Tool market

Artificialanalysis: Get Model Detail

Get detailed information for a specific model by its slug, including benchmark scores, intelligence index, context window size, pricing, and evaluation data. Uses the model's providers page for efficient retrieval. Access AI model benchmarks, hardware performance data, provider leaderboards, and model comparisons from Artificial Analysis. Fulfilled by Parse from artificialanalysis.ai.

Artificialanalysis via Parse

Artificialanalysis: Get Models List

Get a list of all LLM models and their summary metrics including name, slug, creator, and reasoning capability flag. Access AI model benchmarks, hardware performance data, provider leaderboards, and model comparisons from Artificial Analysis. Fulfilled by Parse from artificialanalysis.ai.

Artificialanalysis via Parse

Artificialanalysis: Get Model Providers

Get API providers for a specific model, including detailed model information and a list of provider endpoints with pricing (input/output token costs, cache pricing, feature support like JSON mode and function calling), host details, and performance timescale data. Access AI model benchmarks, hardware performance data, provider leaderboards, and model comparisons from Artificial Analysis. Fulfilled by Parse from artificialanalysis.ai.

Artificialanalysis via Parse

Huggingface: List Top Spaces

List Spaces ranked by the chosen sort criterion. Each Space includes its identifier, title, author, like count, SDK, tags, and timestamps. Results are returned as a single page; pass offset to advance manually. When sort is trendingScore, each item also carries its trending_score. List and discover top Spaces on Hugging Face, sorted by likes, trending score, or recency. Fulfilled by Parse from huggingface.co.

Huggingface via Parse

Tbench: Get Leaderboard

Get leaderboard entries for a specific Terminal-Bench benchmark version. Returns ranked entries sorted by accuracy descending, with optional filtering by search term, agent name, model name, and verified status. Query leaderboard data from the Terminal-Bench benchmark for terminal agents, including rankings, accuracy scores, and agent/model metadata. Fulfilled by Parse from www.tbench.ai.

Tbench via Parse

Ollama: Search Models

Search for models on Ollama by keyword, with optional capability filters, sorting, and parameter size range filtering. Returns a list of matching models with descriptions, capabilities, available sizes, download counts, and pull commands. When min_size or max_size is specified, only models with at least one variant within the given parameter size range are returned. Combining sort=newest with a capability filter may return fewer results than sort=popular. Search and retrieve detailed information about AI models available on Ollama, including model variants, sizes, context windows, and pull commands. Fulfilled by Parse from ollama.com.

Ollama via Parse

Ollama: Get Model Detail

Get detailed information about a specific model including description, capabilities, available parameter sizes, download count, and pull/run commands. Search and retrieve detailed information about AI models available on Ollama, including model variants, sizes, context windows, and pull commands. Fulfilled by Parse from ollama.com.

Ollama via Parse

Cloud Gpus: Get Gpu Pricing

Returns all GPU cloud rental offerings from cloud-gpus.com. Each offering includes the GPU model, price per GPU-hour, GPU count, provisioning tenor, region availability, and availability status. Data is extracted from the site's embedded compressed dataset which contains thousands of instance configurations across 30+ providers. One request fetches the complete dataset; no pagination required. Retrieve GPU cloud rental pricing from cloud-gpus.com, covering 30+ providers with on-demand, reserved, and spot offerings across multiple regions. Fulfilled by Parse from cloud-gpus.com.

Cloud Gpus via Parse

Computeprices: Get Gpu Prices

Returns all GPU cloud rental pricing records from ComputePrices.com. Each record represents a specific (provider, GPU model, GPU count, pricing type) combination with its per-GPU hourly price. Approximately 900-1000 records are returned covering 65+ providers and 50+ GPU models. Optionally filter by pricing type or GPU model slug. One network round-trip. Retrieve GPU cloud rental pricing across all major providers tracked by ComputePrices.com. Returns every GPU offering with price, provider, configuration, and region details. Fulfilled by Parse from computeprices.com.

Computeprices via Parse

Tbench: List Leaderboards

List all available Terminal-Bench leaderboards with their benchmark name, version, and status (live or in progress). Query leaderboard data from the Terminal-Bench benchmark for terminal agents, including rankings, accuracy scores, and agent/model metadata. Fulfilled by Parse from www.tbench.ai.

Tbench via Parse

Nebius: Get Gpu Pricing

Returns every GPU offering listed on Nebius AI Cloud pricing page. Each GPU model produces two records: one for spot (preemptible) pricing and one for on-demand pricing. Prices are USD per single GPU-hour. Models without a published numeric price have price_per_hour as null with availability indicating the reason (unavailable or contact_us). No pagination; returns all offerings in one call. Retrieve GPU cloud rental pricing from Nebius AI Cloud, including all listed GPU models with on-demand and spot (preemptible) per-GPU-hour rates. Fulfilled by Parse from nebius.com.

Nebius via Parse

Designarena: Get Agent Arena Leaderboard

Returns the complete Agent Arena leaderboard combining ELO-based rankings with signal metrics (adoption, sentiment, steerability). Each row includes rank, model name with thinking-effort suffix, provider, net improvement over baseline, and three signal columns with confidence margins. Also returns the leaderboard's last-updated timestamp and total model count. Access the Design Arena Agent Arena leaderboard with ELO rankings, model metadata, and signal metrics for AI coding agents. Fulfilled by Parse from designarena.ai.

