檢查網站的 llms.txt、Markdown 頁面、robots.txt AI 爬蟲設定與 sitemap，並自動產生 llms.txt 草稿。

LLM inference API: OpenAI-compatible chat completions for 136 AI models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM), paid per call in USDC on Base with x402. No account, no API key, automatic refund if the model fails.

LLM inference API: OpenAI-compatible chat completions for 136 AI models (Claude, GPT, Gemini, Grok, DeepSeek, Qwen, Kimi, GLM), paid per call in USDC on Base with x402. No account, no API key, automatic refund if the model fails.

3 independent LLM perspectives (security, logic, gas) + static analysis. Returns scored findings.

Pay-per-call Gemini LLM inference. x402, USDC on Base, 0.002-0.02 by model tier.

—

Qwen3 30B FP8 frontier — reasoning, code, and agent tiers via ?full=1.

AI chat and summarization powered by Groq Llama 3.3 70B

—

JWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus t

Six checks: llms.txt, llms-full.txt, .md twins, Accept: text/markdown, sitemap.md, alt link. Free.

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

Run a prompt through a LangChain (system + human) chain over Gemini on Vertex AI; optional LangSmith

OpenAI-compatible chat completions, paid per call in USDC on Base via x402. $0.01 per call, no account or API key.

Deterministic repair of broken or LLM-style JSON into valid JSON, $0.005 per call via x402.

x402-powered LLM provider intelligence API. Get recommendations, capability data, and status for AI agent routing decisions. Pay per query in USDC on Base mainnet.

Free paywall co-pilot /v1/resolve. Paid llm-pack $0.005, clean $0.002, extract $0.01. x402 USDC on Base. No free trial. No hub.

LLM API offers pay per call inference on a curated set of frontier models. OpenAI compatible chat completions, Anthropic native messages, the Responses API, and embeddings, billed by exact token usage. Responses are non streaming; set stream to false. The full model catalog is available with an LLM API account at llmapi.ai. This server is a transparent proxy in front of LLM API's own API that s...

OpenAI-compatible /v1/chat/completions pay-per-call, no API keys. Smart free-tier models (llama-3.3-70b class) with automatic upstream failover, Ed25519-signed. 0.005 USDC via x402 on Base. POST {"messages":[{"role":"user","content":"..."}]}.

Ranks models cheapest first by blended USD per 1M tokens (inputShare weights input vs output). Filter by provider, mode, minContextTokens, input/output modality, function calling, vision and price caps. Skips sample_spec and models past their deprecation date.; Looks up pricing for one model by name

Uncensored 27B LLM inference (Qwen3.8-27B) + live data API. OpenAI-compatible chat, 98k ctx, ~230 tok/s, no content filter. x402 pay-per-use USDC on Base: $0.02 per call (4 free/day/IP). Data endpoints: GET /data/news (headlines $0.02), /data/price (crypto+equities+commodities $0.01), /data/signal (prediction-market edge feed $0.05). Agent discovery: /agent.md, /llms.txt, /.well-known/ai-catalog.j

Pay-per-call, OpenAI-compatible LLM API for agents: POST /v1/chat/completions (Llama 3.3 70B or Qwen 2.5 Coder 32B, up to 32,000 characters of messages, up to 1,024 output tokens, optional JSON mode) and POST /v1/embeddings (BGE-M3, 1,024 dimensions, up to 32 inputs per call). Point any OpenAI client at this base URL and pay per request in USDC on Base via x402: no API key, no account, no rate ...

OpenAI-compatible LLM gateway at $0.005/call — change base_url, pay in USDC. Plus pay-per-call market data: multi-oracle price consensus, sentiment, forex, equities, commodities, Brazil macro (BCB/B3) and crypto. No API keys, no accounts. USDC on Base, Solana, Algorand and Polygon via x402.

Multi-LLM Smart Contract Audit: 3 independent LLM perspectives (security, logic, gas) + static pattern scan on Solidity/Vyper source. Severity: clean/low/medium/high/critical. Ed25519-signed, publishable on-chain. POST {"source":"pragma solidity...","language":"solidity"} or {"address":"0x..","chain":"base"} for Sourcify-verified contracts.

