---
title: "Task classification market share"
method: GET
path: "/classifications/task"
tags: ["Classifications"]
---

# Task classification market share

`GET /classifications/task`

Returns the market-share breakdown of OpenRouter traffic by task classification
(e.g. code generation, web search, summarization) over a trailing time window.

Each classification reports its share of classified sampled requests (`usage_share`)
and classified sampled token volume (`token_share`) as fractions between 0 and 1.
The unclassified `other` bucket is excluded. Absolute volumes are not exposed
because the underlying data is sampled.

Each classification also includes a `models` array listing the top models by
request volume within that classification, with their within-tag usage and token shares.

Classifications are grouped into macro-categories (Code, Data, Agent, General)
with aggregate shares provided for each.

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 data, cite as:
"Source: OpenRouter (openrouter.ai/rankings), as of {as_of}."

## Query parameters

- `window` '7d' — Trailing time window for the classification data. Currently only `7d` (trailing 7 days) is supported.

## Response `200`

Task classification market-share data for the requested trailing window.

- TaskClassificationResponse
  - `data` object, required
    - `as_of` string, required — UTC date (YYYY-MM-DD) of the window upper bound (yesterday). Data is exclusive of the current incomplete UTC day. This is the expected latest date in the snapshot; it does not confirm data presence for that date.
    - `classifications` TaskClassificationItem[], required — Per-task classification market-share data, sorted by usage_share descending.
      - `category_token_share` number, double, required — Fraction of this classification's token volume within its macro-category (0–1). Sums to 1 across all classifications sharing the same `macro_category`.
      - `category_usage_share` number, double, required — Fraction of this classification's usage within its macro-category (0–1). Sums to 1 across all classifications sharing the same `macro_category`.
      - `display_name` string, required — Human-readable label for the classification.
      - `macro_category` string, required — Coarse grouping derived from the tag prefix: `code`, `data`, `agent`, or `general`.
      - `models` TaskClassificationModel[], required — Top models for this classification by request volume, sorted descending. Each entry reports the model's share of this classification's requests and tokens.
        - `id` string, required — Model identifier (permaslug).
        - `tag_token_share` number, double, required — Fraction of this classification's sampled token volume attributed to this model (0–1). Sums to ≤1 across the returned models (only top-N are included and unattributed requests are excluded).
        - `tag_usage_share` number, double, required — Fraction of this classification's sampled requests attributed to this model (0–1). Sums to ≤1 across the returned models (only top-N are included and unattributed requests are excluded).
      - `tag` string, required — Classification tag identifier (e.g. `code:general_impl`, `agent:web_search`).
      - `token_share` number, double, required — Fraction of classified sampled token volume (prompt + completion) attributed to this classification (0–1). The unclassified `other` bucket is excluded from the denominator.
      - `usage_share` number, double, required — Fraction of classified sampled requests attributed to this classification (0–1). The unclassified `other` bucket is excluded from the denominator.
    - `macro_categories` TaskClassificationMacroCategory[], required — Aggregate market-share data per macro-category (code, data, agent, general).
      - `key` string, required — Macro-category identifier.
      - `label` string, required — Human-readable label for the macro-category.
      - `token_share` number, double, required — Combined token share of all classifications in this macro-category (0–1).
      - `usage_share` number, double, required — Combined usage share of all classifications in this macro-category (0–1).
    - `window_days` integer, required — Number of trailing days covered by this snapshot.

## Other responses

- `400` — Bad Request - Invalid request parameters or malformed input
- `401` — Unauthorized - Authentication required or invalid credentials
- `429` — Too Many Requests - Rate limit exceeded
- `500` — Internal Server Error - Unexpected server error

---

[API](https://skmtc.net/openrouterteam/apis/openrouter-api.md) · [All operations](https://skmtc.net/openrouterteam/apis/openrouter-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/openrouterteam/openrouter-api/versions/4836d63be710/schema)