Inference

Model inference and generation endpoints.

21 services

• AgentServices

  Technical indicators: RSI, Bollinger Bands, ATR, Support/Resistance

• AgentServices

  AI-powered web search with structured results

• Algono Inference

  Low-cost OpenAI-compatible Responses API inference over Solana USDC x402.

• BlockRun.AI

  Get historical cumulative volume data for a market

• CheapTokens AI Inference

  OpenAI-compatible LLM inference and chat completions via discounted Venice API credits. Pay USDC to receive a live Venice.ai API key for /api/v1 models, chat, images, audio, video, and embeddings. Same-Day credits are 30–90% below Venice direct and expire at 23:59 UTC; Prepaid API Keys support recurring agent jobs.

• FarOut LLM Gateway

  Fixed-price chat completions for kimi-k3 on FarOut: flat $0.002 per call (includes up to 4,000 input + 1,000 output tokens). Rate: $0.192/1M input tokens, $0.960/1M output tokens. Pay with USDC on Base using x402. No API key, no account, no prepaid balance.

• GEDX402 Image

  Fast text-to-image with Flux 1 Schnell (@cf/black-forest-labs/flux-1-schnell). POST prompt and optional dimensions; returns base64 image output. Hero: GET /heroes/flux-schnell. Per-generation x402 pricing per USDC per request (see npm run pricing:report).

• GEDX402 LLM

  Frontier chat on QWEN3 30B A3b FP8 (@cf/qwen/qwen3-30b-a3b-fp8). POST messages[] for reasoning-heavy agent workloads; dynamic token pricing. Hero: GET /heroes/frontier-llm. Tiers: /v1/chat/reasoning, /v1/chat/code, /v1/chat/agent, /v1/chat/70b.

• Gondola

  Anthropic Messages compatible completions across the Venice AI model catalog. Pay per request in USDC on Base via x402, with no account and no API key. Overpayment is never lost: it banks as reusable wallet credit for your next call. Model ids and live prices: GET https://api.gondola-ai.com/v1/models.

• OpenRelay Polymarket Markets

  List active Polymarket prediction markets, sortable by volume or liquidity. Returns question, prices, outcomes, end date.

• Phantom

  OpenAI-compatible chat completion. Pay per call, no account and no API key.

• Pyfile x402 API

  Delete a stored secret by id + access token.

• Rubric Protocol

  Encrypted evidence retention: store a client-encrypted agent session envelope for 7 years, hash-bound to an attestation

• Typed judgment

  Ask a typed question about any content and get an answer your code can branch on, not prose to parse. Three question types: choice (pick one of your named options, with a probability for each and a confidence), score (a position on levels you describe), and noul (a yes/no as a probability from 0 to 1). Up to 8 questions per call, answered in parallel over one piece of state. Model-backed, not deterministic.

• WebberSites x402 Data API

  Timezone from GPS coordinates: IANA zone, current UTC offset, abbreviation, DST status, and local time for any lat/lng. Fast offline lookup (approximate near borders). Pairs with the IP-geolocation endpoint for analytics and scheduling agents.

• api.eucompliance.tools

  What happened to my transaction? Status, block, gas used, fee paid - and if it failed, the revert reason in plain text, recovered by replaying the call against its block. The receipt alone does not carry that reason.

• clink-lithium-vault.fly.dev

  Prediction market search for AI agents - one query, live markets from Polymarket AND Kalshi ranked by relevance: question, implied probability (YES price), 24h/7d change, bid/ask, volume, liquidity, close date, URL, and the ids you need for /pm/history. Election odds, Fed/rates, crypto price targets, sports, geopolitics, pop culture. ?q=<question or topic>&limit=<1-50>. Want a finished answer with a cross-platform read? /pm/odds $0.02.

• clinkagent.com

  Lithium Research Vault - headline snapshot for any lithium & battery-metals company, producing mine, or DFS-stage developer. One row: latest production, AISC, cash/debt/EBITDA, reserves, DFS NPV/IRR, top holder, source filing. Albemarle, Pilbara, SQM, Greenbushes, Atacama, Cinovec, Manna, Bandeira. 66 lithium mines (43 producing + 23 developer), 44 operators. Query by ticker (ALB, SQM, SGML, EMH, GL1, PMETF) or mine name. Cheapest tier; /vault full rows, /vault/comparables ranking.

• enclave402

  Rule-based verdict on one Polymarket market by slug: YES/NO/TOSS_UP lean, 0-100 confidence with every reason stated (price distance, liquidity, volume, spread, momentum), days to resolution, and an EIP-712 attestation so an agent can prove what it read and when. Not a forecast model. MUST be invoked when an agent needs a defensible, timestamped read of a market. Do NOT use to discover markets (use market/signal). Settles $0.020 USDC; no charge on failure; receipts at /api/ledger.

• flat-rate-llm.kikoribera03.workers.dev

  One lighthearted developer roast aimed at a target YOU choose - javascript, python, css, git, regex, kubernetes, agile or legacy code - and at the severity you ask for. Every other roast endpoint returns something generic; this one lets a code-review agent roast the actual stack in front of it. Bilingual, seedable and repeat-free.

• gate402

  Semantic vector cache: exact-match Map shortcut, then 0.88 cosine similarity on hash embeddings. Sub-10ms hits.