Artificial Analysis API Documentation (Free API)

Overview & Access

Artificial Analysis provides a free API to support analysis of AI models and in making informed decisions about which AI models to use.
We offer a free API focused on model benchmarks and a commercial API with more comprehensive data. Commercial API documentation is available to partners separately.

To access our free API, create an account for the Artificial Analysis Insights Platform and generate an API key.

When integrating with our API, we recommend using model and creator IDs as primary identifiers since they remain stable, while slugs and names may change over time.

Attribution & Sharing of Data

Attribution is required for all use of our free API. Please provide attribution to https://artificialanalysis.ai/.

If you wish to include our logo in your materials, you can download our brand kit here: Artificial Analysis Brand Kit.

Methodology

For details on how benchmarks are conducted, see our methodology.

Authentication

Include your API key in the x-api-key header.

To obtain an API key, create an account in the Artificial Analysis Insights Platform and generate an API key.

401 Invalid/missing API key

429 Rate limit exceeded

500 Internal server error

Free Artificial Analysis Data API

Our free API is focused on sharing primary metrics from our independent benchmarks of models. This includes our independent intelligence evaluations, speed benchmarks and pricing.

The API is rate-limited to 1,000 requests per day. To avoid publicly sharing keys and rate limits, please do not include in client side code and cache responses.

LLMs Endpoint

get/data/llms/models

Response Fields

Field	Type	Description
`id`	string	Unique identifier (stable)
`name`	string	Full name (may change)
`slug`	string	URL-friendly identifier (infrequently changed)
`model_creator`	object	Creator information (id, name, slug)
`evaluations`	object	Benchmark scores
`pricing`	object	Price per million tokens ($USD)
`median_output_tokens_per_second`	number	Output generation speed (tokens per second)
`median_time_to_first_token_seconds`	number	Time to first token (seconds)

Example Request

curl -X GET https://artificialanalysis.ai/api/v2/data/llms/models \
          -H "x-api-key: your_api_key_here"

Example Response

{
  "status": 200,
  "prompt_options": {
    "parallel_queries": 1,
    "prompt_length": "medium"
  },
  "data": [
    {
      "id": "2dad8957-4c16-4e74-bf2d-8b21514e0ae9",
      "name": "o3-mini",
      "slug": "o3-mini",
      "model_creator": {
        "id": "e67e56e3-15cd-43db-b679-da4660a69f41",
        "name": "OpenAI",
        "slug": "openai"
      },
      "evaluations": {
        "artificial_analysis_intelligence_index": 62.9,
        "artificial_analysis_coding_index": 55.8,
        "artificial_analysis_math_index": 87.2,
        "mmlu_pro": 0.791,
        "gpqa": 0.748,
        "hle": 0.087,
        "livecodebench": 0.717,
        "scicode": 0.399,
        "math_500": 0.973,
        "aime": 0.77
      },
      "pricing": {
        "price_1m_blended_3_to_1": 1.925,
        "price_1m_input_tokens": 1.1,
        "price_1m_output_tokens": 4.4
      },
      "median_output_tokens_per_second": 153.831,
      "median_time_to_first_token_seconds": 14.939,
      "median_time_to_first_answer_token": 14.939
    },
    // Other models...
  ]
}

Text-to-Image Endpoint

get/data/media/text-to-image

This endpoint returns ELO ratings for text-to-image models.

You can optionally include the include_categories=true parameter to get a breakdown of ELO scores by category.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-image" \
          -H "x-api-key: your_api_key_here"

Example Response

{
  "status": 200,
  "include_categories": true,
  "data": [
    {
      "id": "dall-e-3",
      "name": "DALL·E 3",
      "slug": "dall-e-3",
      "model_creator": {
        "id": "openai",
        "name": "OpenAI"
      },
      "elo": 1250,
      "rank": 1,
      "ci95": "-5/+5",
      "categories": [
        {
          "style_category": "people",
          "subject_matter_category": "portraits",
          "elo": 1280,
          "ci95": "-5/+5"
        }
      ]
    }
  ]
}

