Conservatively repair common JSON syntax errors (unquoted keys, single-quoted strings, trailing commas) and parse the result; input is never evaluated as code.

Gemini 3.6 Flash API (google/gemini-3.6-flash): 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 Gemini 3.6 Flash 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 payment; automatic refund if the model fails to answer.

Gemini 3.8 Flash API (google/gemini-3.8-flash): 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 Gemini 3.8 Flash 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 payment; automatic refund if the model fails to answer.

Bitcoin ecosystem new-project radar: latest list of newly launched Bitcoin L1 tokens and inscriptions (BRC-20 4-byte, Runes, Alkanes, Stamps/SRC-20), each with stage, verdict and risk flags plus source links. Research feed for agents tracking new Bitcoin token launches and mints. $0.01. Not investment advice.

Invoice pipeline in one call: PDF to structured Markdown (hallucination-guarded OCR), invoice field extraction, arithmetic verification, optional issuer enrichment. Flat 0.05/document (text PDFs to 20 pages, scans to 3).

Resolve a UK legal company name or registration number to a sourced Companies House profile. Returns company status, incorporation, SIC codes, registered office, filing due dates and overdue flags. Use for company research and CRM enrichment. Ambiguous names return candidates without settlement. Does not verify trading websites or provide credit scores.

Japan net salary calculator for AI agents: annual gross to take-home pay (social insurance + income tax incl. reconstruction surtax + resident tax with adjustment credit). Exact NTA Beppyo-5 table, official Kyokai-Kenpo FY2026 rates, cited primary sources, deterministic. $0.02/call.

TableGrab: give a public URL and get clean, typed JSON tables (headers, row objects, inferred column types, caption/heading context; colspan/rowspan handled; ISO dates and real numbers) or the page's main content as Markdown with title, byline, date and links. Handles HTML, CSV, XLSX and text PDFs. SSRF-safe, no JS rendering (returns js_required). $0.01 per call. Feedback/support: POST /feedback (free) or js4336638@gmail.com.

LLM inference API: OpenAI-compatible chat completions for 100+ AI models (DeepSeek, GPT, Claude, Gemini, Grok, GLM, Qwen, Kimi, Llama, Mistral). Suited for AI agents that need on-demand text generation, coding or tool calling paid per request in USDC on Base with x402: no account, no API key. Model in body.model (GET /v1/models); streaming supported. Exact price in the 402 quote; automatic refund if the model fails.

Claude Haiku 5.5 API (anthropic/claude-haiku-5.5): 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 Claude Haiku 5.5 on demand. Streaming and function calling supported. Exact price in the 402 quote before payment; automatic refund if the model fails to answer.

Qwen3.8 Max API (qwen/qwen3.8-max): 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 Qwen3.8 Max 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 payment; automatic refund if the model fails to answer.

Complete AI-powered smart contract security audit - analyzes code against checklist and provides detailed findings with severity levels. Returns immediately (202 Accepted) with a polling URL. Poll GET {jobStatusUrl} every 5-10 seconds until status is 'completed'. Estimated time: ~120 seconds. PRICING (based on model): DeepSeek: $0.15 USDC, Sonnet: $0.25 USDC, Fable: $0.70 USDC. Payment must match selected model.

GPT-5.5 API (openai/gpt-5.5): 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 GPT-5.5 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 payment; automatic refund if the model fails to answer.

GPT-6 Luna API (openai/gpt-6-luna): 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 GPT-6 Luna 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 payment; automatic refund if the model fails to answer.

GPT-6.1 Sol API (openai/gpt-6.1-sol): 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 GPT-6.1 Sol 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 payment; automatic refund if the model fails to answer.

Kimi K3 API (moonshot/kimi-k3): 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 Kimi K3 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 payment; automatic refund if the model fails to answer.

AI-powered smart contract audit checklist matching - analyzes contract code and returns relevant security checklist items. Returns immediately (202 Accepted) with a polling URL. Poll GET {jobStatusUrl} every 5-10 seconds until status is 'completed'. Estimated time: ~90 seconds. PRICING (based on model): DeepSeek: $0.05 USDC, Sonnet: $0.15 USDC, Fable: $0.30 USDC. Payment must match selected model.

Signed verdict: is this action (action, amount, currency, counterparty, payment instrument) inside the agent's mandate and is the credential active? Evaluates the reserved mandate fields; lists the fields it did not evaluate.

DeepSeek V4.1 Flash API (deepseek/deepseek-v4.1-flash): 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 V4.1 Flash on demand. Streaming and function calling supported. Exact price in the 402 quote before payment; automatic refund if the model fails to answer.

One call for all of an agent's dependencies: npm, PyPI, crates.io and Go packages (new publishers, install scripts, license changes), public API contracts (breaking changes), AI models (retirement dates, price changes), MCP servers (tool changes, uptime) and x402 services (wallet and price changes, flags), for the last 1 to 30 days, with what needs attention first. Signed.