Saylor Innovations Prompt Inject x402 REST
Prompt injection detection - screen text, a web page or tool output for block, review or allow with a risk score
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.
Prompt injection detection - screen text, a web page or tool output for block, review or allow with a risk score
Synap by Linkrra — OpenAI-compatible chat completions for coding and agent workloads on dedicated GPUs. Pay per call in USDC on any network offered in the payment challenge; no account, no API key. Self-hosted open model...
OpenAI-compatible chat completions (local GPU, Quebec/CA)
Fetches any public web page and returns LLM-ready output: title, byline, publish date, canonical URL, word count and clean markdown body text. Query param: url (required).
Batch web extraction: turns up to 5 public URLs into LLM-ready markdown in one paid call (comma-separated urls param; 0.02 USDC regardless of count — under half the per-URL price). Failed URLs come back with ok:false, no...
Low-cost Bitcoin (BTC) 60-minute / 1-hour higher/lower probability, expected return, freshness, and model metadata for autonomous agents.
Deterministically repairs malformed or truncated LLM JSON payloads (missing quotes, trailing commas, markdown fences) while scrubbing embedded prompt-injection payloads.
Calculates exact input, cached-input, and output token costs across frontier LLMs (OpenAI, Anthropic, Gemini, DeepSeek, Meta) and recommends optimal model routing.
Ultra-fast deterministic prompt-injection and wallet-drainer scrubber for agent context windows.
Fetch a public web page and convert it to clean Markdown (title, description, headings, absolute links). LLM-free, deterministic, honours robots.txt. ?url=
Publish a permanent, server-side rendered (SSR) contextual article with JSON-LD schema, DoFollow attribution, /llms.txt indexing & Ed25519 receipt across 93 canonical domains in 12 verticals ($1.00 USDC).
Queued forecast job for btc_usdt. This request returns a job ID immediately; poll the status URL for the result. Fresh inference runs only for missing cache timeframes.
Cheap LLM answer (Llama 3.2 3B on Workers AI): ?q=<prompt up to 500 chars>, returns concise text. Pay-per-call, no API key.
Scan untrusted tool or web responses for prompt-injection and credential/payment exfiltration patterns; return findings plus sanitized content.
llms.txt reader: checks whether a site publishes llms.txt or llms-full.txt (the emerging standard for telling AI agents what a site offers), returns the content (up to 20 KB) and its headings and links. Discover agent-fr...
A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
Automated /llms.txt & Agent Documentation Context Compiler (/v1/llms-generator) — Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle.
Automated /llms.txt & Agent Documentation Context Compiler (/v1/llms-generator) — Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle.
A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
Automated /llms.txt & Agent Documentation Context Compiler (/v1/llms-generator) — Crawls any documentation or SaaS site and compiles a standards-compliant /llms.txt manifest and JSON-LD schema bundle.
AgentDiet Semantic Distillation (/v1/distill) — Strips 85-97% of HTML token bloat
agentdiet-jailbreak-scan: A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized text.
agentdiet-injection-firewall: A2A Indirect Prompt-Injection & Jailbreak Firewall (/v1/prompt-guard) — Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections and returns sanitized t...