundary (e.g., 10:00:00Z); when bucket_width=1d, it must align to a day boundary (e.g., 00:00:00Z).

end_time

string<date-time>

required

RFC 3339 timestamp in UTC. Must fall on a 5-minute boundary (e.g., 2026-01-01T10:05:00Z), and its minute value must match start_time's. It must obey the same hour/day alignment as start_time when bucket_width=1h or 1d.

bucket_width

enum<string> | null

default:1d

Width of each time bucket in response. Currently 1d, 1h, and 5m are supported, default to 1d.

Available options:

1d,

1h,

5m

limit

integer | null

Specifies the number of buckets to return.

bucket_width=1d: default limit = 7, max limit = 31
bucket_width=1h: default limit = 24, max limit = 168
bucket_width=5m: default limit = 12, max limit = 288

page

string | null

A cursor for use in pagination. Corresponding to the next_page field from the previous response.

group_by

enum<string>[] | null

Group the usage by the specified fields. Support fields include model, product_type, user_id and any combination of them.

Available options:

model,

product_type,

user_id

models

string[] | null

Return only usage for the listed Model APIs and Dedicated Endpoints. Values are model IDs, endpoint IDs, or a mix.

user_ids

string[] | null

Return only usage for these users.

product_types

enum<string>[] | null

Return only usage for the specified product types. Supported fields include model_apis, dedicated_endpoints and any combination of them.

Available options:

model_apis,

dedicated_endpoints

gpu_types

string[] | null

Return only usage for the specified GPU types. When this filter is given, only 'gpu_usage' will be provided. Combining gpu_types with 'product_types=model_apis` is rejected with HTTP 400.

Response

Team usage response

has_more

boolean

required

data

UsageBucket · object[]

required

Hide child attributes

data.start_time

string<date-time>

required

data.end_time

string<date-time>

required

data.results

UsageResult · object[]

required

Hide child attributes

data.results.product_type

enum<string> | null

When group_by=product_type, this field provides the product type of the grouped usage result. Supported values are model_apis and dedicated_endpoints.

Available options:

model_apis,

dedicated_endpoints

Example:

"model_apis"

data.results.model

string | null

When group_by=model, this field provides the model ID of the grouped usage result. For Model APIs usage, this is the model ID. For Dedicated Endpoints usage, this is the endpoint ID.

Example:

"zai-org/GLM-5.2"

data.results.user_id

string | null

When group_by=user_id, this field provides the user ID of the grouped usage result.

Example:

"user_id_123"

data.results.num_model_requests

integer | null

default:0

The count of requests made.

Example:

1200

data.results.input_tokens

integer | null

default:0

The aggregated number of input tokens used, including cached tokens.

Example:

180000

data.results.input_cached_tokens

integer | null

default:0

The aggregated number of input tokens that has been cached.

Example:

45000

data.results.output_tokens

integer | null

default:0

The aggregated number of text output tokens used.

Example:

62000

data.results.gpu_usage

Gpu Usage · object | null

The GPU time in seconds, keyed by GPU type. When group_by=user_id, this is attributed to the bucket of the user who created the endpoint. When the gpu_types filter is set, only Dedicated Endpoints usage is returned, and only GPU time is provided — per-GPU-type token usage is not yet supported.

Hide child attributes

data.results.gpu_usage.{key}

integer

Example:

{ "a100": 120000, "h100": 80000 }

data.results.processed_audio_length_ms

integer | null

default:0

The number of processed audio length in milliseconds. Zero when there is no audio usage.

Example:

300000

next_page

string | null

Last modified on July 22, 2026

Cost

Dataset Overview

⌘I

API Reference

Model APIs

Dedicated

Container

Administration

Dataset and File

Friendli SDK

Usage

Authorizations

Headers

Query Parameters

Response