Datasets - Python SDK

Overview

Datasets endpoints

Available Operations

• get_app_rankings - Top apps by token usage
• get_rankings_daily - Daily token totals for top 50 models

get_app_rankings

Returns the top public apps on OpenRouter ranked by token usage inside the requested date window, matching the public apps marketplace on openrouter.ai/apps. Token totals are prompt_tokens + completion_tokens; hidden and private apps are excluded and traffic from related app aliases is merged into the canonical visible app.

sort=popular (default) ranks by total token volume inside the window. sort=trending ranks by absolute excess token growth: window volume minus the average volume of the three equal-length periods immediately preceding the window. Apps with no excess growth are omitted, so trending may return fewer than limit rows.

Filter with category (marketplace category group, e.g. coding) or subcategory (e.g. cli-agent). Ranks are re-numbered 1..N after filtering. Page with offset — rank stays absolute, so the first row of offset=50 is rank: 51.

Authenticate with any valid OpenRouter API key (same key used for inference). Rate-limited to 30 requests/minute per key and 500 requests/day per account.

When republishing or quoting this dataset, OpenRouter must be cited as: “Source: OpenRouter (openrouter.ai/apps), as of {as_of}.”

Token counts come from each upstream provider’s own tokenizer, so a token attributed to one app is not directly comparable to a token attributed to another app whose traffic flows through a different provider.

Example Usage

1
from openrouter import OpenRouter
2
import os
3
4
with OpenRouter(
5
    http_referer="<value>",
6
    x_open_router_title="<value>",
7
    x_open_router_categories="<value>",
8
    api_key=os.getenv("OPENROUTER_API_KEY", ""),
9
) as open_router:
10
11
    res = open_router.datasets.get_app_rankings(sort="popular", limit=50, offset=0)
12
13
    while res is not None:
14
        # Handle items
15
16
        res = res.next()

Parameters

Response

operations.GetAppRankingsResponse

Errors

get_rankings_daily

Returns the top 50 public models per day by total token usage on OpenRouter, plus a single aggregated other row per day that sums every model outside that top 50. Token totals are prompt_tokens + completion_tokens, matching the public rankings chart on openrouter.ai/rankings.

Each row is a distinct (date, model_permaslug) pair. The other row uses the reserved permaslug other and is always returned last within its date, so callers can compute top-50 traffic / total daily traffic without a second request.

Authenticate with any valid OpenRouter API key (same key used for inference). Rate-limited to 30 requests/minute per key and 500 requests/day per account.

When republishing or quoting this dataset, OpenRouter must be cited as: “Source: OpenRouter (openrouter.ai/rankings), as of {as_of}.”

Token counts come from each upstream provider’s own tokenizer (Anthropic counts are as reported by Anthropic, OpenAI counts are as reported by OpenAI, etc.), so a token in one row is not directly comparable to a token in another row from a different provider.

Example Usage

1
from openrouter import OpenRouter
2
import os
3
4
with OpenRouter(
5
    http_referer="<value>",
6
    x_open_router_title="<value>",
7
    x_open_router_categories="<value>",
8
    api_key=os.getenv("OPENROUTER_API_KEY", ""),
9
) as open_router:
10
11
    res = open_router.datasets.get_rankings_daily()
12
13
    # Handle response
14
    print(res)

Parameters

Response

components.RankingsDailyResponse

Errors