AI Inference

gpt-5.4-long: OpenAI GPT 5.4 (>272K input tokens) chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 2.5/11.25, Standard 5.0/22.5; pick with s…

chatgpt-image-latest: OpenAI ChatGPT Image Latest image generation, paid per call in USDC. OpenAI list $32 per 1M image tokens (1024x1024: low 272, medium 1056, high 416…

gpt-5-nano: OpenAI GPT 5 Nano chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.025/0.2, Standard 0.05/0.4; pick with service_tier. Plus $0…

The full plain text of a Wikipedia article, up to 20,000 characters, ready for LLM context

CRA AGENT data

The full plain text of a Wikipedia article, up to 20,000 characters, ready for LLM context. Content is CC BY-SA 4.0.

Title, description, headings and up to 20,000 characters of clean readable text from an…

CRA AGENT data

Title, description, headings and up to 20,000 characters of clean readable text from any public URL. Built for LLM context. Private and local addresses are refused.

Base token market snapshot: live price, deepest listed pool, 24h volume and on-chain facts for one ERC-20 (no LLM)

Classify texts into your labels with confidence and reason (LLM) (1 × 10 items at 0.040000 USDC each)

Translate text between languages (LLM, structure and placeholders preserved) (1 × 1,000 characters at 0.030000 USDC each)

JSON tier (deterministic, no LLM): verifies a claimed value lives at a named JSON path in a public endpoint's response, by independent double re-fetch. Use it for machin…

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;…

PRESENCE tier (deterministic, no LLM): confirms the claimed value appears on the live page — it does NOT confirm the value is the right answer to the question. Positive…

Validate revocation authority separately from x402 payment and prepare bounded propagation to opted-in verified targets.

Maps caller-supplied agent-commerce role facts into payment, fulfillment, support, and refund boundaries.

Buyer agents can land on public docs but fail to find service purpose, examples, price, limitations, and support path.

Compares agent-commerce quote, checkout, final payment, and order totals for unexplained deltas.

Classifies commerce schema fields for buyer-data minimization risk.

Compares seller checkout facts with caller-supplied agent-rendered buyer views.

Simulates caller-supplied agent checkout state facts for readiness gaps.

Semantic web search (understands intent, not just keyword matching) — for an agent that needs current information, facts, or sources beyond its training data. Returns ra…

Describe a screen in plain English via `?q=` (e.g. 'oversold large caps up today on high volume'). An LLM parses it into a filter, screens the entire US market, optional…

OpenAI-compatible chat completion on NVIDIA Nemotron-3-Nano-4B (nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16, base weights), a small open model served from Taifoon's own GPU: s…

Cross-provider arbitrage analytics for hosted inference. Per-model: cheapest_paid, most_expensive_paid, spread_usd, savings_pct, median_paid_blended, fastest_tps, cheape…

Top 100 recent AI papers ranked by the share of their total citations earned in the most recent calendar year. Papers published in the last 2 years with 3+ citations. Su…

Any URL as clean, LLM-ready content. $0.01 USDC per call on Base, no API key. GET ?url=... (required), format=markdown|text|html (default markdown), max_chars (default 4…