Image Editing Endpoint

get/data/media/image-editing

This endpoint returns ELO ratings for image editing models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/image-editing" \
          -H "x-api-key: your_api_key_here"

Text-to-Speech Endpoint

get/data/media/text-to-speech

This endpoint returns ELO ratings for text-to-speech models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-speech" \
          -H "x-api-key: your_api_key_here"

Text-to-Video Endpoint

get/data/media/text-to-video

This endpoint returns ELO ratings for text-to-video models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-video" \
          -H "x-api-key: your_api_key_here"

Image-to-Video Endpoint

get/data/media/image-to-video

This endpoint returns ELO ratings for image-to-video models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/image-to-video" \
          -H "x-api-key: your_api_key_here"

CritPt Benchmark Evaluation API

This API provides the official gateway for evaluating code generation submissions against the CritPt benchmark private evaluation set.

Authentication & Rate Limiting

Authentication: An Artificial Analysis API key is required in the x-api-key header
Rate Limiting: Default limit of 10 requests per 24-hour window (custom limits available upon request)
Rate Limit Headers: Responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers

Attribution

When using this API or the broader CritPt evaluation, please provide appropriate attribution to the CritPt project.

Batch Evaluation Endpoint

post/api/v2/critpt/evaluate

Submit a batch of code generation submissions for evaluation against CritPt benchmark problems.

Note: Requests may take substantial time to complete as they are processed by the evaluation system.

Request Body

Field	Type	Required	Description
`submissions`	array	Yes	Array of submission objects (see below) - must include all problems in the public set to be processed
`batch_metadata`	object	Yes	Metadata object for the batch (any additional properties allowed)

Submission Object Fields

Field	Type	Required	Description
`problem_id`	string	Yes	Unique identifier for the CritPt problem
`generated_code`	string	Yes	The code generated by the model
`model`	string	Yes	Name/identifier of the model used
`generation_config`	object	Yes	Configuration used for code generation (any properties allowed)
`messages`	array	No	Optional array of message objects

Response Fields (Success)

Field	Type	Description
`accuracy`	number	Average accuracy from 0-1 across submissions
`timeout_rate`	number	Share of submission grading processes that timed out in the upstream grading server
`server_timeout_count`	number	Number of submission grading processes that timed out in the upstream grading server

Rate Limit Headers

All successful responses include the following headers:

X-RateLimit-Limit: Maximum requests allowed in the time window
X-RateLimit-Remaining: Number of requests remaining in current window
X-RateLimit-Reset: Human-readable date string when the rate limit window resets

Error Responses

400 Invalid request body

401 Invalid/missing API key

429 Rate limit exceeded

502 Invalid response from evaluation system

504 Evaluation timeout

429 Rate Limit Exceeded Response

{
  "error": "Rate limit exceeded",
  "limit": 10,
  "remaining": 0,
  "reset": "Wed Jan 01 2025 00:00:00 GMT+0000 (Coordinated Universal Time)",
  "retryAfter": 3600
}

The response also includes Retry-After header with seconds to wait.

Example Request (truncated)

curl -X POST https://artificialanalysis.ai/api/v2/critpt/evaluate \
  -H "Content-Type: application/json" \
  -H "x-api-key: your_api_key_here" \
  -d '{
    "submissions": [
      {
        "problem_id": "Challenge_1_main",
        "generated_code": "```python\ndef solution():\n    return 42\n```",
        "model": "gpt-5",
        "generation_config": {
          "use_golden_for_prev_steps": false,
          "parsing": false,
          "multiturn_with_answer": false,
          "use_python": false,
          "use_web_search": false
        }
      },
      # Submission for *all* problems in the public set are required in each grading request
      ...
    ],
    "batch_metadata": {}
  }'

Example Response

{
  "accuracy": 0.0,
  "timeout_rate": 0.0,
  "server_timeout_count": 0
}

Artificial Analysis

For Enterprise Insights

Artificial Analysis API Documentation (Free API)

Overview & Access

To access our free API, create an account for the Artificial Analysis Insights Platform and generate an API key.

