← All headings
AI models & inference
1,003 listings from 521 providers, 773 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 51–75, one row per provider, those answering first · names and descriptions as their source publishes them
- base.mapleai.shop/v1/chat/completionsbase.mapleai.shopOpenAI-compatible chat completion, priced by counted input tokens + max output tokens at per-model ratesLivechecked Evidence 1/4x402x402 Bazaar3 payers2 more from mapleai.shop
- Pocket Networkagent.pocket.networkOpen-weight text embeddings at a fixed model and precision: deterministic vectors for RAG and memory pipelines, identical across suppliers. POST /v1/text with {inputs} (a string or array of strings) and get the embedding vectors as one JSON object. Pay per request in USDC; no account, no API key.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- contextiq.trango-compute.com/api/v1/token-inspector/pricing/x402-v2contextiq.trango-compute.comToken Inspector model pricing (per call)Livechecked Evidence 1/4x402x402 Bazaar3 payers
- Hashing, HMAC & Checksum Suitehash-hmac.underscoredone.comGive this API any text or binary data and it returns its fingerprint under whichever hash algorithms you choose - SHA-256, SHA-512, MD5, BLAKE2, CRC32 and more. It also signs data with a secret key (HMAC) and safely verifies whether an incoming signature matches, using a timing-safe comparison. Language models cannot hash: they emit a string of the right length and character set that is simply wrong, so every webhook check built on a guessed hash is silently broken.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- agentdata-api.sander-van-aard.workers.dev/llm/chatagentdata-api.sander-van-aard.workers.devLLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- ToolRoute by YourAIToolsapi.youraitools.coTool selection API for AI agents (tool routing). Pick the tools an agent needs for a task from a large tool list: send set_id (from the free /v1/register) or tools, plus the task. Returns a ranked shortlist (adaptive 3-12, or k), confidence, matched terms, token savings and the definitions in MCP, OpenAI, Anthropic or Gemini form. BM25, no LLM. Unknown set_id: 404, never charged.Livechecked Evidence 1/4x402x402 Bazaar2 payers3 more from youraitools.co
- GEDX402 Knowledgeembed.gedx402.comRelevance scores for your candidate passages against a query. POST { query, contexts: [{ text }], top_k? } on embed.gedx402.com. Returns response[] of { index, score } sorted by relevance for search and RAG. Example: { query: "vector search", contexts: [{ text: "Embeddings store meaning." }], top_k: 2 } → [{ index: 0, score: 0.92 }].Livechecked Evidence 1/4x402x402 Bazaar2 payers2 more from gedx402.com
- SiteCheck Company Recordsapi.companyrecords-api.workers.devOpen LLM Leaderboard v2 (Hugging Face, archived March 2025): finds open-source language models by name across all 4,576 leaderboard rows and returns average score, IFEval, BBH, MATH Lvl 5, GPQA, MUSR and MMLU-PRO scores, parameter count, likes, license and hub URL, best average first.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- x402 Text Generatoragentx402pay.comReal LLM-backed text generation (Gemini). Pay with upto (billed by output length, max $0.05) or exact (flat $0.05). Base only. Independently monitored by x402-list.com: 100% uptime since Oct 27, 2026, 14/14 x402 compliance checks (as of Oct 31, 2026). Evidence: https://x402-list.com/services/agentx402payLivechecked Evidence 1/4x402x402 Bazaar2 payers
- Deepent Research Agent APIapi.deepentresearch.comDeepent Research — refusal-free LLM inference (per-request)Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Annalistapi.annalist.devRetirement calendar for AI models across platforms: shutdown dates, 'not sooner than' floors, states and recommended replacements from the official Anthropic, OpenAI and Amazon Bedrock deprecation pages, plus Azure, Vertex, Gemini and others, recorded daily so moved dates show. The same model often retires on different dates on different platforms. One model with model=, or upcoming shutdowns. Signed.Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from annalist.dev
- Agent Toolboxagent-toolbox.zafermemon87.workers.devText embeddings with BGE-M3 (multilingual, 1024 dimensions) for search, clustering and RAG: up to 100 texts of up to 8,000 characters per call.Livechecked Evidence 1/4x402x402 Bazaar2 payers5 more from zafermemon87.workers.dev
