← All headings
AI models & inference
1,003 listings from 491 providers, 788 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 201–225, one row per provider, those answering first · names and descriptions as their source publishes them
- SiteCheck Agent Intel & Devapi.fadeandco.workers.devHugging Face Papers search: arXiv papers matching a query with title, abstract summary, publish date, community upvotes, comment count and arXiv link. Public search API; ranking is Hugging Face's.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Crypto Sentiment Analysisagentforge-taupe.vercel.appSentiment analysis for agents processing crypto/finance text: scores news, governance proposals, and social posts from very bearish to very bullish with per-entity breakdown. Category: inference.Livechecked Evidence 1/4x402x402 Bazaar2 payers3 more from agentforge-taupe.vercel.app
- glim.shLLM chat completion (OpenAI-compatible, streaming supported)Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Quartermaster Embeddingsquartermaster.surewhynot.appText embeddings for semantic search and RAG: one vector per call, 1024 dimensions.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- api.x402node.dev/md/stripapi.x402node.devStrip all Markdown syntax, returning plain text (no headings, links, code, emphasis, lists). Use url param or ?text=.... Built for AI agents feeding markdown to embeddings, TTS, or fulltext search. Accepts payment on Base or Solana — either network works.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Agent Extraction APIfreetier-agent-api.pages.devAI model list prices (USD per 1M input/output/cached tokens, context window, vision/tools/reasoning flags) for ~3,000 models across OpenAI, Anthropic, Google, Mistral, Groq, Bedrock, Azure, Together, Fireworks and more, plus verified free tiers/rate limits of AI APIs. Filters: q, provider, free=yes, max_input_per_m, min_context, vision=yes, tools=yes, sort=input|output|context, limit<=100.Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from freetier-agent-api.pages.dev
- KoreaKitkoreakit.celee.workers.devChoose the grammatically correct Korean particle (은/는, 이/가, 을/를, 과/와, 으로/로 …) for a word, number or acronym, based on its final consonant (받침). For templated Korean text generation.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- api.flashctx.xyz/v1/chat/completionsapi.flashctx.xyzUncensored DeepSeek V4.1 Flash (heretic), 1M-token context, vision, OpenAI-compatible chat completions. Priced per request: $0.4125/M input, $1.65/M output. Streaming supported and recommended for long outputs. Agent guide: https://api.flashctx.xyz/agent.mdLivechecked Evidence 1/4x402x402 Bazaar2 payers
- api.rentaipower.app/v1/chat/completionsapi.rentaipower.appOpenAI-compatible chat completion with openai/gpt-oss-20b (open-weight, Apache 2.0). Send a messages array like the OpenAI Chat Completions API; get one non-streaming answer of up to 1024 tokens. Supports reasoning and multilingual text. Pay per request in USDC, no API key or account. You are charged only when a non-empty answer is returned.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Textokittienda.textokit.storeArgentine peso dollar rates in one GET with no parameters: oficial, blue, MEP, CCL, tarjeta and cripto with buy and sell quotes from DolarApi (open source, MIT), plus the gap percent between the crypto dollar and the official rate, source URL, read time and provider update time. Use this when an agent prices, converts or reports anything in Argentina and needs the real dollar, not only the official one. JSON, no model inference. Free sample at /api/dolar-ar/sample.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- api.myceliasignal.com/oracle/inference/cerebras/pricingapi.myceliasignal.comCerebras model pricing — input/output $/M tokens, context windows — Ed25519 signed attestationLivechecked Evidence 1/4x402x402 Bazaar1 payer13 more from myceliasignal.com
- x402-gatewayx402.freeq.oneLLM Chat: Chat with a language model. OpenAI-compatible /v1/chat/completions interface. Supports 50+ models. Free models (auto, eco, premium) are $0 — paid models (gpt-5.2, claude-opus-5, deepseek-v4-pro, ...) are charged at cost. See /tools/llm_chat/models for the full model list and rates. Pay per call in USDC on Base via x402 — POST https://x402.freeq.one/tools/llm_chat.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- OmniProviderpay.omnidev.techPay-per-call chat completion on the small tier. One request returns one assistant message, limited to 8000 input and 1024 output tokens, at 0.008 USDC per call on Base. Payment settles after the response is produced. A client nonce header makes a retry free of a second charge.Livechecked Evidence 1/4x402x402 Bazaar1 payer1 more from omnidev.tech
