All projects matching “model”

Jev hires a model for your task and grades the result. Rejected work is refunded.

Check CSV data for missing values, duplicate rows, schema mismatches and invalid types. Returns a deterministic JSON quality report. Up to 1 MB and 10,000 rows. No AI model calls. $0.01 USDC per check. Resubmit the same payment and input to recover a response.

Global weather forecast by latitude/longitude: up to 48 hours of temperature, humidity, wind, cloud cover and next-hour precipitation in UTC with explicit units and model update time. Forecasts, not live observations; missing fields are null and sparse periods are not interpolated. Based on MET Norway data (CC BY 4.0); outage cache is flagged stale.

Latest liquidation map for one coin: price clusters of leveraged liquidation levels with each cluster's share of the map and its exact (on-chain) share, the reference price, open interest on-chain and on centralized exchanges, and the exact vs modeled fraction. Coins: BTC, ETH, SOL, XRP, DOGE, BNB, AVAX, LINK, LTC, ADA, SUI, WIF.

Structured varietal data and verifiable research provenance for 150+ honey varieties, including the obscure long tail foundation models get wrong. Every compositional datum resolves to a real, published source (DOI/PMID). Per variety: color grade (USDA Pfund band with measured or estimated source), intensity, flavor profile, texture, use cases, best-for pairing tags, primary and secondary countrie

Full JSON catalog of verified AI coding-subscription plans across 31 providers (Claude, OpenAI, Cursor, Gemini, and more). Each record: monthly price and cadence, included models, usage ceilings and rate-limit windows, coding-tool lock-in, and pricing provenance with lastChecked dates. Use it to pick the right plan for an agent workload or to compare providers.

Pay $0.01 USDC to ask Omniac, the Omniacs DAO mascot, any question about crypto, data science, or tech. Responses are concise by default. Powered by llama-3.3-70b via Venice.ai. Max question length: 2000 characters. Network: Base Mainnet. Each request sends one natural-language question to the model and returns one direct answer, making it useful for crypto explainers, technical Q&A, research supp

Embeds up to 32 texts on the local Ollama runtime. Returns explicit model and dimensions; no paid third-party API is called.

Prepaid credit of $0.10 for paid API calls without signing each request. On Rota Nacional it pays for the AI API without an account or key: chat with models compatible with OpenAI and Anthropic clients, embeddings, transcription, speech, OCR, image generation and personal-data cleaning, priced per use in Brazilian reais. The same token pays the paid APIs of our other products.

Findings brief for data and API sellers: how AI agents with funded wallets behave at a paywall. 1,416 purchases and refusals across six models and three agent frameworks on x402, with the install checklist. Full text, markdown, September 2026.

The RSMAD Sculpture Park as data: placards and preview images for 37 sculptures. The park is free for people to walk. No 3D model files, no license. $0.50 USDC.

Create image using GPT-Image-1 AI model

What exactly is this aircraft? Resolve an aircraft by FAA N-number and return normalized identity, registration, manufacturer, model, serial and related identity evidence where available.

GPT-OSS 120B open-source language model API - high-quality text generation without API keys

Claude inference. GET this URL → HTTP 402 $0.001 USDC Solana. Pay, retry PAYMENT-SIGNATURE, get JSON. POST {message, modelId} for a full Claude reply. claude, anthropic, inference. Models: anthropic/claude-opus-5 $0.009, anthropic/claude-sonnet-5 $0.006, anthropic/claude-fable-5.1 $0.007, anthropic/claude-fable-5 $0.00

Identify CQC regulated activities and whether England provider registration remains required after modeled exceptions.

Generate one video with a GetVideos public model at the quoted per-request price.

Monexus Terminal API — Model-card watch: launches, silent downgrades, safeguards, policy events by lab. Params: limit (<=50).

Agent data APIs: web search, page crawl, company enrich, X/Twitter mentions — plus cheap LLM. GET any URL → HTTP 402 USDC Solana. Pay, retry PAYMENT-SIGNATURE, get JSON. search, crawl, enrich, twitter, inference. Models: openrouter/free $0.001, google/gemma-4-31b-it:free $0.001, google/gemma-4-26b-a4b-it:free $0.001, n

Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic.

Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic.

Low-cost Bitcoin (BTC) 60-minute / 1-hour higher/lower probability, expected return, freshness, and model metadata for autonomous agents.

Video generation from a text prompt, a start image, reference images, or a reference clip (Kling, Seedance, MiniMax H3, Wan, Veo, Grok Imagine, more), billed at the render's actual cost — from about half provider list price, never above list. Per-model length, resolution, and audio options; the call returns finished video URLs. Menu + prices: GET /api/v1/media/models (free).

Buy prepaid credits for an AI gateway covering chat, image, and video models, paid in USDC or USDG at $1 per credit. Send {usd} with your API key (keys at mystudios.fun/account), then call any paid endpoint with the key instead of paying per call.

HackerNews & Developer Ecosystem Real-Time Sentiment Pulse (/v1/hn-pulse) — Queries live HackerNews discussions, front-page velocity, and developer sentiment on any framework, startup, or AI model. (https://hn-pulse.agentdiet.dev/v1/hn-pulse)

Answer a focused question from 1-3 caller-supplied text sources, with exact excerpts, source hashes, offsets, model-assessed conflicts and evidence gaps. No URL fetching or source authentication. Quote presence is checked; semantic truth/support is not independently proved. 0.01 USDC per completed brief, including insufficient/conflicting evidence; malformed output and execution failures are not s

Simulate a cloud architecture (1-8 resources on AWS, GCP, Azure, OCI or DigitalOcean) under a traffic load and get modeled cost per hour, p50/p95/p99 latency where supported, throughput, error rate, reliability and autoscaling results in one synchronous call. Use it before provisioning or resizing to compare designs. No account or saved simulation; deterministic by seed. $0.003 per call.

Low-cost Bitcoin (BTC) 60-minute / 1-hour higher/lower probability, expected return, freshness, and model metadata for autonomous agents.

Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, gener

OpenAI-compatible LLM inference, paid per call. POST a standard chat completion body with an x402 payment and the response is the completion itself; the API key and remaining balance come back in headers, so the next call can skip payment. Serves MiniMax language models: MiniMax-M3 for long-context reasoning with a 1,048,576-token window, and MiniMax-M2.7 for general chat, agent loops and coding.