Benchmarks - OpenRouter | Documentation

Overview

Benchmarks endpoints

Available Operations

get_benchmarks - List Benchmarks

get_benchmarks

Unified benchmark endpoint that aggregates scores from multiple benchmark sources (Artificial Analysis, Design Arena). Filter by source to reproduce the exact shapes from the legacy per-source endpoints, or use task_type to find models suited for specific workloads. Authenticate with any valid OpenRouter API key. Rate-limited to 30 requests/minute per key and 500 requests/day per account.

Example Usage

from openrouter import OpenRouter
import os


with OpenRouter(
    http_referer="<value>",
    x_open_router_title="<value>",
    x_open_router_categories="<value>",
    api_key=os.getenv("OPENROUTER_API_KEY", ""),
) as open_router:

    res = open_router.benchmarks.get_benchmarks()

    # Handle response
    print(res)

Parameters

Parameter	Type	Required	Description	Example
`http_referer`	Optional[str]	:heavy_minus_sign:	The app identifier should be your app’s URL and is used as the primary identifier for rankings. This is used to track API usage per application.
`x_open_router_title`	Optional[str]	:heavy_minus_sign:	The app display name allows you to customize how your app appears in OpenRouter’s dashboard.
`x_open_router_categories`	Optional[str]	:heavy_minus_sign:	Comma-separated list of app categories (e.g. “cli-agent,cloud-agent”). Used for marketplace rankings.
`source`	Optional[operations.Source]	:heavy_minus_sign:	Benchmark source to query. Determines the shape of the returned items. When omitted, returns results from all sources.	artificial-analysis
`task_type`	Optional[operations.TaskType]	:heavy_minus_sign:	Filter results by task type. For Artificial Analysis, maps to the corresponding index. For Design Arena, maps to the matching category.	coding
`arena`	Optional[operations.Arena]	:heavy_minus_sign:	Design Arena only: arena to query. Defaults to `models` when source is `design-arena`.	models
`category`	Optional[str]	:heavy_minus_sign:	Design Arena only: category within the arena (e.g. `codecategories`, `uicomponent`, `gamedev`, `3d`, `dataviz`, `image`, `video`, `svg`). When omitted, returns all categories.	codecategories
`max_results`	Optional[int]	:heavy_minus_sign:	Maximum number of items to return. When omitted, all matching results are returned.	50
`retries`	Optional[utils.RetryConfig]	:heavy_minus_sign:	Configuration to override the default retry behavior of the client.

Response

components.UnifiedBenchmarksResponse

Errors

Error Type	Status Code	Content Type
errors.BadRequestResponseError	400	application/json
errors.UnauthorizedResponseError	401	application/json
errors.TooManyRequestsResponseError	429	application/json
errors.InternalServerResponseError	500	application/json
errors.OpenRouterDefaultError	4XX, 5XX	/

​Overview

​Available Operations

​get_benchmarks

​Example Usage

​Parameters

​Response

​Errors