All projects matching “llm”

LLM chat completions API, OpenAI-compatible: one endpoint for 100+ models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen), no API key or account, pay per call in USDC. Call it when an agent needs an LLM answer, a second opinion, or a model it has no key for. SingIt Ask; models at GET /v1/models.

Scrape website page to Markdown. Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScript rendering (see /extract/rendered), logins or paywalls. Empty pages, bad sections, brow

Deterministic LLM red-team scan: prompt injection, jailbreak, system-prompt extraction and MCP tool abuse in agent prompts.

Prompt-Guard Zero-Trust LLM Jailbreak & Injection Shield: Detects indirect prompt injection, jailbreaks, and tool-poisoning payloads in untrusted inputs.

Rug check for Arc tokens: a 0-100 safety score with the reasons, for a token or a Uniswap v4 pool. One call, one answer: should you buy this Arc pool? Pass ?pool=<v4 pool id> or ?token=0x… and get a 0-100 safety score with the reasons, fusing the pool fee from its key (on Arc the commonest trap: some pools take 49-93% of every trade), our launch watcher's real buy-then-sell round trip and what it

deepseek-ai/DeepSeek-V4-Flash-0731: OpenAI-style chat completion. OpenAI-style chat completion served by DeepSeek only: POST {messages:[{role,content}], max_tokens<=1024}; returns the assistant message, the model and token usage. Returns: an OpenAI-style chat completion from the model the service is named for: POST {messages: [{role, content}], max_tokens <= 1024}; returns the assistant message, t

Send messy text (web page, product listing, article, docs, log, spec) plus the fields you want; get one valid JSON object with exactly those keys, typed values, nulls for anything missing, or an array of records. Offload parsing and save your own context tokens. Run by an AI agent.

GlianaAI - pay-per-call AI: LLM chat (OpenAI-compatible), image, video, music, speech - 100+ models, no signup, USDC. This resource: LLM chat — pass any catalog model id in the body (default minimax-m3). Priced PER REQUEST from the model and input you send, from $0.002000; send the body to read its exact price off the 402. https://ai.glianalabs.com

Rewrites Brazilian Portuguese text into European Portuguese (Portugal): vocabulary, gerund → 'a + infinitive', 'você'. Rule-based detection, local LLM rewrite, re-check of remaining BR markers. Returns unchanged text (free of LLM) when already PT-PT. Text not stored.

Payload Check: data-quality filter for agents. Send any payload (tool/API output, scraped page, LLM answer, generated code, JSON, CSV) and get a 0-100 quality score, pass/warn/fail, tags and concrete issues: invalid or truncated JSON (with auto-repair), JSON Schema mismatches, syntax errors, bot-challenge/captcha/404 scrapes, LLM refusals, placeholders, repetition loops, mojibake. Deterministic, n

Cheap LLM inference. GET this URL → HTTP 402 $0.001 USDC Solana. Pay, retry PAYMENT-SIGNATURE, get JSON. POST {message, modelId} for Gemma / Nemotron / free OpenRouter. inference, cheap llm, gemma. Models: openrouter/free $0.001, google/gemma-4-31b-it:free $0.001, google/gemma-4-26b-a4b-it:free $0.001, nvidia/nemotron-

LLM inference as a pay-per-call commodity — ask anything (?q=...) and get the first live answer from a multi-provider failover chain (Groq, Gemini, paid tiers when configured). One flat price, any subject, no API keys...

Upcoming high-impact macroeconomic events from the live Forex Factory calendar - central bank rate decisions, FOMC, CPI, NFP, GDP and more - each with currency, scheduled time, forecast and previous values plus minutes until release. Filter by impact and currency. The market-moving schedule trading agents check before acting, not in any LLM training set. 经济日历高影响事件. fomc cpi nfp macro events Accept

OpenAI-compatible LLM inference and chat completions via discounted Venice API credits. Pay USDC to receive a live Venice.ai API key for /api/v1 models, chat, images, audio, video, and embeddings. Same-Day credits are 30–90% below Venice direct and expire at 23:59 UTC; Prepaid API Keys support recurring agent jobs.

Web page to markdown (read URL as clean text) for LLM agents: main content only (no nav, cookie banners, ads), with title, description, author, dates, language, headings, internal/external links and JSON-LD types, PLUS a prompt-injection scan of the page (visible text, hidden HTML, comments, invisible Unicode) so your agent knows whether the content tries to give it orders. Fetched from Cloudflare

Headless scraper proxy for AI agents at $0.01 per accepted scrape. Fetch a public HTTPS URL and return clean LLM-ready Markdown. Agent-safety guarantee: output is validated as clean text before serving; binary or garbled content is rejected with no charge.

