Catalog
Tool catalog
Connect once and your AI can find and run any tool it needs. Below is what it can reach today: tools your agent pays for by the call.
Catalog results
19 tools in Model Benchmarks.
AI Model API Hosts (Price and Speed, by Model Slug)
Given a model slug, returns each API host the source tracks for that model: the host's name and slug; prices in US dollars per million…
$0.0137 per call
Artificial Analysis · Model Benchmarks
AI Model Cost Per Task Benchmark (by Model Slug)
Given a model slug, returns that model's cost-per-task benchmark: the average dollar cost of running a standard task (with a breakdown by…
$0.137 per call
Artificial Analysis · Model Benchmarks
AI Model Cost Per Task Benchmark (Multiple Models)
Returns cost-per-task benchmark data for a set of AI models at once: the average dollar cost of running a standard task per model (with a…
$0.0683 per call
Artificial Analysis · Model Benchmarks
AI Model Leaderboard Search (by Name or Organization)
Searches a community AI-model leaderboard by keyword (a model name or the organization that built it) within a given category, returning…
$0.0137 per call
LMArena · Model Benchmarks
AI Model Search (by Name, Slug, or Short Name)
Searches a catalog of AI models by keyword against model name, slug, and short name, returning each match's release name, release date,…
$0.0137 per call
Artificial Analysis · Model Benchmarks
AI Model Variants (Full List, No Search)
Returns the whole list of AI language model variants tracked by an independent model benchmark catalog, with no search input: one row per…
$0.0273 per call
Artificial Analysis · Model Benchmarks
AI Search Model Leaderboard (Search Arena Rankings)
Returns the current Search Arena leaderboard: every ranked search/retrieval model's position, Elo-style rating with its confidence range,…
$0.0137 per call
LMArena · Model Benchmarks
AI Vision Model Leaderboard (Current Rankings)
Returns the current LMArena Vision Arena leaderboard in a single parameterless call: every ranked vision-capable AI model's rank with its…
$0.0137 per call
LMArena · Model Benchmarks
Best AI Coding Models + Top Text Model Snapshot (LMArena Leaderboard)
One call returns the full LMArena Code Arena leaderboard -- every model's rank, Elo-style rating with its confidence range, vote count,…
$0.0137 per call
LMArena · Model Benchmarks
Claude Model Name Search (Reasoning & Web Search Flags)
Searches a catalog of Claude model names by a name fragment and returns up to 50 matching model names, each with two flags: whether it is a…
$0.001 per call
Anthropic · Model Benchmarks
Full AI Model Catalog (Capabilities & Ranks)
Returns the full catalog of AI models available on the platform in a single call: each model's public and versioned names, publishing…
$0.0137 per call
LMArena · Model Benchmarks
Gemini Model Name Search (Reasoning & Web Search Flags)
Searches a catalog of Gemini model names by a name fragment and returns up to 50 matching model names, each with two flags: whether it is a…
$0.001 per call
Google · Model Benchmarks
LLM API Providers Leaderboard (Speed, Price & Benchmark Scores)
Returns the full LLM API providers leaderboard: every tracked model-endpoint combination (a model as served by a specific hosting…
$0.0137 per call
Artificial Analysis · Model Benchmarks
OpenAI GPT & o-Series Model Name Search (Reasoning & Web Search Flags)
Searches a catalog of OpenAI model names (GPT and o-series) by a name fragment and returns up to 50 matching model names, each with two…
$0.001 per call
OpenAI · Model Benchmarks
Perplexity Model Names by Fragment (Web Search and Reasoning Flags)
Searches the Perplexity model names a web-answer service accepts, matching a fragment of the name, and returns each matching name with two…
$0.001 per call
Perplexity · Model Benchmarks
Speech, Image & Video AI Model Directory (by Creator)
Returns the full catalog of tracked generative AI model families across four categories in one call: image generation, video generation,…
$0.0137 per call
Artificial Analysis · Model Benchmarks
Text-to-Video Arena Leaderboard (Current Rankings)
Returns the current community leaderboard for text-to-video AI models: each model's rank (with a best/worst rank range), Elo-style rating…
$0.0137 per call
LMArena · Model Benchmarks
Top AI Model Leaderboard Overview
Returns the default community AI-model leaderboard overview: the ten top-ranked models, each with its current rank plus a best/worst rank…
$0.137 per call
LMArena · Model Benchmarks
Top AI Models By Leaderboard Category
Returns the top-ranked models in a given leaderboard category (e.g. text, image, video), sorted by rank, up to a requested limit -- each…
$0.0137 per call
LMArena · Model Benchmarks
Every tool has an explicit pricing model and a usage guide written for it and checked against its schema.
You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. Run omnial_execute with dry_run: true for an exact quote.
Search here runs the same omnial_search call your agent makes over MCP: ranked matches, each showing the keyword or field it matched on. It always answers with what it found; an empty result means the catalog carries none of those terms, and the full list is right below.