Connect AI agents to Artificial Analysis

Scalekit connector

The Artificial Analysis connector lets your AI agent act in each user's Artificial Analysis account. Each user connects their own Artificial Analysis API key once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 6 tools.

Tools: 6
What they doRead · write · destructive: 6 · 0 · 06 read0 write0 destructive
Users sign in with: API key

Setup

Install the SDK
- Node.js
- Python
Terminal window
npm install @scalekit-sdk/node dotenv
Terminal window
pip install scalekit-sdk-python python-dotenv
Set your credentials
Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.
.env
```
SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
SCALEKIT_CLIENT_ID=<your-client-id>
SCALEKIT_CLIENT_SECRET=<your-client-secret>
```
Create the Artificial Analysis connection
In AgentKit > Connections, create an Artificial Analysis connection. The name you give it is the connection_name your code passes. See Configure connections.

Authorize a user and make your first call

Node.js
Python

1
import { ScalekitClient } from '@scalekit-sdk/node'
2
import 'dotenv/config'
3
import { createInterface } from 'node:readline/promises'
4

5
const scalekit = new ScalekitClient(
6
  process.env.SCALEKIT_ENVIRONMENT_URL,
7
  process.env.SCALEKIT_CLIENT_ID,
8
  process.env.SCALEKIT_CLIENT_SECRET,
9
)
10
const actions = scalekit.actions
11

12
const connector = 'artificialanalysis'
13
const identifier = 'user_123'
14

15
// Generate an authorization link for the user
16
const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
17
console.log('Authorize Artificial Analysis:', link)
18
const rl = createInterface({ input: process.stdin, output: process.stdout })
19
await rl.question('Press Enter after authorizing...')
20
rl.close()
21

22
// Make your first call
23
const result = await actions.executeTool({
24
  connector,
25
  identifier,
26
  toolName: 'artificialanalysis_get_image_editing_leaderboard',
27
  toolInput: {},
28
})
29
console.log(result)

npx tsx quickstart.mts

1
import os
2
from scalekit import ScalekitClient
3
from dotenv import load_dotenv
4
load_dotenv()
5

6
scalekit_client = ScalekitClient(
7
    env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
8
    client_id=os.getenv("SCALEKIT_CLIENT_ID"),
9
    client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
10
)
11
actions = scalekit_client.actions
12

13
connection_name = "artificialanalysis"
14
identifier = "user_123"
15

16
# Generate an authorization link for the user
17
link_response = actions.get_authorization_link(
18
    connection_name=connection_name,
19
    identifier=identifier,
20
)
21
print("Authorize Artificial Analysis:", link_response.link)
22
input("Press Enter after authorizing...")
23

24
# Make your first call
25
result = actions.execute_tool(
26
    tool_input={},
27
    tool_name="artificialanalysis_get_image_editing_leaderboard",
28
    connection_name=connection_name,
29
    identifier=identifier,
30
)
31
print(result)

python quickstart.py

Each user opens the link once and enters their Artificial Analysis credentials there. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool

Try in Playground Request a tool

artificialanalysis_get_image_editing_leaderboardGet the Artificial Analysis image editing leaderboard: Elo ratings for models that edit an existing image from an instruction, from the Artificial Analysis arena.Read-only
Get Image Editing Leaderboard
Get the Artificial Analysis image editing leaderboard: Elo ratings for models that edit an existing image from an instruction, from the Artificial Analysis arena. Returns ranked models with id, name, slug, creator, Elo, rank, 95% confidence interval, arena appearances and release date. Only current models with at least 500 arena appearances are listed. Use this to compare image editing models. Use artificialanalysis_get_text_to_image_leaderboard for models that generate new images from a text prompt.
Inputs
This tool takes no inputs.
artificialanalysis_get_image_to_video_leaderboardGet the Artificial Analysis image-to-video leaderboard: Elo ratings for models that turn a starting image into a video, from the Artificial Analysis arena.Read-only
Get Image-to-Video Leaderboard
Get the Artificial Analysis image-to-video leaderboard: Elo ratings for models that turn a starting image into a video, from the Artificial Analysis arena. Returns ranked models with id, name, slug, creator, Elo, rank, 95% confidence interval, arena appearances and release date. With include_categories=true, each model also has Elo broken down by style, subject-matter and format category. Only current models with at least 1,000 arena appearances are listed. Use this to compare image animation models. Use artificialanalysis_get_text_to_video_leaderboard for models that generate video from a text prompt alone.
Inputs
include_categoriesboolean
Set to true to add a categories list to each model, giving its Elo, 95% confidence interval and arena appearances for each combination of style, subject-matter and format category (for example Photorealistic, Nature, Moving camera). False or omitted returns overall ratings only. Example: true
artificialanalysis_get_text_to_image_leaderboardGet the Artificial Analysis text-to-image leaderboard: Elo ratings for models that generate images from a text prompt, from the Artificial Analysis arena.Read-only
Get Text-to-Image Leaderboard
Get the Artificial Analysis text-to-image leaderboard: Elo ratings for models that generate images from a text prompt, from the Artificial Analysis arena. Returns ranked models with id, name, slug, creator, Elo, rank, 95% confidence interval, arena appearances and release date. With include_categories=true, each model also has Elo broken down by style and subject-matter category. Only current models with at least 500 arena appearances are listed. Use this to compare image generation models. Use artificialanalysis_get_image_editing_leaderboard for models that edit an existing image, and artificialanalysis_list_llm_models for language models.
Inputs
include_categoriesboolean
Set to true to add a categories list to each model, giving its Elo, 95% confidence interval and arena appearances for each style and subject-matter category (for example General & Photorealistic, People: Portraits). False or omitted returns overall ratings only. Example: true
artificialanalysis_get_text_to_speech_leaderboardGet the Artificial Analysis text-to-speech leaderboard: Elo ratings for models that turn text into spoken audio.Read-only
Get Text-to-Speech Leaderboard
Get the Artificial Analysis text-to-speech leaderboard: Elo ratings for models that turn text into spoken audio. Returns the text-to-speech models with their Elo ratings. Use this to compare speech generation models. Use artificialanalysis_get_text_to_video_leaderboard for video models and artificialanalysis_list_llm_models for language models.
Inputs
This tool takes no inputs.
artificialanalysis_get_text_to_video_leaderboardGet the Artificial Analysis text-to-video leaderboard: Elo ratings for models that generate video from a text prompt, from the Artificial Analysis arena.Read-only
Get Text-to-Video Leaderboard
Get the Artificial Analysis text-to-video leaderboard: Elo ratings for models that generate video from a text prompt, from the Artificial Analysis arena. Returns ranked models with id, name, slug, creator, Elo, rank, 95% confidence interval, arena appearances and release date. With include_categories=true, each model also has Elo broken down by style, subject-matter and format category. Only current models with at least 1,000 arena appearances are listed. Use this to compare video generation from text. Use artificialanalysis_get_image_to_video_leaderboard for models that animate a starting image.
Inputs
include_categoriesboolean
Set to true to add a categories list to each model, giving its Elo, 95% confidence interval and arena appearances for each combination of style, subject-matter and format category (for example Photorealistic, People, Moving camera). False or omitted returns overall ratings only. Example: true
artificialanalysis_list_llm_modelsList the large language models that Artificial Analysis benchmarks, with their intelligence scores, token prices and speed.Read-only
List LLM Models
List the large language models that Artificial Analysis benchmarks, with their intelligence scores, token prices and speed. Returns each model's stable id, name, slug and creator (id, name, slug); its evaluation scores, including the Artificial Analysis Intelligence, Coding and Math indexes and benchmarks such as MMLU-Pro, GPQA, HLE, LiveCodeBench, SciCode, MATH-500 and AIME; price per million input, output and blended (3:1) tokens in USD; median output tokens per second; and median time to first token in seconds. Speed and latency are measured with a medium (about 1k input token) prompt. Use this to compare or choose language models. Use the media leaderboard tools, such as artificialanalysis_get_text_to_image_leaderboard, for image, speech and video models.
Inputs
This tool takes no inputs.

Setup

Install the SDK

Set your credentials

Create the Artificial Analysis connection

Authorize a user and make your first call

Tools

Call it

Returns

Get Image Editing Leaderboard

Inputs

Get Image-to-Video Leaderboard

Inputs

Get Text-to-Image Leaderboard

Inputs

Get Text-to-Speech Leaderboard

Inputs

Get Text-to-Video Leaderboard

Inputs

List LLM Models

Inputs

Related: other AI connectors