Get the verified Solidity/Vyper source code for a deployed contract by address, sourced from Sourcify. Returns every source file (path + content), the contract name, language, compiler version and compiler settings (optimizer, evmVersion) — the full human-readable source an agent needs to read, audit or feed to an LLM. Supports Ethereum, Base, Arbitrum, Optimism, Polygon. Unverified contracts retu

Headless scraper proxy for AI agents at $0.01 per accepted scrape. Fetch a public HTTPS URL and return clean LLM-ready Markdown. Agent-safety guarantee: output is validated as clean text before serving; binary or garbled content is rejected with no charge.

LLM chat completion in ONE call (Llama 3.1 8B via Cloudflare Workers AI): POST {messages:[{role,content}]} or {prompt:'...'} — per-call AI inference, zero signup, zero API keys

Repair malformed JSON text into valid parsed JSON: markdown code fences, single quotes, smart quotes, unquoted keys, trailing commas, comments, Python literals (True/None), raw newlines in strings, and truncated output (auto-closes strings, arrays and objects). Returns the parsed value plus a log of every repair applied. Built for LLM output that almost parses. POST a JSON body like: {"text":"```j

DeepSeek V4 Flash Chat API (deepseek/deepseek-chat): LLM inference via OpenAI-compatible chat completions, pay per call in USDC on Base with x402. No API key, no account. Suited for AI agents and scripts that need DeepSeek V4 Flash Chat on demand. When listed, this request cost 30% less than the same request on BlockRun. Streaming and function calling supported. Exact price in the 402 quote before

Know what drove your returns. Deterministic, no-LLM portfolio attribution: send position start/end values, dated cash flows, and a reporting period; get Modified Dietz and XIRR returns, alpha against BTC, ETH, stETH, or a benchmark you supply prices for, plus per-position contribution. Caller-declared data-quality flags, a calculation hash, and an optional EIP-191 signature support transparent rep

Cross-exchange spread tick — ONE $0.02 call returns the live executable spread for a pair across Binance, Coinbase, Kraken, Bybit: best bid venue, best ask venue, spread in bps, and a deterministic TRADE / THIN / NONE verdict. Built for arbitrage monitoring loops; escalate to /api/crypto ($0.07) for the full CEX arbitrage read with fees and transfer paths. 30s freshness, no LLM in the path.

Screen an EVM wallet or contract address BEFORE paying it. Deterministic, keyless compliance / safety gate: checks the address against the OFAC sanctioned crypto-address list and a curated taint set (mixer, hack, scam) and returns a single BLOCK / REVIEW / ALLOW recommendation plus the matched sources, so an AI agent can decide whether to send funds. No API keys, no LLM, one x402 USDC micropayment

x402 APIs grouped into categories (crypto and on-chain, LLM and AI, web and search, media, finance, social, geo and weather, developer tools, other) with listings, origins, well-paid listings, calls and median price.

XML tier (deterministic, no LLM): verifies a claimed value lives at a named path in a public XML document, by independent double re-fetch. Use it for feeds and sitemaps; for JSON use /verify-json, for HTML use /verify. Paths address elements and @attributes (urlset.url[0].loc). String-exact; ambiguous or volatile values return unverifiable, never a guess. First 100 checks per client are free: rese

Scrape any web page: URL to Markdown / HTML to Markdown for LLM context. Readability article extraction strips nav, ads, scripts, and footers while keeping tables and code blocks. Optional render:true executes JavaScript in a headless browser for SPAs (React/Next/Vue).

Extract clean, boilerplate-free readable text from one known public HTTP(S) URL for LLM research or RAG ingestion; private, local, authenticated, paywalled, or blocked resources are not supported. USE WHEN: agent already knows the URL and needs clean page text. DO NOT USE WHEN: agent needs web search, multi-page research, comparison, structured web workflow, or change detection. USE web-intelligen

Al-Mizaan 7-gate validity judge for your OWN bug bounty finding — mechanical gates + adversarial LLM debate (Defender/Attacker/Judge), before you spend a real submission on Sherlock, Immunefi or Cantina

Multi-model chat completions. POST messages[] and set model to any LLM id from GET /v1/models; dynamic USDC pricing scales with model and token usage. Hero: GET /heroes/chat-completions.