Rough LLM token estimate of text from characters and words, as a low-high range by content type. Not a tokenizer.

SYNTHORA LLM Gateway SMART: OpenAI-compatible /v1/chat/completions pay-per-call, no API keys. Large free-tier models (llama-3.3-70b class) with automatic upstream failover, Ed25519-signed. 0.005 USDC via x402 on Base. POST {"messages":[{"role":"user","content":"..."}]} (or {"prompt":"..."}).

Fetch any public web page live and get clean main-content text, light Markdown, page metadata and the outbound link graph. Up to 10 URLs per call, pay per URL. Pick fields (price, author, date) straight from JSON-LD/meta; recovers content from JS-rendered pages without a browser; flags hidden prompt-injection text. Keyless x402 USDC on Base, no signup. Free preview at /web/extract/preview. $0.003 per URL. Ed25519-signed receipts.

63 keyless pay-per-call endpoints for AI agents, paid in USDC on Base over x402: on-chain reads (balances, transactions, token info, token safety, Uniswap V3 price), network checks (RDAP whois, DNS, TLS certificates, IP/ASN, blocklists), email verdict with a 0-100 score and the evidence behind it, OFAC SDN screening, ECB FX rates, weather and time zones. Every answer carries a `next` array with the follow-up call prefilled. $0.001–$0.01 per call. No account, no API key.

x402-paid LLM APIs on a private GPU fleet (Qwen3.8-27B, VL 30B). USDC on Base, settle in seconds via a self-hosted facilitator. Unique: verifier-gated correctness on /premium/deep — wrong answers regenerated free. First call free, no wallet: POST /premium/first.

Historical cloud pricing for AWS, GCP and Azure back to 2014, GPU rental prices across neo-clouds and marketplaces, and LLM token prices per model, as free charts and as an API that agents pay per request in USDC over x402.

Free LLM agent security review: paste your system prompt, get a ~35s report with live jailbreak/injection/extraction probes plus a static audit of which guardrails your spec is missing. No signup.

Runs one language model completion for a text prompt of up to 4000 characters and returns the generated answer as JSON. Price is 0.008 USDC per call.

Deterministic GitHub repository analysis and AGENTS.md generation. No language model is used: every command is quoted from a manifest in the repository and every path is checked against the git tree, so results are reproducible for a given commit.

Deterministic GitHub repository analysis for coding agents. Returns an AGENTS.md with build and test commands quoted from the repository's own manifests, each tagged with the file it came from, plus a directory map and entry points. No language model is used: every path is checked against the git tree and ambiguous areas are marked unverified rather than guessed, so the same commit always returns

Give this API any text or binary data and it returns its fingerprint under whichever hash algorithms you choose - SHA-256, SHA-512, MD5, BLAKE2, CRC32 and more. It also signs data with a secret key (HMAC) and safely verifies whether an incoming signature matches, using a timing-safe comparison. Language models cannot hash: they emit a string of the right length and character set that is simply ...

POST a question; a language model turns it into a compute spec, AgentReeve runs it on recorded data and returns the numbers, the exact spec used and a short answer grounded only in those numbers.

Deepent Research — refusal-free LLM inference (per-request)

Agent-first directory of x402 API services with live uptime monitoring and machine-readable discovery for AI agents (JSON API, OpenAPI 3.1, llms.txt). Per-service endpoints, pricing, response time, and uptime charts. ([API](https://x402-list.com/api/v1/services)) ([OpenAPI](https://x402-list.com/api/v1/openapi.json)) ([llms.txt](https://x402-list.com/llms.txt))

Informational Bittensor allocation analysis API for AI agents, paid with x402 v2 USDC on Base. Supports walletless model portfolio snapshots, wallet-specific preflight flows, OpenAPI, read-only MCP, and llms.txt discovery. ([OpenAPI](https://api.stakao.com/agent/openapi.json) | [Docs](https://stakao.com/docs/ai-agents.md) | [llms.txt](https://stakao.com/llms.txt))

Agent-native LLM inference gateway. 20+ EU-hosted models (DeepSeek, Qwen, Llama, GLM, Mixtral) via x402 USDC micropayments on Base. OpenAI-compatible API, SSE streaming, GDPR-compliant, zero data retention. No API keys — wallet is auth. [Models](https://tx402.ai/v1/models) | [OpenAPI](https://tx402.ai/openapi.json) | [llms.txt](https://tx402.ai/llms.txt) | [Source](https://github.com/Tensorix-ai/agent-gateway)

Fetch a public URL and return clean LLM-ready markdown from static HTML.