When integrating with our API, we recommend using model and creator IDs as primary identifiers since they remain stable, while slugs and names may change over time.

Attribution & Sharing of Data

Attribution is required for all use of our free API. Please provide attribution to https://artificialanalysis.ai/.

If you wish to include our logo in your materials, you can download our brand kit here: Artificial Analysis Brand Kit.

Methodology

For details on how benchmarks are conducted, see our methodology.

Authentication

Include your API key in the x-api-key header.

To obtain an API key, create an account in the Artificial Analysis Insights Platform and generate an API key.

401 Invalid/missing API key

429 Rate limit exceeded

500 Internal server error

Free Artificial Analysis Data API

Our free API is focused on sharing primary metrics from our independent benchmarks of models. This includes our independent intelligence evaluations, speed benchmarks and pricing.

The API is rate-limited to 1,000 requests per day. To avoid publicly sharing keys and rate limits, please do not include in client side code and cache responses.

LLMs Endpoint

get/data/llms/models

Response Fields

Field	Type	Description
`id`	string	Unique identifier (stable)
`name`	string	Full name (may change)
`slug`	string	URL-friendly identifier (infrequently changed)
`model_creator`	object	Creator information (id, name, slug)
`evaluations`	object	Benchmark scores
`pricing`	object	Price per million tokens ($USD)
`median_output_tokens_per_second`	number	Output generation speed (tokens per second)
`median_time_to_first_token_seconds`	number	Time to first token (seconds)

Example Request

curl -X GET https://artificialanalysis.ai/api/v2/data/llms/models \
          -H "x-api-key: your_api_key_here"

Example Response

{
  "status": 200,
  "prompt_options": {
    "parallel_queries": 1,
    "prompt_length": "medium"
  },
  "data": [
    {
      "id": "2dad8957-4c16-4e74-bf2d-8b21514e0ae9",
      "name": "o3-mini",
      "slug": "o3-mini",
      "model_creator": {
        "id": "e67e56e3-15cd-43db-b679-da4660a69f41",
        "name": "OpenAI",
        "slug": "openai"
      },
      "evaluations": {
        "artificial_analysis_intelligence_index": 62.9,
        "artificial_analysis_coding_index": 55.8,
        "artificial_analysis_math_index": 87.2,
        "mmlu_pro": 0.791,
        "gpqa": 0.748,
        "hle": 0.087,
        "livecodebench": 0.717,
        "scicode": 0.399,
        "math_500": 0.973,
        "aime": 0.77
      },
      "pricing": {
        "price_1m_blended_3_to_1": 1.925,
        "price_1m_input_tokens": 1.1,
        "price_1m_output_tokens": 4.4
      },
      "median_output_tokens_per_second": 153.831,
      "median_time_to_first_token_seconds": 14.939,
      "median_time_to_first_answer_token": 14.939
    },
    // Other models...
  ]
}

Text-to-Image Endpoint

get/data/media/text-to-image

This endpoint returns ELO ratings for text-to-image models.

You can optionally include the include_categories=true parameter to get a breakdown of ELO scores by category.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-image" \
          -H "x-api-key: your_api_key_here"

Example Response

{
  "status": 200,
  "include_categories": true,
  "data": [
    {
      "id": "dall-e-3",
      "name": "DALL·E 3",
      "slug": "dall-e-3",
      "model_creator": {
        "id": "openai",
        "name": "OpenAI"
      },
      "elo": 1250,
      "rank": 1,
      "ci95": "-5/+5",
      "categories": [
        {
          "style_category": "people",
          "subject_matter_category": "portraits",
          "elo": 1280,
          "ci95": "-5/+5"
        }
      ]
    }
  ]
}

Image Editing Endpoint

get/data/media/image-editing

This endpoint returns ELO ratings for image editing models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/image-editing" \
          -H "x-api-key: your_api_key_here"

Text-to-Speech Endpoint

get/data/media/text-to-speech

This endpoint returns ELO ratings for text-to-speech models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-speech" \
          -H "x-api-key: your_api_key_here"

Text-to-Video Endpoint

get/data/media/text-to-video

This endpoint returns ELO ratings for text-to-video models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/text-to-video" \
          -H "x-api-key: your_api_key_here"

Image-to-Video Endpoint

get/data/media/image-to-video

This endpoint returns ELO ratings for image-to-video models.

