# /artificialanalysis/models/search

`POST /api/artificialanalysis/models/search`

Price: 20 credits

Search the Artificial Analysis model leaderboard

## How to use it

Independent third-party measurements, so use it when the question is how models compare rather than what a vendor claims. One product name maps to several aliases because a reasoning-effort setting is its own row — read `effort_label` before treating two rows as duplicates. Price and speed here describe the reference host; the per-host spread is /artificialanalysis/models/providers. `intelligence_index` is blended from the scores in `evaluations`, and `is_intelligence_index_estimated` says whether it was measured or inferred.

## Parameters

- `access-token` (string, required)

## Request body

- `timeout` (integer) — Max scrapping execution timeout (in seconds) (default: 300; min: 20; max: 1500)
- `q` (string, nullable) — Keep only models whose name or alias contains this text (examples: "gpt")
- `creators` (array, nullable) — Keep only models from these creators, by creator name or alias (examples: ["openai"])
- `input_modalities` (array, nullable) — Accepted but not applied: this leaderboard surface carries no per-modality flags, so the parameter is currently a no-op (one of: "text", "image", "speech", "video"; examples: ["image"])
- `output_modalities` (array, nullable) — Accepted but not applied: this leaderboard surface carries no per-modality flags, so the parameter is currently a no-op (one of: "text", "image", "speech", "video"; examples: ["text"])
- `open_weights_only` (boolean) — Keep only open-weights models (default: false)
- `reasoning_only` (boolean) — Keep only reasoning models (default: false)
- `exclude_deprecated` (boolean) — Drop models the site marks as deprecated (default: false)
- `min_intelligence_index` (number, nullable) — Minimum blended intelligence index (examples: 50; min: 0)
- `max_intelligence_index` (number, nullable) — Maximum blended intelligence index (examples: 20; min: 0)
- `min_input_price` (number, nullable) — Minimum input price, USD per 1M tokens (examples: 1; min: 0)
- `max_input_price` (number, nullable) — Maximum input price, USD per 1M tokens (examples: 1; min: 0)
- `min_output_price` (number, nullable) — Minimum output price, USD per 1M tokens (examples: 5; min: 0)
- `max_output_price` (number, nullable) — Maximum output price, USD per 1M tokens (examples: 5; min: 0)
- `min_context_window_tokens` (integer, nullable) — Minimum context window, in tokens (examples: 200000; min: 0)
- `min_output_speed` (number, nullable) — Minimum median output speed, tokens per second (examples: 100; min: 0)
- `max_time_to_first_token` (number, nullable) — Maximum median time to first token, in seconds (examples: 1; min: 0)
- `order` (string, nullable) — Result ordering; omitted keeps the site's own leaderboard order (one of: "intelligence-high-to-low", "intelligence-low-to-high", "input-price-low-to-high", "input-price-high-to-low", "output-price-low-to-high", "output-price-high-to-low", "output-speed-high-to-low", "time-to-first-token-low-to-high", "context-high-to-low", "newest", "oldest")
- `count` (integer, required) — Max result count (min: 1)