Fetch a site's /llms.txt and check its format: H1 title, summary, sections and links, with the problems listed.

Validates an llms.txt file against the llmstxt.org spec for free; /generate drafts a correct llms.txt from a site's own pages, paid in USDC on Base (x402). Pay by sending USDC to the address in the 402 challenge, then retry with header X-PAYMENT-TX: <tx hash>.

LLM inference API (OpenAI- and Anthropic-compatible) with x402 pay-per-request in USDC on Base: keyless requests get a 402 with USDC pricing. Serves open-weights models (Kimi K2.7, GLM 5.2, MiniMax M3, DeepSeek V4 Flash), and agents can also purchase flat-monthly unlimited subscription pools autonomously. ([Agent Card](https://api.cheapestinference.com/.well-known/agent.json) | [MCP](https://api.cheapestinference.com/mcp) | [llms.txt](https://cheapestinference.com/llms.txt))

Webshop agent-readiness score (https robots sitemap llms schema). x402.

Accountless, crypto-paid uncensored open-weight LLM inference with signed execution receipts (OpenAI-compatible).

Fetch any public URL, render client-side JS, strip nav/ads, return clean LLM-ready Markdown.

Current LLM API pricing, verified by hand every week: input and output USD per million tokens, plus cached-input rates and context windows where the provider publishes them, across Anthropic, OpenAI, Google, xAI and Together. Every row is read off the provider's own page on its stated date and carries that URL. A row the provider stops publishing is dropped, not carried forward. The free listin...

LLM cost scout: send your monthly OpenAI API spend in USD and get back the flat ChatGPT/Codex subscription tier that absorbs it through the ProxyLLM gateway, the exact new monthly total and savings, the live model catalog, and machine-readable signup steps an agent can complete autonomously (email OTP, no browser).

Which discovery documents does a host serve? llms.txt, agent card, owners.json, mcp.json.

Pay-per-call JSON tools for AI agents: Indian identifier validation (GSTIN, PAN, TAN, CIN, LLPIN, IFSC, PIN code, UPI ID, vehicle registration), AI-visibility (GEO) audits, AI crawler robots.txt matrices and llms.txt checks. x402 (USDC on Base) or RapidAPI.

Fetch a public http(s) URL and return cleaned markdown, page metadata, same-origin agent discovery files (llms.txt, OpenAPI, ai-plugin), and Lightning pay hints. Free preview at /api/preview. Discovery: /llms.txt, /openapi.json, /api/agent.json. Pay 21 sats Lightning L402: GET returns 402 with macaroon+invoice, pay, retry with Authorization L402 macaroon:preimage and ?url=. Public URLs only; priva

Send habit stats; get ranked next-best actions per habit, each with a rationale and a priority score. Deterministic, no LLM.

Live LLM API price + status radar across 11 providers, with public per-model price HISTORY.

Runs a single prompt against up to 5 LLMs in parallel and returns all responses, token counts, latencies, and costs in one call

Momus football model: 1X2 probabilities, fair odds, correct-score grid and derived markets for one fixture. Deterministic Dixon-Coles, no LLM. Team names are matched loosely.

51 Baidu AI MCP tools: OCR, Vision, LLM, Speech, NLP, Image Gen, Video Gen. 50 free calls/day. No credit card. Pay-per-call from $0.001.

Crypto compliance suite for AI agents. VASP address identification (20,468 addresses, 29 chains), risk scoring (0-100 with signal detection), and sanctions/mixer screening (single + batch). Three endpoints at $0.01 USDC per call on Base. [Source](https://github.com/tedddb-ai/compliance-api) | [llms.txt](https://compliance-api-ruddy.vercel.app/llms.txt)