News headlines, latest news

Token supply, total supply. Total supply of any ERC-20 token on Ethereum, Base, Arbitrum, Optimism or Polygon, read live from the contract: raw and decimal-adjusted supply, decimals, name and symbol. Give a 0x address or a known ticker (USDC, USDT, WETH, DAI…). Use to check a token's circulating maximum or compare supply across chains.

Uniswap pool, V3 pool. Uniswap v3 pools for a token pair on Ethereum, Base, Arbitrum, Optimism or Polygon, read live from the factory and each pool: pool address per fee tier (0.01%, 0.05%, 0.3%, 1%), price of each token in the other, current tick, in-range liquidity and both token balances held, deepest pool first. Tokens by 0x address or ticker. Use to find the right pool, check depth before a s

Page contents API (urls or ids, text.maxCharacters), pay per request: clean text, title, author and date of up to 5 pages in one call. No account or API key; failed calls are not charged.

OpenAI-compatible embeddings, pay per request: one input string in, a 1,024-dimension BGE-M3 vector out (multilingual, for search and RAG). No account or API key; failed calls are not charged.

OpenAI-compatible image generation, pay per image: a prompt in, one 1024x1024 FLUX.1 schnell JPEG out as b64_json. No account or API key; failed calls are not charged.

Whale alert, large transfers. Large stablecoin transfers in the last minutes, read live from the network: every USDC and USDT transfer of at least min USD (default 100,000) on Ethereum, Base, Arbitrum, Optimism or Polygon, largest first, with sender, receiver, transaction and block, mints and burns marked. Covers up to 15 minutes on Ethereum and 3 on Base (busiest). Addresses are not labelled. Use

Mistral Small 3.1 chat API. Chat with Mistral AI's Mistral Small 3.1 24B model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "mistral-small" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name.

Qwen2.5 Coder 32B, code LLM API. Chat with Alibaba's Qwen2.5 Coder 32B code model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "qwen-coder" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name.

GPT-OSS 20B chat API. Chat with OpenAI's open-weight gpt-oss-20b reasoning model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens. Also reachable as model "gpt-oss-20b" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by name.

Qwen3 30B chat API. Chat with Alibaba's Qwen3 30B-A3B mixture-of-experts model (Apache 2.0) through one paid HTTP call: send a prompt and an optional system prompt, get the answer, up to 1,024 output tokens; its reasoning is removed from the answer. Also reachable as model "qwen3-30b" on the OpenAI-compatible /v1/chat/completions. No account or provider key. Use when an agent wants this model by n

Content moderation, safety check. Classify a text as safe or unsafe with Meta's Llama Guard 3 and name the hazard categories it falls into (violent and non-violent crimes, sexual content, child exploitation, hate, self-harm, weapons, privacy, defamation, elections and others; 14 in all). Up to 8,000 characters. Also available in the OpenAI moderation shape at /v1/moderations. Use to screen user me

Rerank documents by relevance. Order up to 50 documents by how well each answers a query, with a relevance score from 0 to 1 (BAAI bge-reranker-base, a cross-encoder). Send documents as a JSON array or one per line; each is read up to 2,000 characters, 40,000 in all. Returns the original index, score and text, best first; top_n keeps only the best. Also available in the Cohere-style shape at /v1/r

Agent memory, delete a key. Delete the value saved under a key in your namespace now, before it expires. Answers deleted: false when there was nothing to delete. Values are kept until they expire (at most 30 days) or are deleted; reads anywhere may lag a write made elsewhere by up to a minute. Use to forget a fact or clear task state.

Agent memory, recall. Read the value saved under a key in your namespace with /memory/set, with when it was saved and when it expires. A key that was never saved or has expired is a 404 and is not charged. Values are kept until they expire (at most 30 days) or are deleted; reads anywhere may lag a write made elsewhere by up to a minute. Use to recall what an agent saved in an earlier run.

Agent memory, list keys. List up to 100 keys saved in your namespace, optionally only those starting with a prefix, with their size, save time and expiry; pass the returned cursor for the next page. Values are not included (read them with /memory/get). Values are kept until they expire (at most 30 days) or are deleted; reads anywhere may lag a write made elsewhere by up to a minute. Use to see wha

Agent memory, save. Save a value (up to 8,000 characters of text or JSON) under a key in your own namespace, so an agent can remember facts, preferences or task state between runs. Overwrites an existing key; expires after 1 to 30 days (default 30). Values are kept until they expire (at most 30 days) or are deleted; reads anywhere may lag a write made elsewhere by up to a minute. Use to persist wh

API recommendation. Describe a task in plain words and get the best-matching paid API calls for it from a catalog of 320 tools (web search and page reading, LLM chat, token prices and chain reads on 5 networks, sanctions and company checks, weather, finance and utilities): each pick with the exact call URL, required inputs, price, MCP tool name and whether it is in the free calls. Use when an agen

OpenAI-compatible chat completions for agents, pay per request: Llama 4 Scout by default with function calling (tools, tool_calls), JSON mode and streaming; Llama 3.3 70B, gpt-oss-20b/120b, Qwen3 30B, Qwen2.5 Coder, Mistral Small 3.1 or DeepSeek R1 by model name. No account or API key; failed calls are not charged.

OpenAI-compatible moderation, pay per request: one input in, flagged and categories out (Llama Guard 3, 14 hazard categories mapped onto OpenAI names). No account or API key; failed calls are not charged.

Rerank API, Cohere-style request shape, pay per request: query and up to 50 documents in, relevance scores best first out (BAAI bge-reranker-base). No account or API key; failed calls are not charged.

OpenAI Responses API shape, pay per request: input text or messages, instructions and max_output_tokens in, one completed message and output_text out. Llama 4 Scout by default, Llama 3.3 70B or gpt-oss-120b by model name. No account or API key; failed calls are not charged.

Web search API, neural-search request shape (query, numResults, contents.text), pay per request: top 1-20 results with title and URL, and the page text of the top 5 when contents.text is asked for. Brave Search results; no account or API key; failed calls are not charged.

Answer API (query), pay per request: an answer from live web search results with citations (title, URL). No account or API key; failed calls are not charged.

Solana balance. SOL balance of a Solana wallet, read live from mainnet in lamports and SOL, plus its SPL token accounts (mint, symbol for well-known tokens, decimals, amount) when the public node serves them; otherwise tokens is null with a note. Use to check a Solana wallet before a payment. An address that is not 32-byte base58 is 400, uncharged.

Solana token info. Look up a Solana SPL token by its mint address, live from mainnet: decimals, total supply, whether a mint authority can still create more and whether a freeze authority can freeze holders (two common rug-pull risks), the token program, and, on request, the largest holder accounts with their share of supply. Use before buying or accepting an unknown Solana token. A mint that does