## Response

### 200 — Successful Response

- `@type` (string) (default: "ArtificialanalysisModel")
- `alias` (string, required)
- `url` (string, required)
- `id` (string, nullable)
- `name` (string, nullable)
- `short_name` (string, nullable)
- `creator_name` (string, nullable)
- `creator_alias` (string, nullable)
- `creator_country` (string, nullable)
- `creator_url` (string, nullable)
- `creator_image` (string, nullable)
- `release_alias` (string, nullable)
- `release_name` (string, nullable)
- `release_date` (string, nullable)
- `knowledge_cutoff_date` (string, nullable)
- `is_deprecated` (boolean, nullable)
- `deprecated_to` (string, nullable)
- `is_reasoning` (boolean, nullable)
- `is_open_weights` (boolean, nullable)
- `open_source_categorization` (string, nullable)
- `license_name` (string, nullable)
- `license_url` (string, nullable)
- `model_weights_url` (string, nullable)
- `openness` (object) (default: {})
- `param_class` (string, nullable)
- `size_class` (string, nullable)
- `parameter_count_billions` (number, nullable)
- `active_parameter_count_billions` (number, nullable)
- `context_window_tokens` (integer, nullable)
- `effort_alias` (string, nullable)
- `effort_label` (string, nullable)
- `effort_level` (integer, nullable)
- `host_model_count` (integer, nullable)
- `reasoning_token_count` (integer, nullable)
- `input_modalities` (array) (default: [])
- `output_modalities` (array) (default: [])
- `intelligence_index` (number, nullable)
- `is_intelligence_index_estimated` (boolean, nullable)
- `intelligence_index_time_per_task` (number, nullable)
- `intelligence_index_cost` (object) (default: {})
- `intelligence_index_cost_per_task` (object) (default: {})
- `intelligence_index_output_tokens_per_task` (object) (default: {})
- `intelligence_index_token_count` (object) (default: {})
- `briefcase` (object) (default: {})
- `timescale_data` (object) (default: {})
- `evaluations` (object, nullable)
  - `@type` (string) (default: "ArtificialanalysisEvaluations")
  - `aime25` (number, nullable)
  - `analyst_agent` (number, nullable)
  - `apex_agents` (number, nullable)
  - `automation_bench` (number, nullable)
  - `automation_bench_partial_score` (number, nullable)
  - `briefcase_total_cost` (number, nullable)
  - `briefcase_breakdown` (object) (default: {})
  - `critpt` (number, nullable)
  - `enterprise_ops_gym` (number, nullable)
  - `gdp_pdf_all_pass` (number, nullable)
  - `gdpval` (number, nullable)
  - `gdpval_normalized` (number, nullable)
  - `gpqa` (number, nullable)
  - `harvey_lab` (number, nullable)
  - `hle` (number, nullable)
  - `ifbench` (number, nullable)
  - `it_bench_sre` (number, nullable)
  - `lcr` (number, nullable)
  - `livecodebench` (number, nullable)
  - `mlcr_overall` (number, nullable)
  - `mmmu_pro` (number, nullable)
  - `omniscience` (number, nullable)
  - `omniscience_accuracy` (number, nullable)
  - `omniscience_non_hallucination` (number, nullable)
  - `omniscience_hallucination_rate` (number, nullable)
  - `scicode` (number, nullable)
  - `tau2` (number, nullable)
  - `tau_banking` (number, nullable)
  - `terminalbench_hard` (number, nullable)
  - `terminalbench_v21` (number, nullable)
  - `terminalbench_v40` (number, nullable)
- `pricing` (object, nullable)
  - `@type` (string) (default: "ArtificialanalysisPricing")
  - `price_class` (string, nullable)
  - `price_1m_input_tokens` (number, nullable)
  - `price_1m_output_tokens` (number, nullable)
  - `cache_hit_price` (number, nullable)
  - `cache_write_price` (number, nullable)
  - `cache_hit_discount_percent` (number, nullable)
  - `price_per_1k_images` (number, nullable)
  - `cost_per_task` (number, nullable)
  - `blended_price_0to1to1` (number, nullable)
  - `blended_price_0to3to1` (number, nullable)
  - `blended_price_0to100to1` (number, nullable)
  - `blended_price_100to1to1` (number, nullable)
  - `blended_price_7to2to1` (number, nullable)
- `performance` (object, nullable)
  - `@type` (string) (default: "ArtificialanalysisPerformance")
  - `median_output_tokens_per_second` (number, nullable)
  - `p05_output_tokens_per_second` (number, nullable)
  - `q25_output_tokens_per_second` (number, nullable)
  - `q75_output_tokens_per_second` (number, nullable)
  - `p95_output_tokens_per_second` (number, nullable)
  - `median_time_to_first_token_seconds` (number, nullable)
  - `p05_time_to_first_token_seconds` (number, nullable)
  - `q25_time_to_first_token_seconds` (number, nullable)
  - `q75_time_to_first_token_seconds` (number, nullable)
  - `p95_time_to_first_token_seconds` (number, nullable)
  - `median_time_to_first_answer_token_seconds` (number, nullable)
  - `median_end_to_end_response_time_seconds` (number, nullable)
  - `median_reasoning_time_seconds` (number, nullable)
  - `time_to_first_answer_token_breakdown` (object) (default: {})
  - `end_to_end_response_time_breakdown` (object) (default: {})
  - `by_prompt_type` (object) (default: {})
  - `data_source` (string, nullable)
  - `data_source_provider_name` (string, nullable)

## Errors

### 422 — Validation Error

The request body did not validate

What to do: Check the fields against this schema. A URN with the wrong prefix is the most common cause.

- `detail` (array)
  - `loc` (array, required)
  - `msg` (string, required)
  - `type` (string, required)
  - `input` (any)
  - `ctx` (object)

### 408

The request ran past its time limit

What to do: Raise `timeout` in the request body, up to the maximum this endpoint documents. Lowering `count` or turning off the `with_*` flags also helps, because less work finishes sooner.

### 412

The entity was not found, or a precondition failed

What to do: Retrying will not help: either the entity does not exist, or the input points at a different one.

### 429

Too many requests: a rate limit or a usage window is exhausted

What to do: When the response carries an X-Retry-After header, wait that many seconds and retry: the same number is in the body as `detail.retry_after`, and the limit clears once that window passes. The message in the body names the limit that was hit.

### 500

Something broke on our side

What to do: Retrying will not help. If it keeps happening, send us the X-Request-ID from the response headers.

### 529

Rate limit reached, or the endpoint is overloaded

What to do: Wait at least 30 seconds, then retry.

## Response envelope

Success: Array of objects (may be empty if no results)

Error: Error may coexist with partial results if it occurs mid-execution. Check X-Error header and status code.

Every response carries these headers:

- `X-Error` — Error message text (present only on error)
- `X-Request-ID` — Unique request identifier
- `X-Execution-Time` — Execution time in seconds
- `X-Result-Count` — How many records the body carries. 0 means an empty result, which is a normal answer and not by itself an error. A non-zero count can come back together with X-Error when the failure happened partway through — read this header and X-Error independently.
- `X-Total-Available-Results` — How many records exist for this query, when the endpoint can say. On a `dry_run` request this is the answer and the body is empty. It saturates: the endpoint's documented maximum means 'at least that many', any smaller number is exact.
- `X-Warning` — Present when the request body carried keys this endpoint does not document. They were ignored, so any filter you meant to apply through them did not apply. Check the spelling against this schema and retry.
- `X-Retry-After` — Seconds to wait before retrying. Present only on 429.