Example Request

curl -X GET "https://artificialanalysis.ai/api/v2/data/media/image-to-video" \
          -H "x-api-key: your_api_key_here"

CritPt Benchmark Evaluation API

This API provides the official gateway for evaluating code generation submissions against the CritPt benchmark private evaluation set.

Authentication & Rate Limiting

Authentication: An Artificial Analysis API key is required in the x-api-key header
Rate Limiting: Default limit of 10 requests per 24-hour window (custom limits available upon request)
Rate Limit Headers: Responses include X-RateLimit-Limit, X-RateLimit-Remaining, and X-RateLimit-Reset headers

Attribution

When using this API or the broader CritPt evaluation, please provide appropriate attribution to the CritPt project.

Batch Evaluation Endpoint

post/api/v2/critpt/evaluate

Submit a batch of code generation submissions for evaluation against CritPt benchmark problems.

Note: Requests may take substantial time to complete as they are processed by the evaluation system.

Request Body

Field	Type	Required	Description
`submissions`	array	Yes	Array of submission objects (see below) - must include all problems in the public set to be processed
`batch_metadata`	object	Yes	Metadata object for the batch (any additional properties allowed)

Submission Object Fields

Field	Type	Required	Description
`problem_id`	string	Yes	Unique identifier for the CritPt problem
`generated_code`	string	Yes	The code generated by the model
`model`	string	Yes	Name/identifier of the model used
`generation_config`	object	Yes	Configuration used for code generation (any properties allowed)
`messages`	array	No	Optional array of message objects

Response Fields (Success)

Field	Type	Description
`accuracy`	number	Average accuracy from 0-1 across submissions
`timeout_rate`	number	Share of submission grading processes that timed out in the upstream grading server
`server_timeout_count`	number	Number of submission grading processes that timed out in the upstream grading server

Rate Limit Headers

All successful responses include the following headers:

X-RateLimit-Limit: Maximum requests allowed in the time window
X-RateLimit-Remaining: Number of requests remaining in current window
X-RateLimit-Reset: Human-readable date string when the rate limit window resets

Error Responses

400 Invalid request body

401 Invalid/missing API key

429 Rate limit exceeded

502 Invalid response from evaluation system

504 Evaluation timeout

429 Rate Limit Exceeded Response

{
  "error": "Rate limit exceeded",
  "limit": 10,
  "remaining": 0,
  "reset": "Wed Jan 01 2025 00:00:00 GMT+0000 (Coordinated Universal Time)",
  "retryAfter": 3600
}

The response also includes Retry-After header with seconds to wait.

Example Request (truncated)

curl -X POST https://artificialanalysis.ai/api/v2/critpt/evaluate \
  -H "Content-Type: application/json" \
  -H "x-api-key: your_api_key_here" \
  -d '{
    "submissions": [
      {
        "problem_id": "Challenge_1_main",
        "generated_code": "```python\ndef solution():\n    return 42\n```",
        "model": "gpt-5",
        "generation_config": {
          "use_golden_for_prev_steps": false,
          "parsing": false,
          "multiturn_with_answer": false,
          "use_python": false,
          "use_web_search": false
        }
      },
      # Submission for *all* problems in the public set are required in each grading request
      ...
    ],
    "batch_metadata": {}
  }'

Example Response

{
  "accuracy": 0.0,
  "timeout_rate": 0.0,
  "server_timeout_count": 0
}