Designarena via Parse

Gpus: Get Gpu Pricing

Returns all GPU cloud rental pricing configurations from gpus.io. Each record represents one rentable GPU configuration from a specific provider with exact per-GPU-hour pricing in USD. Supports optional filters for GPU model name, provider name, and region code. Without filters, returns all configurations (2000+). A single upstream request fetches the full dataset; no pagination is needed. Retrieve live GPU cloud rental pricing across 25+ providers, normalized into comparable configurations with filters for GPU model, provider, and region. Fulfilled by Parse from gpus.io.

Gpus via Parse

Together: Get Gpu Pricing

Returns every GPU offering from Together AI's pricing page, covering both Dedicated Inference and GPU Clusters sections. Each row represents one GPU model at one pricing tenor. Prices are per GPU per hour in USD. Makes a single request to the pricing page and parses all GPU hardware tables. Retrieve GPU cloud rental pricing from Together AI, including on-demand and reserved capacity rates for all available GPU hardware. Fulfilled by Parse from www.together.ai.

Together via Parse

Ollama: Get Model Tags

Get all tags/variants for a specific model with detailed information including file sizes, context window lengths, input types, hashes, and pull commands for each variant. Search and retrieve detailed information about AI models available on Ollama, including model variants, sizes, context windows, and pull commands. Fulfilled by Parse from ollama.com.

Ollama via Parse

Epoch: Get Scores

Fetches all FrontierMath benchmark scores for both Tier 4 and Tier 1-3, merged into a single response. Each model carries scores for both tiers (null when not evaluated for a tier). Models are sorted by Tier 4 score descending, then Tier 1-3 score. A single CSV fetch powers the response — no pagination, no parameters. Extracts AI model benchmark scores from Epoch AI's FrontierMath leaderboard. Provides scores for Tier 4 (hardest problems) and Tier 1-3 tiers, along with model release dates and provider information for 100+ AI models. Fulfilled by Parse from epoch.ai.

Epoch via Parse

Producthunt: Get Leaderboard Date Range

Aggregate leaderboard entries over a date range. Fetches each day's leaderboard within the range and returns the top products by upvotes, deduplicated by slug. Each day's fetch is a separate page load, so keep ranges short (1-7 days recommended). Product Hunt API for fetching daily leaderboards, product details, and searching products. Includes support for date range aggregation. Fulfilled by Parse from producthunt.com.

Producthunt via Parse

Llmstxt: Get Companies

Get a list of companies from the llms.txt directory with their website and llms.txt URLs. Supports searching, filtering by category, sorting, and pagination. Returns up to ~20 companies per page. API for the llms.txt directory, enabling discovery of companies and their LLM-friendly documentation URLs. Fulfilled by Parse from directory.llmstxt.cloud.

Llmstxt via Parse

Artificialanalysis: Get Hardware Benchmarks

Get hardware benchmark data for GPUs including system benchmarks with throughput, output speed, latency measurements, pricing, and chip specifications. Access AI model benchmarks, hardware performance data, provider leaderboards, and model comparisons from Artificial Analysis. Fulfilled by Parse from artificialanalysis.ai.

Artificialanalysis via Parse

Epoch: Get Tier4 Scores

Fetches FrontierMath Tier 4 benchmark scores only (the hardest problems, approximately 50 total). Returns all models evaluated on Tier 4, sorted by score descending. Each model includes display name, organization, release date, mean score, standard error, and best score. Extracts AI model benchmark scores from Epoch AI's FrontierMath leaderboard. Provides scores for Tier 4 (hardest problems) and Tier 1-3 tiers, along with model release dates and provider information for 100+ AI models. Fulfilled by Parse from epoch.ai.

Epoch via Parse

Coreweave: Get Gpu Pricing

Returns all GPU offerings from the CoreWeave pricing page. Each offering includes the GPU model, price per hour, GPU count per instance, pricing tenor (on-demand, spot, or inference), and region. Prices shown as 'Contact sales' indicate the offering requires a sales inquiry. The inference tenor represents single-GPU pricing available only in North America. Makes a single request to the pricing page. Retrieve GPU cloud pricing from CoreWeave, including on-demand, spot, and inference pricing across all available regions. Fulfilled by Parse from www.coreweave.com.

Coreweave via Parse

Producthunt: Get Daily Leaderboard

Fetch all product launches from the daily leaderboard for a given date. Returns products ranked by community votes for that day. Each item includes rank, name, slug, tagline, topics, and upvote count. Only the top ~8 featured products are returned per day. Product Hunt API for fetching daily leaderboards, product details, and searching products. Includes support for date range aggregation. Fulfilled by Parse from producthunt.com.

Producthunt via Parse

Artificialanalysis: Get Llm Providers Leaderboard

Get the main LLM API Providers Leaderboard data, including all model endpoints and their performance metrics (speed, latency, price, etc.). Returns a large dataset of provider-model combinations with pricing, timescale performance data, and benchmark scores. Access AI model benchmarks, hardware performance data, provider leaderboards, and model comparisons from Artificial Analysis. Fulfilled by Parse from artificialanalysis.ai.

Artificialanalysis via Parse

Openai: Get Pricing

Get all OpenAI model pricing. Returns each model with its section, pricing tier, and per-token costs. Optionally filter by section name or pricing tier using case-insensitive partial matching. Pricing fields vary by section: text models have input/output/cached_input; image models have modality-based pricing; video models have price_per_second; tools have flat per-call or per-GB pricing. Returns a single page of all matching models. Retrieve OpenAI API model pricing across all categories (Flagship, Multimodal, Image generation, Video generation, Realtime and audio generation, Transcription, Tools, Specialized, Finetuning) and pricing tiers (Standard, Batch, Flex, Priority). Fulfilled by Parse from developers.openai.com.

Openai via Parse