AI models & inference

AI video generation API with x402 USDC payment. TTS voiceover, animated text.

MCP server for building and testing AI agents with multi-model experimentation and insights.

Official Korean apartment sale prices (MOLIT). Clean JSON, data global models cannot know — paid pe…

Connect Claude to your Shopify store. Edit themes, pages and products by describing what you want.

10 deterministic micro-tools for agents. x402 on X Layer, zero LLM.

Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.

Live grid carbon intensity, deterministic. Answers "how clean is the grid right now", "gCO2 per kWh in Germany", "cleanest hour to run a job today". Current intensity + forward curve (to 48h) + cleanest and dirtiest slots, from NESO (GB national + 14 DNO regions) and energy-charts/Fraunhofer ISE (DE FR NL BE AT ES IT NO). No LLM, no key. Pair with /api/energy/compute-window for full job scheduling.

Live USGS river-gauge tick, deterministic. Answers "what is the flow at this gauge right now", "is this river high or low vs this week". Returns the latest streamflow (discharge, cfs) and gage height (ft) for one USGS site plus the 7-day min/max range, reading count, site name and coordinates, straight from USGS instantaneous values. Unknown sites 404 before payment. No LLM, no key, public domain.

AI text summarization and analysis (Qwen3-4B, local). Send any text in the 'texto' field (you may start it with an instruction, e.g. 'Summarize in 3 bullets: ...') and get a concise summary or analysis in the same language.

+24 more from Vextorium

Frontier chat on QWEN3 30B A3b FP8 (@cf/qwen/qwen3-30b-a3b-fp8). POST messages[] for reasoning-heavy agent workloads; dynamic token pricing. Hero: GET /heroes/frontier-llm. Tiers: /v1/chat/reasoning, /v1/chat/code, /v1/chat/agent, /v1/chat/70b.

US safety recalls for a VIN, deterministic. Answers "does this car have open recalls", "is this used car safe to buy", "what NHTSA campaigns cover this vehicle". Decodes the VIN via NHTSA vPIC (year, make, model, body, engine) then lists every NHTSA recall campaign for that vehicle: component, summary, remedy, park-outside and do-not-drive flags. No LLM, no key, public domain.

Fast text-to-image with Flux 1 Schnell (@cf/black-forest-labs/flux-1-schnell). POST prompt and optional dimensions; returns base64 image output. Hero: GET /heroes/flux-schnell. Per-generation x402 pricing per USDC per request (see npm run pricing:report).

SIDERA Memory compiles supported Claude, Codex, Grok and Gemini JSONL logs into agent memory: reusable memory.md and lossless raw.tar.zst with source evidence. Processing: 1 MB $0.02; 100 MB $2; 1 GB $18; 5 GB+ from $75, by measured original size. Isolated container per order. This $0.001 call returns service information and ordering steps; processing is purchased separately. Sample: https://shadowharness.com/sidera/#sample

English dictionary definitions by part of speech, with examples, pronunciation and word frequency

Returns natural AI voice audio URL from text prompt via Kokoro. Agents: voice bots, accessibility, narration, TTS. Keywords: text-to-speech, TTS API, voice generation, audio synthesis, AI voice. Keyless, pay-per-call USDC on Base/Solana, $0.01/call, no API key, no signup.

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

Brazilian vehicle reference price (Fipe table) by brand, model and year - price in BRL by fuel type

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

AI chat completions API - pay per request with USDC on Base

Use when you are choosing or monitoring one AI model and need its live prices, price changes, context, status and events. Conditions report for one AI model listed on OpenRouter (GET /v1/models/report?id={model id}): current input/output prices per 1M tokens with 24h and 7d change (absolute and %), standard job cost (10,000 input + 1,000 output tokens, formula shown), context length and modalities, the vendor's own status page indicator and active incidents (unknown when the vendor has no free JSON status feed), listing events in the last 24h and 7d (added, removed, price change, expiration date), days until expiration, sources, timestamps and data age, plus a one-line summary. Every derived value carries its formula. A conditions report, not a ranking: no statement about how well a model performs. Unknown ids get 400 before any payment. JSON. Example (illustrative): GET /v1/models/report?id=openai/gpt-4o → {summary, prices:{input:{usd_per_1m, change_24h}}, standard_job_cost_usd, status, events}. Price: 0.01 RLUSD on XRPL mainnet (xrpl:0; RLUSD issuer rMxCKbEDwqr76QuheSUMdEGf4B9xJ8m5De) or 0.01 USDC on Base.

AI chat completions API - pay per request with USDC on Base