- AI Crawler Access Testagent-data.centorprat.workers.devTests whether AI search and answer bots (OpenAI, Anthropic, Perplexity, Google, Bing...) can actually read your site: robots.txt per bot (search vs training), a live fetch as each bot vs a browser to catch CDN/WAF blocks, JS-only content, llms.txt and entity schema, with fixes. Up to 3 items per call; failed lookups are not charged.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- PreIPO Feed by Aaron Zhangpreipo-feed.vercel.appOn-chain pre-IPO perps vs private valuation, live: OpenAI and Anthropic perpetuals on Hyperliquid HIP-3 (EntropyIO io:OAI, io:ANTH) converted to implied company valuation, set against the last private round post-money and the IPO valuation target. Premium/discount, funding, open interest, 24h volume; each private anchor keeps source and grade.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Grokzilla x402 Micro Paygrokzilla.shopText or token counts in, cost per model out, cheapest first, from OpenRouter's public price list with a price-fetched-at timestamp. Applies time-of-day pricing. Not charged if the price list is unavailable or no model matches.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- Oblique Marketsapi.oblique.marketsUse when an agent needs chat completion. Returns One bounded chat completion (standard messages request shape) per paid call, with no account to open and no provider key to hold; max 24,000 input characters and 600 output tokens. $0.01.Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from oblique.markets
- x402 Utilsutils.kagurazaka.devCount the tokens of a text for OpenAI models (o200k_base for GPT-4o and later, cl100k_base for GPT-4), with characters, words and lines, to size prompts and estimate cost.Livechecked Evidence 1/4x402x402 Bazaar2 payers
- datastand.dev/api/data/llm-pricingdatastand.devCurrent LLM API pricing, verified by hand every week: input and output USD per million tokens, plus cached-input rates and context windows where the provider publishes them, across Anthropic, OpenAI, Google, DeepSeek, xAI and Together. Every row is read off the provider's own page on its stated date and carries that URL. A row the provider stops publishing is dropped, not carried forward. The free listing counts how many rows carry each column, so the gaps are visible before you pay.Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from datastand.dev
- api.x-402.online/v1/llmapi.x-402.onlineGet a short completion from a capable model, paid per call, with a bounded output of 2000 tokens. LLM inference pay-per-call, no account, no API key: prompt in, completion out (DeepSeek v4, up to 2000 output tokens). STANDARD tier; /v1/llm/pro is the PRO tier with four times the output budget. Original note on $/c…Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from x-402.online
- 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 Bazaar2 payers
- Tanod mlpeektanod.devEmbed texts as 384-dimensional English or multilingual vectors; up to 64 texts, priced per text. USD 0.0005 per text, at least USD 0.001 per call (1-64 texts per call: USD 0.001-0.032). This call: 1 text. Use when an agent needs vector embeddings of texts for semantic search or clustering.Livechecked Evidence 1/4x402x402 Bazaar2 payers6 more from tanod.dev
- 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
- nojunk-llm.mick8511.workers.dev/v1/embeddingsnojunk-llm.mick8511.workers.devAI Chat (LLM) embeddings: OpenAI-compatible text embeddings on BGE-M3 (1024 dimensions, multilingual, up to 32 inputs per call).Livechecked Evidence 1/4x402x402 Bazaar2 payers1 more from mick8511.workers.dev
- 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
- Prompt Caching Reviewapi.aiskills402.comPrompt Caching Review — Reviews ONE Claude API request (tools, system, messages, the cache marks, the model, the sizes and how often it is sent) for the five reasons its prompt cache does not pay off, and lists only those, one line each with a fixed code, the place, why the cache misses and the fix - or exactly No findings. It catches text that changes on every call (a clock, a request id, a user name) at or before the cache mark, a large stable prefix with no mark, a marked prefix shorter than…Livechecked Evidence 1/4x402x402 Bazaar2 payers2 more from aiskills402.com