- Qwen3.8 Max APIagent402-arb.rosariovitale0096.workers.devQwen3.8 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.Livechecked Evidence 1/4x402x402 Bazaar1 payer25 more from rosariovitale0096.workers.dev
- claim-verificationx402.agentindex.worldCheck whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /verify/sample.Livechecked Evidence 1/4x402x402 Bazaar1 payer6 more from agentindex.world
- Community AI Model Pricing Indexai-data-marketplace-1042299154756.us-central1.run.appFetch a current third-party aggregated model-pricing snapshot from LiteLLM. Buyers should verify final pricing with each provider.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- 402scrape402scrape.vercel.appFetch any public webpage and return clean, agent-ready content for RAG, LLM context, research, and summarization. Strips navigation, ads, and boilerplate from static or JavaScript-rendered pages, typically cutting page size 80%+ to save context tokens and inference cost. Input: url (required), format (markdown/text/json), renderJs (optional, for JS-rendered pages). Returns {success, url, format, data}.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- VerifyLiteverifylite.hydratinghealingtouch.workers.devCryptographically secure, unbiased randomness: whole numbers between min and max (default 1 to 100), or random picks from a list of choices, one or up to 100 per call. Useful because language models are bad at being random: fair draws, sampling, shuffling decisions, and A/B assignment. Not charged for invalid options.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- AiSpace Venicex402.aispace.botVenice Responses API (beta) — OpenAI-compatible structured agent outputs with typed blocks (reasoning, message, tool calls), paid per request in USDC on Base via x402, no API key. No x-venice-responses-mode header → Venice default (OpenAI models native; Venice-only extras stay onLivechecked Evidence 1/4x402x402 Bazaar1 payer1 more from aispace.bot
- Forest Marketshttp--forest-gas-station-mainnet--lcjl27p8lmjs.code.runReturn the latest published U.S. Treasury Daily Treasury Par Yield Curve Rates snapshot across standard maturities from 1 month through 30 years. Forest normalizes one coherent official daily observation, reports missing Treasury tenors as null, and performs no forecast, interpolation, trading signal or secondary-market inference. Base mainnet USDCLivechecked Evidence 1/4x402x402 Bazaar1 payer
- api.strale.io/x402/token-countapi.strale.ioEstimate token count and cost for text across LLM models (GPT-4o, Claude, Gemini, Mistral, Llama). Algorithmic — no API calls.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- HivemindOSapi.hivemindos.appMedia Studio image or video: generates an image (FLUX, Imagen 4, GPT Image, Nano Banana Pro) or a video (Seedance, Kling, Veo 3.1) from a prompt, or gives a video synced sound design (model remaster-audio, dialogue kept). Use when an agent needs an image, a short video or a soundtrack for a silent clip, priced before it pays. $0.04 this call, in USDC on Base; you pay only if it succeeds. HivemindOS SuperAgent API.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- agentproof-murex.vercel.app/schema/inferagentproof-murex.vercel.appJSON Schema inference for APIs - infer schema from sample responses.Livechecked Evidence 1/4x402x402 Bazaar1 payer
- Forest Webhttp--forest-gas-station-mainnet--lcjl27p8lmjs.code.runExtract the main article/content body from one bounded public static HTML page as clean text and conservative Markdown. Forest deterministically selects article-like content, strips common navigation/footer/form/aside/consent chrome and returns bounded metadata. No JavaScript rendering, link following, authentication or model inference. Base mainnet USDCLivechecked Evidence 1/4x402x402 Bazaar1 payer
- tokenplans.devapi.tokenplans.devFull JSON catalog of verified AI coding-subscription plans across 31 providers (Claude, OpenAI, Cursor, Gemini, and more). Each record: monthly price and cadence, included models, usage ceilings and rate-limit windows, coding-tool lock-in, and pricing provenance with lastChecked dates. Use it to pick the right plan for an agent workload or to compare providers.Livechecked Evidence 1/4x402x402 Bazaar1 payer