Llm topk probability mass x402 REST usage
Return observed probability mass, residual mass and partial entropy from supplied natural log probabilities. Supplied data only; no model call or provider request.
Model inference and embedding endpoints, including routers that front several providers. Context limits and prices change often, so treat the price with its check date.
Return observed probability mass, residual mass and partial entropy from supplied natural log probabilities. Supplied data only; no model call or provider request.
Return directed three-model preference cycles and win totals from supplied pairwise winners. Supplied data only; no model call or provider request.
Return fractional unique-token coverage weights for overlapping embedding windows. Supplied data only; no model call or provider request.
Full detail for one Port66 listing: description, price and minimum offer, condition, size, color, material, brand, category, images, seller, authenticity level, on-chain provenance on Base, and views, saves and offers. P...
Whether a URL may be fetched by 20 named AI and search agents (GPTBot, ChatGPT-User, ClaudeBot, Claude-User, PerplexityBot, Google-Extended, Googlebot, Bingbot, CCBot, and more), parsed to RFC 9309: the rules group that...
Parity evidence for agents that need public OpenAPI, llms.txt, x402, service-catalog, and agent-card declarations compared for consistency.
Looks up the Bodenrichtwert zone containing the point in the open BORIS services of the Länder: Berlin (WFS Bodenrichtwerte 01.01.2026, dl-de/zero-2-0), Lower Saxony (BORIS.NI WFS, VBORIS/BRM model, dl-de/by-2-0; only th...
Linear algebra API: determinant, inverse, transpose, eigenvalues, multiply, or add matrices up to 50x50 with structured array inputs — exact computation, instant. The linear algebra LLMs can't do reliably in-context. For...
Text statistics API: characters, words, sentences, average sentence length, Flesch reading-ease score, estimated reading time, and estimated LLM token count for any text — instant, computed locally, nothing stored. For c...
Cheap short LLM completion (open-weights model on dedicated hardware). POST a prompt, get up to 512 tokens of text back. English and Portuguese.
Fetch any public web page and return clean Markdown of the main content plus title, meta description, word count and absolute links. Strips scripts, navigation and boilerplate. Good for feeding pages to an LLM.
Use when an agent is written against the Anthropic Messages API and must call a model with no account: the same request and response shape - system as its own field, content as text blocks, stop_reason - so pointing your...
AI chat completions API - pay per request with USDC on Base
Chat completion from an open AI model (Llama 3.3 70B by default; Llama 3.1 8B for speed), no account or API key: send messages (or a prompt), get the model's reply. Up to 24,000 characters in and 1,024 tokens out per cal...
AI model prices: return public model catalog, context limits and pricing metadata. Use it when an agent needs a model reference.
Private pay-per-call LLM inference for autonomous agents. Prompts run on our own GPU (house Qwen3 brain, resident model qwen3-14b); settled in USDC on Base L2.
Owner-reported problem lookup for US vehicles: every defect report on file for a year/make/model with component, incident date, and a plain-language description of what went wrong. VIN input is auto-identified. Use it to...
AI Chat (LLM) chat: OpenAI-compatible chat completion on Llama 3.3 70B or Qwen 2.5 Coder 32B (up to 32000 characters in, 1024 tokens out, optional JSON mode).
Fetch and parse robots.txt (+ llms.txt if present) into structured JSON, including which AI crawlers are blocked.
Chat completions with the exact request and response shape of the OpenAI API: point your existing client at this URL and it works, no code change. One flat price per call whatever the size of the prompt or the answer — n...
Focused check of a site's /llms.txt and /llms-full.txt: presence, size and llmstxt.org structural validity (an H1 title, a blockquote summary, sections of markdown links). Returns a readiness score plus fixes. Cheap sub-...
LLM inference at a flat $0.005 per call, with no account, no API key and no token metering. POST a prompt, get the completion: the same price for 10 tokens or 4000, while metered gateways scale with usage. Automatic fail...
Compress a string with Brotli (RFC 7932) and return it as base64. Brotli typically beats gzip by 15-25% on text - useful when bytes matter (e.g. cramming context into an LLM prompt, fitting under a transport cap). Slower...
Count exact LLM tokens for a string using the real OpenAI BPE (o200k_base for gpt-4o/o-series, cl100k_base for gpt-4/gpt-3.5). Deterministic, offline - budget context windows without calling a model.